SiteGuardian

Official5 toolsLive

by gweber · Shell

EU-hosted website monitoring + 17-framework compliance MCP. One anonymous tool, four authenticated.

SiteGuardian MCP Server (io.github.gweber/siteguardian)

This MCP server provides EU-hosted website monitoring and “17-framework compliance.” It is described as having one anonymous tool and four authenticated tools (toolCount: 5 total). The repository focuses on examples, client configurations, and an MCP server manifest rather than the server’s implementation.

🛠️ Key Features

EU-hosted website monitoring
17-framework compliance MCP
Tool access split: one anonymous tool, four authenticated tools (5 total)

🚀 Use Cases

Website monitoring in an EU-hosted setup
Compliance checks aligned to the “17-framework” reference

⚡ Developer Benefits

Example client configurations and copy-paste integration code
MCP server manifest available for client setup
Documentation at siteguardian.io/docs/mcp

⚠️ Limitations

Repository content is described as examples and client integration code only; the MCP server implementation is not detailed in the provided excerpt.

Topics

anthropicclaudecompliancedoragdprmcpmodel-context-protocolmonitoringnis2securityeu-hosted

Captured live from the server via tools/list.

scan_domain

Runs a free one-off security scan of the given domain and returns its grade (A–F), scan timestamp, and up to three top-priority issues with a permalink to the full report on siteguardian.io. Use this when the user asks for a quick security check of a domain that is NOT yet under SiteGuardian monitoring, or when they want a fresh assessment before subscribing. Results are cached for two hours, so repeated calls about the same domain return the same snapshot and mark it with cached=True. Do NOT use this for domains already under monitoring by the user — call get_domain_status instead for the account-scoped view with framework tags. Do NOT use this to batch-scan many domains as a competitive-intelligence tool; per-source-IP and per-target rate limits bound usage. This tool does not require authentication.

Parameters1

domain

string

required

Raw schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string"
    }
  },
  "required": [
    "domain"
  ],
  "additionalProperties": false
}

list_monitored_domains

Returns the full list of domains under continuous SiteGuardian monitoring for the authenticated account. Each entry includes the domain, current security grade (A–F), timestamp of the last completed scan, and a relative dashboard URL. Use this when the user asks what they are monitoring, wants an inventory summary, or needs to look up a specific domain's exact spelling before calling get_domain_status / get_drift_events / get_fix_recommendations. The list is scoped entirely by the API key — there is no filter parameter to widen or narrow the result. Do NOT use this to enumerate domains the user does not own or monitor — it only returns their own inventory. Do NOT call it to trigger a scan (it does not); use scan_domain for one-off checks. Requires a valid API key.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

get_domain_status

Returns the current security grade (A–F), last-scan timestamp, and list of active issues for a domain that is ALREADY under SiteGuardian monitoring by the authenticated account. Each issue carries a stable id, a severity, a short title, and an impact description. The response also includes a relative dashboard URL. Use this when the user asks about the current state of a specific monitored domain, wants to confirm a recent change landed, or needs issue ids to call get_fix_recommendations with a specific issue_id. Do NOT use this for domains not yet under monitoring — it will return a domain_not_monitored error; call scan_domain for one-off checks instead. Compliance framework tags (NIS2 / GDPR / DORA) are NOT included in v1; framework tagging on the monitored-domain path is tracked as a follow-up. Requires a valid API key.

Parameters1

domain

string

required

Raw schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string"
    }
  },
  "required": [
    "domain"
  ],
  "additionalProperties": false
}

get_drift_events

Returns recent configuration drift events for a domain under monitoring by the authenticated account — TLS changes, DNSSEC state changes, new or removed security headers, shifts in third-party JS hosts, new cookies. Each event carries its observed-at timestamp, a kind (tls/dnssec/cookies/js_hosts/headers), a severity classified centrally (high for tls/dnssec/headers, medium for cookies/js_hosts, otherwise low), a short summary, and a sanitised detail payload. Use this when the user asks 'what changed' on a domain, wants to audit recent posture shifts, or is diagnosing an unexpected issue. Pair it with get_domain_status to see the current state and get_drift_events to see how it got there. Do NOT use this for a domain that is not under monitoring — you'll get a domain_not_monitored error; monitoring has to be active for the drift history to accumulate. Optional since (ISO-8601) and limit (1..100) params narrow the window. Requires a valid API key.

Parameