be.vibedeploy/vibedeploy

Official39 toolsLive

by thomasbillen-netizen

Deploy and host AI-built websites on EU infrastructure, straight from your AI agent.

VibeDeploy MCP Server (be.vibedeploy/vibedeploy)

The VibeDeploy MCP server enables deployment and hosting of AI-built websites on EU infrastructure, controlled from an AI agent. It provides a remote MCP endpoint over streamable HTTP with OAuth sign-in. Supported inputs include Claude artifacts, ChatGPT pages, and various site exports or builds.

🛠️ Key Features

Deploy and host AI-built websites on EU infrastructure
Remote server: https://mcp.vibedeploy.be/mcp (streamable HTTP, OAuth sign-in)
Listed in the official MCP registry as be.vibedeploy/vibedeploy
Website references: vibedeploy.be, vibedeploy.eu
Tool set count: 39

🚀 Use Cases

Deploy a Claude artifact to hosting via an AI agent
Deploy a ChatGPT page to hosting via an AI agent
Deploy other AI-generated site outputs or builds (including Vite builds and plain HTML)

⚡ Developer Benefits

Standardized access through Model Context Protocol (MCP)
Works “straight from your AI agent” using OAuth-authenticated access

⚠️ Limitations

The provided documentation excerpt stops mid-sentence and does not enumerate all supported artifact types or deployment options beyond the examples shown.

Topics

ai-agentschatgptclaudecursordeploymenteugdprhostingmcpmcp-servermodel-context-protocolstatic-site-hosting

Captured live from the server via tools/list.

get_account

Return the team's plan, its limits, and current usage. Use this BEFORE deploy_site or add_custom_domain to know whether a deploy would trip a plan limit, instead of provoking PLAN_LIMIT_EXCEEDED. Also returns the per-token MCP rate-limit ceiling (live remaining is in X-RateLimit-Remaining response header).

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}

deploy_site

Publish a website to a live URL. Deploy a static site or single-page app you built (with AI or by hand) to your platform subdomain (e.g. {name}.vibedeploy.be or {name}.vibedeploy.eu) with automatic SSL, and optionally a custom domain. The fastest way to get a localhost project or an AI-generated site online. DESTRUCTIVE on existing sites: replaces every file on the named site with the supplied set. Files not in this call are deleted. For a new site, creates and provisions it. For an existing site, requires `confirm: "I-want-to-replace-all-files"` to proceed; without confirm the call is rejected before anything is touched. Use update_site (default mode:'patch') if you want to add or change individual files without removing the rest. Use dryRun:true to preview the diff. LARGE FILES: don't split a big text file across a placeholder deploy + chunked follow-ups — a 100-250 KB HTML/CSS/JS file fits in THIS call when sent with encoding:'gzip+base64' (gzip locally, base64 the result; text compresses 3-5×). The site is published at your platform subdomain (e.g. {name}.vibedeploy.be or {name}.vibedeploy.eu). After deploy, call add_custom_domain to also serve at a user-owned hostname.

Parameters4

name	string	required	Site subdomain. Lowercase, 3-63 chars, alphanumeric + hyphens. Must not start or end with a hyphen.
files	any	required	Either an array of {path, content, encoding?} entries OR a path->content map. Total payload <= 500 MB.
confirm	string	optional	Required when the named site already exists. Pass exactly "I-want-to-replace-all-files" to acknowledge that every existing file will be deleted and replaced with this new fileset. Omit on first deploy of a new site. If you want to add or change files without removing the others, use update_site instead — it defaults to patch mode.
dryRun	boolean	optional	If true, validate input + introspect what would change but don't write or delete. Returns the same shape with `dryRun: true` and `deletedFiles` showing what would be removed. Strongly recommended before any deploy_site against an existing site.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Site subdomain. Lowercase, 3-63 chars, alphanumeric + hyphens. Must not start or end with a hyphen."
    },
    "files": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "path": {
                "type": "string"
              },
              "content": {
                "type": "string"
              },
              "encoding": {
                "description": "utf8 (default), base64 (binary files), or gzip+base64 (~3–5× more raw bytes per tool call: gzip locally, base64-encode the gzip output, server gunzips on receive).",
                "type": "string",
                "enum": [
                  "utf8",
                  "base64",
                  "gzip+base64"
                ]
              }
            },
            "required": [
              "path",
              "content"
            ]
          },
          "description": "Array of { path, content, encoding? } file entries. Use this form for binary files."
        },
        {
          "type": "object",
          "propertyNames": {
            "type": "string"
          },
          "additionalProperties": {
            "type": "string"
          },
          "description": "Map of relative file path to UTF-8 content. Use the array form if you need binary support (images, fonts)."
        }
      ],
      "description": "Either an array of {path, content, encoding?} entries OR a path->content map. Total payload <= 500 MB."
    },
    "confirm": {
      "description": "Required when the named site already exists. Pass exactly \"I-want-to-replace-all-files\" to acknowledge that every existing file will be deleted and replaced with this new fileset. Omit on first deploy of a new site. If you want to add or change files without removing the others, use update_site instead — it defaults to patch mode.",
      "type": "string",
      "const": "I-want-to-replace-all-files"
    },
    "dryRun": {
      "description": "If true, validate input + introspect what would change but don't write or delete. Returns the same shape with `dryRun: true` and `deletedFiles` showing what *would* be removed. Strongly recommended before any deploy_site against an existing site.",
      "type": "boolean"
    }
  },
  "required": [
    "name",
    "files"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

update_site

Patch or replace files on an existing site. Defaults to patch mode: only the listed files change; everything else stays. Pass mode:'replace' to wipe-and-replace the whole site (the legacy behaviour, surfaced explicitly so it can't happen by accident). Use `delete: [paths]` in patch mode to remove specific files without wiping the rest. Use `dryRun: true` to preview the diff before committing. LARGE FILES: a 100-250 KB text file fits in one call with encoding:'gzip+base64' (gzip locally, base64 the result) — prefer that over begin_deploy + add_file_chunk streaming. Errors if the site does not exist.

Parameters6

name	string	optional	Site name (preferred).
siteId	string	optional	Site id (alternative to name).
files	any	optional	Files to write. Array form `[{path, content, encoding?}]` (preferred) supports binary via encoding:'base64'; map form `{path: content}` is utf8-only. <= 500 MB total. Optional when `delete` is provided in patch mode for delete-only deploys.
mode	string	optional	patch (default): write only the listed files; everything else stays. replace: delete all existing files and write only the listed ones. Use replace only when you genuinely want to throw away the rest of the site.
delete	array	optional	Patch-mode only: site-relative paths to remove from the pod. Files not in this list are kept. Reported back in `deletedFiles` listing only entries that actually existed. Combine with `files` to atomically rename in one call (write new path + delete old path). Rejected in mode:'replace' since replace already removes anything not in `files`.
dryRun	boolean	optional	If true, validate input + introspect what would change but don't write or delete. Returns the same shape with `dryRun: true` and `deletedFiles` showing what would be removed. Use this before any destructive call (replace mode, or patch with `delete`) to verify the diff.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "description": "Site name (preferred).",
      "type": "string"
    },
    "siteId": {
      "description": "Site id (alternative to name).",
      "type": "string"
    },
    "files": {
      "description": "Files to write. Array form `[{path, content, encoding?}]` (preferred) supports binary via encoding:'base64'; map form `{path: content}` is utf8-only. <= 500 MB total. Optional when `delete` is provided in patch mode for delete-only deploys.",
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "path": {
                "type": "string"
              },
              "content": {
                "type": "string"
              },
              "encoding": {
                "description": "utf8 (default) treats content as a UTF-8 string written verbatim. base64 decodes content from base64 — required for binary files (images, fonts, PDFs); without it the literal base64 string lands on disk and the file is broken. gzip+base64 ships ~3–5× more raw text per tool call: gzip the bytes locally first, then base64-encode the gzip output. Server gunzips before writing.",
                "type": "string",
                "enum": [
                  "utf8",
                  "base64",
                  "gzip+base64"
                ]
              }
            },
            "required": [
              "path",
              "content"
            ]
          }
        },
        {
          "type": "object",
          "propertyNames": {
            "type": "string"
          },
          "additionalProperties": {
            "type": "string"
          }
        }
      ]
    },
    "mode": {
      "description": "patch (default): write only the listed files; everything else stays. replace: delete all existing files and write only the listed ones. Use replace only when you genuinely want to throw away the rest of the site.",
      "type": "string",
      "enum": [
        "patch",
        "replace"
      ]
    },
    "delete": {
      "description": "Patch-mode only: site-relative paths to remove from the pod. Files not in this list are kept. Reported back in `deletedFiles` listing only entries that actually existed. Combine with `files` to atomically rename in one call (write new path + delete old path). Rejected in mode:'replace' since replace already removes anything not in `files`.",
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "dryRun": {
      "description": "If true, validate input + introspect what would change but don't write or delete. Returns the same shape with `dryRun: true` and `deletedFiles` showing what *would* be removed. Use this before any destructive call (replace mode, or patch with `delete`) to verify the diff.",
      "type": "boolean"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

list_sites

List sites for the team this connection belongs to.

Parameters1

includeDeleted

boolean

optional

If true, include soft-deleted sites still in their plan-specific recovery window (status: 'deleted'). Defaults to false: deleted sites can't accept deploys, so an agent rarely wants them in a working list. Use true when you specifically need the recovery view.

Raw schema

{
  "type": "object",
  "properties": {
    "includeDeleted": {
      "description": "If true, include soft-deleted sites still in their plan-specific recovery window (status: 'deleted'). Defaults to false: deleted sites can't accept deploys, so an agent rarely wants them in a working list. Use true when you specifically need the recovery view.",
      "type": "boolean"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

get_site

Return name, url, plan, last deploy time, and recent deploy history.

Parameters2

name	string	optional
siteId	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    },
    "siteId": {
      "type": "string"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

delete_site

Soft-delete a site. confirm=true is required. The site moves to status 'deleted' immediately (its hostname is freed and it stops serving), and is fully purged after the team's recovery window by a sweeper. Use this for the normal 'remove this from my dashboard' flow. The response field 'accepted' is true when the soft-delete is recorded; the response also includes 'purgesAt' so you can tell the user when recovery becomes impossible.

Parameters3

name	string	optional
siteId	string	optional
confirm	boolean	required	Must be exactly true to actually delete the site.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    },
    "siteId": {
      "type": "string"
    },
    "confirm": {
      "type": "boolean",
      "const": true,
      "description": "Must be exactly true to actually delete the site."
    }
  },
  "required": [
    "confirm"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

get_site_analytics

Return a privacy-safe traffic summary for a site over the last `period` days (default 7): total page views, distinct-visitor count, top pages, daily counts, device/browser breakdowns, and Web Vitals averages. Never exposes raw visitor IPs or user-agents.

Parameters3

name	string	optional	Site name. Provide this or siteId.
siteId	string	optional	Site id. Provide this or name.
period	integer	optional	Number of days to aggregate over (1-90). Defaults to 7.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "description": "Site name. Provide this or siteId.",
      "type": "string"
    },
    "siteId": {
      "description": "Site id. Provide this or name.",
      "type": "string"
    },
    "period": {
      "description": "Number of days to aggregate over (1-90). Defaults to 7.",
      "type": "integer",
      "minimum": 1,
      "maximum": 90
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

read_file

Return the bytes of one file currently served by the site. Use this to inspect or edit existing content (call read_file → modify → update_site mode:'patch') so a new chat can iterate on a site without re-uploading. Files larger than 5242880 bytes can't be read in one call. Use list of paths from get_site.filePaths to discover what's available.

Parameters4

name	string	optional	Site name (subdomain) or custom domain. Same lookup rules as get_site.
siteId	string	optional	Alternative to name. One of name\|siteId is required.
path	string	required	Site-relative path of the file to read (e.g. 'index.html', 'assets/main.css'). No leading slash, no '..'.
maxBytes	integer	optional	Per-file size cap. Default 1048576, hard max 5242880. If the file is larger, the call fails with FILE_TOO_LARGE rather than returning truncated bytes — splitting source mid-token would corrupt downstream edits.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "description": "Site name (subdomain) or custom domain. Same lookup rules as get_site.",
      "type": "string"
    },
    "siteId": {
      "description": "Alternative to name. One of name|siteId is required.",
      "type": "string"
    },
    "path": {
      "type": "string",
      "description": "Site-relative path of the file to read (e.g. 'index.html', 'assets/main.css'). No leading slash, no '..'."
    },
    "maxBytes": {
      "description": "Per-file size cap. Default 1048576, hard max 5242880. If the file is larger, the call fails with FILE_TOO_LARGE rather than returning truncated bytes — splitting source mid-token would corrupt downstream edits.",
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 5242880
    }
  },
  "required": [
    "path"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

read_files

Batched version of read_file. Pass up to 50 paths; each is fetched independently with the same per-file rules as read_file. The whole batch is capped at 8388608 bytes total — once that's exhausted, remaining paths fail with BATCH_BUDGET_EXCEEDED so the agent can re-request them in another call.

Parameters4

name	string	optional
siteId	string	optional
paths	array	required	Site-relative paths to read (1..50). Order is preserved in the response.
maxBytesPerFile	integer	optional	Per-file cap. Default 1048576, hard max 5242880.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    },
    "siteId": {
      "type": "string"
    },
    "paths": {
      "minItems": 1,
      "maxItems": 50,
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Site-relative paths to read (1..50). Order is preserved in the response."
    },
    "maxBytesPerFile": {
      "description": "Per-file cap. Default 1048576, hard max 5242880.",
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 5242880
    }
  },
  "required": [
    "paths"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

list_file_hashes

Return SHA-256 + size for every file currently served. Use BEFORE re-deploying to skip files whose content hasn't changed: hash your local files, diff against this list, and only ship the differences via update_site mode:'patch' or begin_deploy → add_files. For SPAs with content-hashed bundle names this typically reduces a full-site redeploy to a handful of files.

Parameters2

name	string	optional	Site name or custom domain. Same lookup rules as get_site.
siteId	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "description": "Site name or custom domain. Same lookup rules as get_site.",
      "type": "string"
    },
    "siteId": {
      "type": "string"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

list_source_files

Return SHA-256 + size for every file in the site's editable source tree (the platform's copy of the pre-build code, not the served dist). Use BEFORE editing so you know which paths exist and which haven't changed since the last build. autoPromote:true will mirror the served dist into source for static-only sites whose source tree is empty (does nothing if the dist looks built).

Parameters4

name	string	optional
siteId	string	optional
autoPromote	boolean	optional	If true and the site has no source tree yet but its dist looks static, copy dist → source on the fly. Default: false.
forcePromote	boolean	optional	If true, mirror dist → source EVEN when dist looks built (e.g. minified Vite output). Use when the original source isn't recoverable and you're willing to edit the build artefact directly. Sets manifest.noBuild=true automatically when no package.json is in the dist, so subsequent build_and_deploy short-circuits to a direct source→dist copy. forcePromote implies autoPromote.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    },
    "siteId": {
      "type": "string"
    },
    "autoPromote": {
      "description": "If true and the site has no source tree yet but its dist looks static, copy dist → source on the fly. Default: false.",
      "type": "boolean"
    },
    "forcePromote": {
      "description": "If true, mirror dist → source EVEN when dist looks built (e.g. minified Vite output). Use when the original source isn't recoverable and you're willing to edit the build artefact directly. Sets manifest.noBuild=true automatically when no package.json is in the dist, so subsequent build_and_deploy short-circuits to a direct source→dist copy. forcePromote implies autoPromote.",
      "type": "boolean"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

read_source_file

Return the bytes of one source file (the platform's editable copy of the pre-build code), letting an AI in any future chat fetch and edit content without needing the original local files. Use list_source_files first to discover paths. For the served dist, use read_file instead.

Parameters4

name	string	optional
siteId	string	optional
path	string	required	Site-relative path inside the source tree, e.g. 'src/App.tsx'.
maxBytes	integer	optional	Per-file size cap. Default 1048576, hard max 5242880.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    },
    "siteId": {
      "type": "string"
    },
    "path": {
      "type": "string",
      "description": "Site-relative path inside the source tree, e.g. 'src/App.tsx'."
    },
    "maxBytes": {
      "description": "Per-file size cap. Default 1048576, hard max 5242880.",
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 5242880
    }
  },
  "required": [
    "path"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

read_source_files

Batched read across the editable source tree (up to 50 paths). Each entry is independent: a missing/oversized file fails its own slot but doesn't abort the batch. Cumulative cap 8388608 bytes; remainder fails with BATCH_BUDGET_EXCEEDED.

Parameters4

name	string	optional
siteId	string	optional
paths	array	required
maxBytesPerFile	integer	optional

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    },
    "siteId": {
      "type": "string"
    },
    "paths": {
      "minItems": 1,
      "maxItems": 50,
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "maxBytesPerFile": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 5242880
    }
  },
  "required": [
    "paths"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

write_source_files

Stage edits to a site's editable source tree (not the live dist). Use list_source_files first to discover what's there. The dist is unchanged until you re-deploy via update_site or run build_and_deploy. Sites have source storage enabled by default; if a legacy site doesn't, the call fails with SOURCE_STORAGE_NOT_ENABLED and the user should contact VibeDeploy support to enable it.

Parameters3

name	string	optional
siteId	string	optional
files	array	required	Files to write into the source tree. Same wire shape as add_files. Re-writing a path overwrites the previous source. Per-file cap 5 MB; per-call cap 50 MB; max 200 files per call.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    },
    "siteId": {
      "type": "string"
    },
    "files": {
      "minItems": 1,
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "path": {
            "type": "string"
          },
          "content": {
            "type": "string"
          },
          "encoding": {
            "description": "utf8 (default) for plain text. base64 for binary files. gzip+base64 for text files where you want to fit ~3x more bytes per tool call: gzip the raw bytes first, then base64-encode. Server gunzips before writing. Useful for shipping bigger source files when you're hitting the per-call output budget.",
            "type": "string",
            "enum": [
              "utf8",
              "base64",
              "gzip+base64"
            ]
          }
        },
        "required": [
          "path",
          "content"
        ]
      },
      "description": "Files to write into the source tree. Same wire shape as add_files. Re-writing a path overwrites the previous source. Per-file cap 5 MB; per-call cap 50 MB; max 200 files per call."
    }
  },
  "required": [
    "files"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

delete_source_file

Remove one file from the site's editable source tree. The served dist is unchanged.

Parameters3

name	string	optional
siteId	string	optional
path	string	required	Source-relative path to delete.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    },
    "siteId": {
      "type": "string"
    },
    "path": {
      "type": "string",
      "description": "Source-relative path to delete."
    }
  },
  "required": [
    "path"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

build_and_deploy

Run a build inside a hardened one-shot pod against the site's editable source tree (write source first via write_source_files / list_source_files autoPromote), then atomically swap the build output into the live dist. Reuses the same build pod the GitProject git-deploy flow uses, so the same isolation guarantees apply: no SA token, no DB/Vault reach, NetworkPolicy-restricted egress. The first run writes the chosen buildCommand/outputDir into Site.sourceManifest; subsequent calls can omit those fields.

Parameters6

name	string	optional
siteId	string	optional
buildCommand	string	optional	Override for the build script's `npm run build` step (e.g. 'npm run build:prod' or 'pnpm vite build'). If omitted, uses the manifest stored on the site, then falls back to 'npm run build'.
outputDir	string	optional	Override for which directory to ship as the new dist. If omitted, uses the manifest, then auto-detects (dist > build > out > public).
rootPath	string	optional	Subdirectory inside the source tree where package.json lives. Empty string = source root. Useful for monorepos.
saveManifest	boolean	optional	If true (default), persists the merged manifest back onto the site so future builds default to these settings. Set false to do a one-off build without changing the saved manifest.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    },
    "siteId": {
      "type": "string"
    },
    "buildCommand": {
      "description": "Override for the build script's `npm run build` step (e.g. 'npm run build:prod' or 'pnpm vite build'). If omitted, uses the manifest stored on the site, then falls back to 'npm run build'.",
      "type": "string"
    },
    "outputDir": {
      "description": "Override for which directory to ship as the new dist. If omitted, uses the manifest, then auto-detects (dist > build > out > public).",
      "type": "string"
    },
    "rootPath": {
      "description": "Subdirectory inside the source tree where package.json lives. Empty string = source root. Useful for monorepos.",
      "type": "string"
    },
    "saveManifest": {
      "description": "If true (default), persists the merged manifest back onto the site so future builds default to these settings. Set false to do a one-off build without changing the saved manifest.",
      "type": "boolean"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

search_files

Search for a literal string or basic regex across all files in either the served dist or the editable source tree. Use this BEFORE batch-reading files to find candidates — saves the 'read 14 batches just to find which 3 files matter' round trip. Pass `target: "source"` to search the editable tree (requires Site.sourceStored=true).

Parameters8

name	string	optional
siteId	string	optional
pattern	string	required	Pattern to search for. Treated literal by default; pass regex:true to use as a basic regex (BusyBox grep BRE — no PCRE features).
target	string	optional	Where to search. 'dist' (default) searches the served files. 'source' searches the editable source tree (requires Site.sourceStored=true).
regex	boolean	optional	When true, the pattern is interpreted as a basic regular expression. Default: false (literal substring match).
caseInsensitive	boolean	optional	Default: false. When true, adds -i to grep.
glob	string	optional	Filename glob filter, e.g. '.js' or '.{js,html}'. Applied via find before grep so we don't read non-matching files.
maxMatches	integer	optional	Cap on returned matches. Default 200, hard max 1000. Truncation is reported via budgetExceeded.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    },
    "siteId": {
      "type": "string"
    },
    "pattern": {
      "type": "string",
      "description": "Pattern to search for. Treated literal by default; pass regex:true to use as a basic regex (BusyBox grep BRE — no PCRE features)."
    },
    "target": {
      "description": "Where to search. 'dist' (default) searches the served files. 'source' searches the editable source tree (requires Site.sourceStored=true).",
      "type": "string",
      "enum": [
        "dist",
        "source"
      ]
    },
    "regex": {
      "description": "When true, the pattern is interpreted as a basic regular expression. Default: false (literal substring match).",
      "type": "boolean"
    },
    "caseInsensitive": {
      "description": "Default: false. When true, adds -i to grep.",
      "type": "boolean"
    },
    "glob": {
      "description": "Filename glob filter, e.g. '*.js' or '*.{js,html}'. Applied via find before grep so we don't read non-matching files.",
      "type": "string"
    },
    "maxMatches": {
      "description": "Cap on returned matches. Default 200, hard max 1000. Truncation is reported via budgetExceeded.",
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 1000
    }
  },
  "required": [
    "pattern"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

deploy_from_url

Publish a website to a live URL from a public archive link. Point this at a tar(.gz) archive on github / gist / S3 and the server fetches and deploys it, no upload from your side. Server-side fetch of a tar(.gz) archive from a public HTTPS URL, then deploy its contents. Sidesteps the case where your code-execution sandbox can reach github / gist / S3 etc. but not mcp.vibedeploy.be's upload endpoint. Equivalent to begin_deploy → POST uploadUrl → commit_deploy in one call. Hostname allowlist enforced; see the archiveUrl description.

Parameters3

name	string	required	Site name to deploy to.
archiveUrl	string	required	Public HTTPS URL of a tar(.gz) archive. The server fetches it (max 100 MB, 60s timeout), parses the tarball, and deploys its files. Allowed hosts: github.com / raw.githubusercontent.com / gist.github.com / gist.githubusercontent.com / gitlab.com / bitbucket.org / codeberg.org / .amazonaws.com / .r2.cloudflarestorage.com / .backblazeb2.com / .workers.dev / *.pages.dev / transfer.sh / 0x0.st / mcp.vibedeploy.be. Use this when your runtime sandbox can reach the host above but can't reach mcp.vibedeploy.be's upload endpoint directly.
mode	string	required	How the archive's files apply: replace wipes the live dist; patch merges them in.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Site name to deploy to."
    },
    "archiveUrl": {
      "type": "string",
      "format": "uri",
      "description": "Public HTTPS URL of a tar(.gz) archive. The server fetches it (max 100 MB, 60s timeout), parses the tarball, and deploys its files. Allowed hosts: github.com / raw.githubusercontent.com / gist.github.com / gist.githubusercontent.com / gitlab.com / bitbucket.org / codeberg.org / *.amazonaws.com / *.r2.cloudflarestorage.com / *.backblazeb2.com / *.workers.dev / *.pages.dev / transfer.sh / 0x0.st / mcp.vibedeploy.be. Use this when your runtime sandbox can reach the host above but can't reach mcp.vibedeploy.be's upload endpoint directly."
    },
    "mode": {
      "type": "string",
      "enum": [
        "replace",
        "patch"
      ],
      "description": "How the archive's files apply: replace wipes the live dist; patch merges them in."
    }
  },
  "required": [
    "name",
    "archiveUrl",
    "mode"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

rehost_images

Download the external images a site references (e.g. from the old site it was rebuilt from), store them on this VibeDeploy site under assets/img/, and rewrite the HTML <img> references to local paths so the site no longer depends on the original. Call this once AFTER deploying a site rebuilt with the Website Converter. Auto-detects the external image URLs from the site's own HTML; downloads are SSRF-guarded, size/count/time capped, and applied atomically (patch mode). Images already hosted on vibedeploy.be are skipped.

Parameters1

name

string

required

Site name (subdomain) whose external images should be downloaded and rehosted locally.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Site name (subdomain) whose external images should be downloaded and rehosted locally."
    }
  },
  "required": [
    "name"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

update_file_content

Apply one or more literal find/replace edits to a single file on the site, in one tool call. Designed for tiny edits where uploading the full file would be wasteful (one nav-button reference, one encoding fix, one env var bump). Each edit must specify how many matches it expects; mismatches abort the whole call with NO writes. For dist edits the change goes live immediately; for source edits you still need to call build_and_deploy.

Parameters4

name	string	required	Site name.
path	string	required	File-relative path inside the chosen target tree.
target	string	optional	Which tree to edit. 'dist' (default) edits the served file directly — visitors see the change immediately. 'source' edits the editable source tree; you'll need build_and_deploy (or it short-circuits via noBuild) to ship.
edits	array	required	Ordered list of edits to apply atomically. Each is `{find, replace, count?}`. If any edit's match count doesn't equal its expected count, the whole call aborts with no writes.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Site name."
    },
    "path": {
      "type": "string",
      "description": "File-relative path inside the chosen target tree."
    },
    "target": {
      "description": "Which tree to edit. 'dist' (default) edits the served file directly — visitors see the change immediately. 'source' edits the editable source tree; you'll need build_and_deploy (or it short-circuits via noBuild) to ship.",
      "type": "string",
      "enum": [
        "dist",
        "source"
      ]
    },
    "edits": {
      "minItems": 1,
      "maxItems": 50,
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "find": {
            "type": "string",
            "minLength": 1,
            "maxLength": 65536,
            "description": "Literal string to find. Not a regex (no escaping needed). Max 64 KB."
          },
          "replace": {
            "type": "string",
            "maxLength": 65536,
            "description": "Literal replacement. Max 64 KB. Empty string to delete the matched text."
          },
          "count": {
            "description": "Expected number of matches. Default 1 (fail if 0 or >1 — protects against unintended bulk edits). Use -1 for replace-all. Use a positive integer to assert an exact count.",
            "type": "integer",
            "minimum": -9007199254740991,
            "maximum": 9007199254740991
          }
        },
        "required": [
          "find",
          "replace"
        ]
      },
      "description": "Ordered list of edits to apply atomically. Each is `{find, replace, count?}`. If any edit's match count doesn't equal its expected count, the whole call aborts with no writes."
    }
  },
  "required": [
    "name",
    "path",
    "edits"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

apply_edits

Apply find/replace edits across MANY files in one tool call. Batch sibling of update_file_content. Per-file edit semantics identical (count: 1 default, -1 = all, positive int asserts exact count). Whole call is atomic across files: validation runs first, writes only proceed if every edit's count check passes.

Parameters3

name	string	required
target	string	optional	Tree to edit, dist (default) or source. Same tree applies to every file in this call.
files	array	required	Files + edits to apply. Up to 25 files / 200 total edits per call. All-or-nothing: if any edit's match count differs from its expected count, NOTHING is written.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    },
    "target": {
      "description": "Tree to edit, dist (default) or source. Same tree applies to every file in this call.",
      "type": "string",
      "enum": [
        "dist",
        "source"
      ]
    },
    "files": {
      "minItems": 1,
      "maxItems": 25,
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "path": {
            "type": "string",
            "description": "File-relative path inside the chosen target."
          },
          "edits": {
            "minItems": 1,
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "find": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 65536
                },
                "replace": {
                  "type": "string",
                  "maxLength": 65536
                },
                "count": {
                  "type": "integer",
                  "minimum": -9007199254740991,
                  "maximum": 9007199254740991
                }
              },
              "required": [
                "find",
                "replace"
              ]
            },
            "description": "Ordered edits applied to THIS file's current state."
          }
        },
        "required": [
          "path",
          "edits"
        ]
      },
      "description": "Files + edits to apply. Up to 25 files / 200 total edits per call. All-or-nothing: if any edit's match count differs from its expected count, NOTHING is written."
    }
  },
  "required": [
    "name",
    "files"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

get_forms_config

Read the form-to-email relay config of a site, plus the resolved delivery mode, the active From address, and (for a custom sender domain) the DNS records to publish and their verification status. Submissions: POST JSON to the returned `endpoint` with Content-Type: application/json (UTF-8). Flat object of form fields (strings/numbers/booleans; checkbox groups may be arrays of strings, joined with ', '). Max 30 fields, 5000 chars/field, 20000 total. Response: {success:true,data:{ok:true}} or {success:false,error:{code,message}}. Rate limit: 10 submits per IP per 10 minutes. Include a hidden honeypot input (default "_gotcha") and leave it empty.

Parameters1

siteName

string

required

The site whose forms-relay config to read.

Raw schema

{
  "type": "object",
  "properties": {
    "siteName": {
      "type": "string",
      "description": "The site whose forms-relay config to read."
    }
  },
  "required": [
    "siteName"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

set_forms_config

Configure the built-in form-to-email relay, fully self-service. Supports a custom From (via a verified sender domain or your own SMTP relay), an explicit Reply-To, and full email branding (subject template, field labels/order, logo, accent color, or a custom HTML body). Requires team role owner or admin. Pass config:null to switch the relay off. If you set a custom `sender` without an `smtpRelay`, the response returns the DNS records to publish; then call verify_forms_sender_domain. Submissions: POST JSON to the returned `endpoint` with Content-Type: application/json (UTF-8). Flat object of form fields (strings/numbers/booleans; checkbox groups may be arrays of strings, joined with ', '). Max 30 fields, 5000 chars/field, 20000 total. Response: {success:true,data:{ok:true}} or {success:false,error:{code,message}}. Rate limit: 10 submits per IP per 10 minutes. Include a hidden honeypot input (default "_gotcha") and leave it empty.

Parameters2

siteName	string	required	The site to configure.
config	any	required	Full config to store (replaces existing). Pass null to disable and clear.

Raw schema

{
  "type": "object",
  "properties": {
    "siteName": {
      "type": "string",
      "description": "The site to configure."
    },
    "config": {
      "anyOf": [
        {
          "type": "object",
          "properties": {
            "enabled": {
              "type": "boolean",
              "description": "Master switch. false keeps the config but the endpoint returns 404."
            },
            "recipients": {
              "minItems": 1,
              "maxItems": 5,
              "type": "array",
              "items": {
                "type": "string"
              },
              "description": "Server-side fixed lead recipients (1-5)."
            },
            "subject": {
              "type": "string",
              "maxLength": 200
            },
            "requiredFields": {
              "maxItems": 30,
              "type": "array",
              "items": {
                "type": "string",
                "maxLength": 100
              }
            },
            "honeypotField": {
              "description": "Hidden field that must stay empty. Default \"_gotcha\".",
              "type": "string",
              "maxLength": 100
            },
            "confirmation": {
              "type": "object",
              "properties": {
                "enabled": {
                  "type": "boolean"
                },
                "emailField": {
                  "description": "Form field with the visitor email. Default \"email\".",
                  "type": "string",
                  "maxLength": 100
                },
                "subject": {
                  "type": "string",
                  "maxLength": 200
                },
                "message": {
                  "type": "string",
                  "maxLength": 2000
                }
              },
              "required": [
                "enabled"
              ],
              "description": "Optional confirmation email to the visitor."
            },
            "allowedOrigins": {
              "description": "Extra origins allowed to POST. The site's own domains are always allowed.",
              "maxItems": 10,
              "type": "array",
              "items": {
                "type": "string"
              }
            },
            "sender": {
              "type": "object",
              "properties": {
                "name": {
                  "description": "Display name, e.g. \"Serso Service Portal\".",
                  "type": "string",
                  "maxLength": 100
                },
                "email": {
                  "type": "string",
                  "description": "From address, e.g. support@serso.be. Only honored once its domain is verified (verify_forms_sender_domain) OR an smtpRelay is set; otherwise mail falls back to the platform address."
                }
              },
              "required": [
                "email"
              ],
              "description": "Custom From sender."
            },
            "replyTo": {
              "description": "Reply-To: \"visitor\" (default), \"none\", a fixed email, or { field: \"<formField>\" }.",
              "anyOf": [
                {
                  "type": "string"
                },
                {
                  "type": "object",
                  "properties": {
                    "field": {
                      "type": "string",
                      "maxLength": 100
                    }
                  },
                  "required": [
                    "field"
                  ]
                }
              ]
            },
            "smtpRelay": {
              "type": "object",
              "properties": {
                "host": {
                  "type": "string",
                  "description": "SMTP server hostname or IP (must be public)."
                },
                "port": {
                  "type": "integer",
                  "minimum": -9007199254740991,
                  "maximum": 9007199254740991,
                  "description": "SMTP port, e.g. 25, 26, 465, 587."
                },
                "security": {
                  "type": "string",
                  "enum": [
                    "none",
                    "starttls",
                    "tls"
                  ],
                  "description": "\"none\" = plaintext, \"starttls\" = upgrade, \"tls\" = implicit TLS."
                },
                "username": {
                  "description": "Omit for a no-auth trusted-host relay.",
                  "type": "string"
                },
                "password": {
                  "description": "Set to store/replace (encrypted at rest). Omit to keep the existing one. null to clear. Never returned on read.",
                  "anyOf": [
                    {
                      "type": "string"
                    },
                    {
                      "type": "null"
                    }
                  ]
                },
                "allowInvalidCert": {
                  "description": "Accept a self-signed/mismatched cert (starttls|tls). Default false.",
                  "type": "boolean"
                }
              },
              "required": [
                "host",
                "port",
                "security"
              ],
              "description": "Deliver via your own SMTP server instead of the platform. Your server then owns SPF/DKIM. Recipients stay server-side — this is not an open relay."
            },
            "template": {
              "type": "object",
              "properties": {
                "subjectTemplate": {
                  "description": "Subject with {fieldName} placeholders. Overrides `subject`.",
                  "type": "string",
                  "maxLength": 200
                },
                "fieldLabels": {
                  "description": "Map raw field name -> human label.",
                  "type": "object",
                  "propertyNames": {
                    "type": "string"
                  },
                  "additionalProperties": {
                    "type": "string"
                  }
                },
                "fieldOrder": {
                  "description": "Display order; unlisted fields follow in submit order.",
                  "type": "array",
                  "items": {
                    "type": "string"
                  }
                },
                "logoUrl": {
                  "description": "https logo URL shown in the email header.",
                  "type": "string"
                },
                "accentColor": {
                  "description": "#RRGGBB accent color.",
                  "type": "string"
                },
                "headerText": {
                  "type": "string",
                  "maxLength": 2000
                },
                "footerText": {
                  "type": "string",
                  "maxLength": 2000
                },
                "bodyHtml": {
                  "description": "Full custom HTML body with {fieldName} placeholders (values HTML-escaped). Overrides the generated table.",
                  "type": "string",
                  "maxLength": 20000
                }
              },
              "description": "Email branding / layout."
            }
          },
          "required": [
            "enabled",
            "recipients"
          ]
        },
        {
          "type": "null"
        }
      ],
      "description": "Full config to store (replaces existing). Pass null to disable and clear."
    }
  },
  "required": [
    "siteName",
    "config"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

verify_forms_sender_domain

Check the DNS records for a site's custom sender domain (DKIM TXT + SPF include). Once the DKIM record is observed, the sender domain is marked verified and the relay sends from the custom From (DKIM-signed). Until then it falls back to the platform address. DNS can take a few minutes to propagate — re-run if it fails the first time. Not needed when the site uses a custom smtpRelay.

Parameters1

siteName

string

required

The site whose custom sender domain to (re)check.

Raw schema

{
  "type": "object",
  "properties": {
    "siteName": {
      "type": "string",
      "description": "The site whose custom sender domain to (re)check."
    }
  },
  "required": [
    "siteName"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

add_custom_domain

Start attaching a user-owned domain to an existing site. Returns a TXT record the user must add at their DNS provider. Idempotent: calling twice with the same (siteName, domain) returns the existing record instead of creating a duplicate. After the TXT is published (typically within minutes; up to 24h), call verify_custom_domain with the returned recordId. The site itself must already exist on a platform subdomain (e.g. {name}.vibedeploy.be or {name}.vibedeploy.eu). Call deploy_site first if it doesn't.

Parameters2

siteName	string	required	The VibeDeploy site name to attach the domain to (e.g. 'tester').
domain	string	required	The user-owned hostname to attach (e.g. 'tester.subsite.site'). Must be a valid FQDN.

Raw schema

{
  "type": "object",
  "properties": {
    "siteName": {
      "type": "string",
      "description": "The VibeDeploy site name to attach the domain to (e.g. 'tester')."
    },
    "domain": {
      "type": "string",
      "description": "The user-owned hostname to attach (e.g. 'tester.subsite.site'). Must be a valid FQDN."
    }
  },
  "required": [
    "siteName",
    "domain"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

verify_custom_domain

Check the TXT record the user added at step 1 and, if found, attach the domain to the site's ingress. If verification fails, the most common cause is DNS propagation delay; wait a few minutes and try again. Once verified, the domain serves the site immediately (HTTPS issues automatically within ~30s).

Parameters2

siteName	string	required	The site the domain was attached to.
recordId	string	required	The recordId returned by add_custom_domain.

Raw schema

{
  "type": "object",
  "properties": {
    "siteName": {
      "type": "string",
      "description": "The site the domain was attached to."
    },
    "recordId": {
      "type": "string",
      "description": "The recordId returned by add_custom_domain."
    }
  },
  "required": [
    "siteName",
    "recordId"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

remove_custom_domain

Remove a custom domain from a site. The site itself is unaffected; only the custom hostname is detached. The {name}.vibedeploy.be subdomain keeps serving the site.

Parameters3

siteName	string	required	The site to detach the domain from.
domain	string	optional	The custom domain to remove (e.g. 'tester.subsite.site'). Provide this OR recordId.
recordId	string	optional	The recordId returned by add_custom_domain. Provide this OR domain.

Raw schema

{
  "type": "object",
  "properties": {
    "siteName": {
      "type": "string",
      "description": "The site to detach the domain from."
    },
    "domain": {
      "description": "The custom domain to remove (e.g. 'tester.subsite.site'). Provide this OR recordId.",
      "type": "string"
    },
    "recordId": {
      "description": "The recordId returned by add_custom_domain. Provide this OR domain.",
      "type": "string"
    }
  },
  "required": [
    "siteName"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

list_custom_domains

Return all custom domains attached to a site. Each entry has a recordId you can pass to verify_custom_domain or remove_custom_domain.

Parameters1

siteName

string

required

The site whose custom domains to list.

Raw schema

{
  "type": "object",
  "properties": {
    "siteName": {
      "type": "string",
      "description": "The site whose custom domains to list."
    }
  },
  "required": [
    "siteName"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

list_dns_records

Read the DNS records VibeDeploy tracks for a site (the records it created/manages on your behalf), oldest first. Returns each record's host, type, and value. Any team member, including viewers, can read DNS records. This tool is read-only and does NOT create, change, or delete any DNS record.

Parameters2

name	string	optional	Site name to look up DNS records for.
siteId	string	optional	Site id to look up DNS records for. Provide name or siteId.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "description": "Site name to look up DNS records for.",
      "type": "string"
    },
    "siteId": {
      "description": "Site id to look up DNS records for. Provide name or siteId.",
      "type": "string"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

check_domain_availability

Check whether a domain can be registered and get an INDICATIVE retail price. IMPORTANT: this is a read-only lookup — it does NOT buy, register, reserve, or pay for any domain, and it changes nothing. The returned price is GROSS (includes 21% VAT) and indicative only. Set alternatives:true to also check the same name across other common TLDs (be, com, net, eu, nl, io, dev, app). Requires a valid team token but is not tied to a specific site.

Parameters2

domain	string	required	The domain to check, e.g. "example.com".
alternatives	boolean	optional	When true, also check the same second-level name across a canonical TLD set (be, com, net, eu, nl, io, dev, app) and return each one's availability + indicative price.

Raw schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "The domain to check, e.g. \"example.com\"."
    },
    "alternatives": {
      "description": "When true, also check the same second-level name across a canonical TLD set (be, com, net, eu, nl, io, dev, app) and return each one's availability + indicative price.",
      "type": "boolean"
    }
  },
  "required": [
    "domain"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

begin_deploy

Opens a staging session for a multi-call deploy. Use when the site is too large to fit in a single deploy_site/update_site call. Pair with add_files (one or more times) OR a single tarball upload to the returned uploadUrl, then commit_deploy. Active session limit per token: 5. Default TTL: 1 hour.

Parameters2

name	string	required	Site name to deploy to. Must already exist; multi-call sessions don't auto-create sites — use deploy_site for that, or call this against an existing site.
mode	string	required	How commit_deploy will apply the staged files. 'replace' wipes the live site and atomic-renames the staged set into place. 'patch' layers staged files on top of the live site (kept files = live + staged; deletes via commit_deploy's `delete` array).

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Site name to deploy to. Must already exist; multi-call sessions don't auto-create sites — use deploy_site for that, or call this against an existing site."
    },
    "mode": {
      "type": "string",
      "enum": [
        "replace",
        "patch"
      ],
      "description": "How commit_deploy will apply the staged files. 'replace' wipes the live site and atomic-renames the staged set into place. 'patch' layers staged files on top of the live site (kept files = live + staged; deletes via commit_deploy's `delete` array)."
    }
  },
  "required": [
    "name",
    "mode"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

add_files

Append files to an open staging session. Call as many times as needed; commit_deploy applies them all at once. Validates path/extension/encoding on every call so a bad file fails fast. Same 500 MB cap as single-call deploys, but cumulative across the session. LARGE TEXT FILES: a file that looks too big to inline (100-250 KB of HTML/CSS/JS) usually still fits in ONE call — gzip it locally, base64 the result, send with encoding:'gzip+base64' (text compresses 3-5×, so ~250 KB of source ≈ ~70 KB on the wire). Prefer that over add_file_chunk: one call, no ordering hazards. Only chunk when a single file exceeds ~250 KB of source even after gzip, or when you have no way to gzip locally. If your environment can run shell but can't reach this host, gzip+base64 via add_files is the fastest path; if it CAN reach this host, begin_deploy's uploadUrl (tarball POST, 100 MB) beats everything.

Parameters2

deployId	string	required	Session id returned by begin_deploy.
files	any	required	Files to append to the staging scratch dir. Same wire shape as deploy_site/update_site — array form supports binary via encoding:'base64'; map form is utf8-only. Re-adding a path overwrites the previously staged version. Cumulative cap across the whole session: 500 MB.

Raw schema

{
  "type": "object",
  "properties": {
    "deployId": {
      "type": "string",
      "description": "Session id returned by begin_deploy."
    },
    "files": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "path": {
                "type": "string"
              },
              "content": {
                "type": "string"
              },
              "encoding": {
                "description": "utf8 (default) for plain text. base64 for binary files (images, fonts, PDFs). gzip+base64 ships ~3–5× more raw text per tool call: gzip the bytes locally first, then base64. Server gunzips before writing. Per-file decoded size capped at 500 MB.",
                "type": "string",
                "enum": [
                  "utf8",
                  "base64",
                  "gzip+base64"
                ]
              }
            },
            "required": [
              "path",
              "content"
            ]
          }
        },
        {
          "type": "object",
          "propertyNames": {
            "type": "string"
          },
          "additionalProperties": {
            "type": "string"
          }
        }
      ],
      "description": "Files to append to the staging scratch dir. Same wire shape as deploy_site/update_site — array form supports binary via encoding:'base64'; map form is utf8-only. Re-adding a path overwrites the previously staged version. Cumulative cap across the whole session: 500 MB."
    }
  },
  "required": [
    "deployId",
    "files"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

add_file_chunk

Stream a single file across multiple calls when its content exceeds the per-MCP-call output budget. LAST RESORT — try these first: (1) add_files with encoding:'gzip+base64' fits ~250 KB of text source in ONE call (gzip locally, base64, send — no chunking, no ordering hazards); (2) begin_deploy's uploadUrl takes a 100 MB tarball in one HTTP POST if your sandbox can reach mcp.vibedeploy.be; (3) deploy_from_url if the files are fetchable from a public URL. Only chunk when none of those work. When you DO chunk, gzip+base64 each chunk too — it quadruples the source bytes per chunk. Mark the first chunk with isFirst=true (truncates + mkdir) and the last with isLast=true (returns assembled size). Send chunks for the same path serially — concurrent chunks interleave and corrupt the file.

Parameters7

deployId	string	required	Session id returned by begin_deploy.
path	string	required	Target path inside the site root, e.g. 'portaal-admin.html'. Same path validation as add_files.
content	string	required	This chunk's bytes. Either raw UTF-8 (default) or base64-encoded — set encoding accordingly. PRACTICAL CHUNK SIZE: bounded by your LLM client's tool-output token budget, NOT by VibeDeploy's server. Empirically ~80 KB of base64 (≈60 KB raw bytes) per chunk is the safe upper bound for current Claude / GPT clients before tool output gets truncated. The server itself accepts up to 100 MB per call (Caddy cap) and 500 MB cumulative across the session. If you keep hitting truncation: split into smaller chunks, OR sidestep tool-output entirely via `deploy_from_url` (publish a tarball to github raw / gist / S3 → 1 tool call) or POST to begin_deploy's uploadUrl from your code-execution sandbox if it can reach mcp.vibedeploy.be.
encoding	string	optional	utf8 (default), base64 (binary files), or gzip+base64 (compress this chunk's bytes locally first; server gunzips before append). Encoding is per-chunk — you can mix across chunks of the same file (e.g. gzip+base64 for big text chunks, base64 for binary tail).
isFirst	boolean	required	True on the FIRST chunk of a file. Truncates any existing scratch entry at this path and creates parent directories. Subsequent chunks must set false.
isLast	boolean	required	True on the FINAL chunk. Triggers an assembled-size stat and refreshes session file count. Mid-stream chunks set false.
expectedByteOffset	integer	optional	Optional alignment check. The byte offset where THIS chunk should start in the assembled file: 0 for isFirst, otherwise the sum of all prior chunks' decoded bytes for this path. If the server's actual offset disagrees, the call fails with MISALIGNED_CHUNK before any bytes are written — catches the classic 'split base64 on a 4-char boundary that wasn't a byte boundary' bug. Omit to skip the check.

Raw schema

{
  "type": "object",
  "properties": {
    "deployId": {
      "type": "string",
      "description": "Session id returned by begin_deploy."
    },
    "path": {
      "type": "string",
      "description": "Target path inside the site root, e.g. 'portaal-admin.html'. Same path validation as add_files."
    },
    "content": {
      "type": "string",
      "description": "This chunk's bytes. Either raw UTF-8 (default) or base64-encoded — set encoding accordingly. PRACTICAL CHUNK SIZE: bounded by your LLM client's tool-output token budget, NOT by VibeDeploy's server. Empirically ~80 KB of base64 (≈60 KB raw bytes) per chunk is the safe upper bound for current Claude / GPT clients before tool output gets truncated. The server itself accepts up to 100 MB per call (Caddy cap) and 500 MB cumulative across the session. If you keep hitting truncation: split into smaller chunks, OR sidestep tool-output entirely via `deploy_from_url` (publish a tarball to github raw / gist / S3 → 1 tool call) or POST to begin_deploy's uploadUrl from your code-execution sandbox if it can reach mcp.vibedeploy.be."
    },
    "encoding": {
      "description": "utf8 (default), base64 (binary files), or gzip+base64 (compress this chunk's bytes locally first; server gunzips before append). Encoding is per-chunk — you can mix across chunks of the same file (e.g. gzip+base64 for big text chunks, base64 for binary tail).",
      "type": "string",
      "enum": [
        "utf8",
        "base64",
        "gzip+base64"
      ]
    },
    "isFirst": {
      "type": "boolean",
      "description": "True on the FIRST chunk of a file. Truncates any existing scratch entry at this path and creates parent directories. Subsequent chunks must set false."
    },
    "isLast": {
      "type": "boolean",
      "description": "True on the FINAL chunk. Triggers an assembled-size stat and refreshes session file count. Mid-stream chunks set false."
    },
    "expectedByteOffset": {
      "description": "Optional alignment check. The byte offset where THIS chunk should start in the assembled file: 0 for isFirst, otherwise the sum of all prior chunks' decoded bytes for this path. If the server's actual offset disagrees, the call fails with MISALIGNED_CHUNK before any bytes are written — catches the classic 'split base64 on a 4-char boundary that wasn't a byte boundary' bug. Omit to skip the check.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    }
  },
  "required": [
    "deployId",
    "path",
    "content",
    "isFirst",
    "isLast"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

commit_deploy

Atomically apply a staging session's files to the live site. Runs preflight + secret/malware scan against the complete staged set; on failure the session stays open and can be re-attempted or aborted. For replace-mode against a site with existing files, requires confirm:"I-want-to-replace-all-files".

Parameters4

deployId	string	required	Session id returned by begin_deploy.
confirm	string	optional	Required only for replace-mode commits against a site that already has files. Pass exactly "I-want-to-replace-all-files" to acknowledge that the live files will be deleted and replaced with the staged set.
delete	array	optional	Patch-mode only: site-relative paths to remove from the live site as part of this commit. Useful for renames (write new path via add_files, delete old path here).
dryRun	boolean	optional	If true, preview what commit would do without touching the live site or scratch dir. Returns the diff (filesDeployed, deletedFiles) plus would-be confirmation gate / preflight outcomes. Skips the secret/malware scan to keep the preview fast — the real commit will still scan. Recommended before any replace-mode commit on a populated site.

Raw schema

{
  "type": "object",
  "properties": {
    "deployId": {
      "type": "string",
      "description": "Session id returned by begin_deploy."
    },
    "confirm": {
      "description": "Required only for replace-mode commits against a site that already has files. Pass exactly \"I-want-to-replace-all-files\" to acknowledge that the live files will be deleted and replaced with the staged set.",
      "type": "string",
      "const": "I-want-to-replace-all-files"
    },
    "delete": {
      "description": "Patch-mode only: site-relative paths to remove from the live site as part of this commit. Useful for renames (write new path via add_files, delete old path here).",
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "dryRun": {
      "description": "If true, preview what commit would do without touching the live site or scratch dir. Returns the diff (filesDeployed, deletedFiles) plus would-be confirmation gate / preflight outcomes. Skips the secret/malware scan to keep the preview fast — the real commit will still scan. Recommended before any replace-mode commit on a populated site.",
      "type": "boolean"
    }
  },
  "required": [
    "deployId"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

abort_deploy

Discard a staging session and its scratch dir. Live site is untouched. Returns immediately; cleanup is best-effort and the sweeper will retry if it fails.

Parameters1

deployId

string

required

Session id to abort.

Raw schema

{
  "type": "object",
  "properties": {
    "deployId": {
      "type": "string",
      "description": "Session id to abort."
    }
  },
  "required": [
    "deployId"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

list_deploys

Return staging sessions for the team this token belongs to. Defaults to currently-active ones (open + committing). Up to 50 rows.

Parameters1

status

string

optional

Filter by status. Default lists 'open' and 'committing' (the actionable ones). Pass an explicit status to inspect history.

Raw schema

{
  "type": "object",
  "properties": {
    "status": {
      "description": "Filter by status. Default lists 'open' and 'committing' (the actionable ones). Pass an explicit status to inspect history.",
      "type": "string",
      "enum": [
        "open",
        "committing",
        "committed",
        "aborted",
        "expired"
      ]
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

list_history

Return the most recent 50 deploy and snapshot history entries for a site, newest first. Includes the source (how it was triggered), an optional label, the associated Longhorn snapshot name (if any), the file count, and the number of secrets detected. Any team member can read history.

Parameters2

name	string	optional
siteId	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    },
    "siteId": {
      "type": "string"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

list_snapshots

List the Longhorn volume snapshots for a site. Snapshots are point-in-time backups of the site's served files. Any team member can list snapshots. Returns NO_VOLUME if the site has no volume yet (it has never been deployed).

Parameters2

name	string	optional
siteId	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    },
    "siteId": {
      "type": "string"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

create_snapshot

Take a point-in-time Longhorn snapshot of a site's served files. This is an additive backup — it does not change anything served. It records a manual-snapshot history entry and runs retention cleanup. Viewers cannot create snapshots. Returns NO_VOLUME if the site has no volume yet (it has never been deployed).

Parameters3

name	string	optional
siteId	string	optional
label	string	optional	Optional human-readable label for this backup.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    },
    "siteId": {
      "type": "string"
    },
    "label": {
      "description": "Optional human-readable label for this backup.",
      "type": "string",
      "maxLength": 200
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

README.md4 KBView on GitHub

VibeDeploy MCP Server

Deploy and host AI-built websites on EU infrastructure, straight from your AI agent.

Remote server: https://mcp.vibedeploy.be/mcp (streamable HTTP, OAuth sign-in) Official MCP registry: be.vibedeploy/vibedeploy Website: vibedeploy.be · vibedeploy.eu

What it does

You build a site with your AI (a Claude artifact, a ChatGPT page, a Lovable or Bolt export, a Vite build, plain HTML). VibeDeploy is the missing last step: the agent deploys it to a live HTTPS URL in one tool call, and can keep editing and redeploying it later from the same conversation.

Hosting runs on Kubernetes in Belgium: automatic SSL, custom domains, deploy history with snapshots and rollback, staging, a forms relay for static contact forms, and GDPR-friendly EU data residency by default.

No local install is needed. This is a remote MCP server: you add one URL to your client and sign in once. Every account starts with a 14-day free trial, no card required.

Quick start

Claude Code

bash

claude mcp add --transport http vibedeploy https://mcp.vibedeploy.be/mcp

Claude Desktop / claude.ai

Settings → Connectors → Add custom connector → https://mcp.vibedeploy.be/mcp

Cursor / Windsurf / other MCP clients

json

{
  "mcpServers": {
    "vibedeploy": { "url": "https://mcp.vibedeploy.be/mcp" }
  }
}

The first tool call opens a browser window to authorize your VibeDeploy account. After that, try:

"Deploy this site to VibeDeploy and give me the URL."

Tools

38 tools, grouped by what they let the agent do:

Area	Tools
Deploy	`deploy_site`, `build_and_deploy`, `deploy_from_url`, chunked uploads via `begin_deploy` / `add_files` / `add_file_chunk` / `commit_deploy` / `abort_deploy`
Sites	`list_sites`, `get_site`, `update_site`, `delete_site`, `get_site_analytics`, `check_domain_availability`
Files	`read_file`, `read_files`, `search_files`, `list_file_hashes`, `apply_edits`, `update_file_content`, `rehost_images`
Source of truth	`list_source_files`, `read_source_file`, `read_source_files`, `write_source_files`, `delete_source_file` (an editable source tree per site, so agents can do incremental edits and rebuilds)
Domains and DNS	`add_custom_domain`, `list_custom_domains`, `verify_custom_domain`, `remove_custom_domain`, `list_dns_records`
Snapshots and history	`create_snapshot`, `list_snapshots`, `list_deploys`, `list_history`
Account and forms	`get_account`, `get_forms_config`, `set_forms_config`, `verify_forms_sender_domain`

Typical flows

Claude artifact to live URL: Claude builds an artifact, you say "deploy this", the agent ships it and replies with the address. Details: hosting Claude artifacts.
Localhost project to production: the agent runs your build, deploys the output folder, and the URL outlives your laptop. Details: deploy localhost.
Custom domain: add_custom_domain plus one CNAME at your registrar; SSL issues automatically.
Safe iteration: every deploy is snapshotted, so a bad regeneration rolls back in one call.

Notes for client authors and agents

Transport is streamable HTTP at a single endpoint; authorization is standard OAuth (the server is its own issuer at mcp.vibedeploy.be).
Large sites: add_files splits between files, add_file_chunk splits within one file (isFirst / isLast); request bodies are capped at 100 MB.
The platform also supports a no-MCP path: a single deploy-guide file you paste into any chat AI, which teaches it to publish over plain HTTPS. See what is MCP hosting for how the two paths compare.

Support

VibeDeploy is operated by Serso BV (Belgium). All hosting layers, control plane, builds and data live in the EU.

Install

Tools (39)

get_accountdeploy_siteupdate_sitelist_sitesget_sitedelete_siteget_site_analyticsread_file

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://mcp.vibedeploy.be/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "vibedeploy": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.vibedeploy.be/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

VibeDeploy MCP Server (be.vibedeploy/vibedeploy)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

get_account

deploy_site

update_site

list_sites

get_site

delete_site

get_site_analytics

read_file

read_files

list_file_hashes

list_source_files

read_source_file

read_source_files

write_source_files

delete_source_file

build_and_deploy

search_files

deploy_from_url

rehost_images

update_file_content

apply_edits

get_forms_config

set_forms_config

verify_forms_sender_domain

add_custom_domain

verify_custom_domain

remove_custom_domain

list_custom_domains

list_dns_records

check_domain_availability

begin_deploy

add_files

add_file_chunk

commit_deploy

abort_deploy

list_deploys

list_history

list_snapshots

create_snapshot

VibeDeploy MCP Server

What it does

Quick start

Tools

Typical flows

Notes for client authors and agents

Support

Install

Remote endpoint

Related servers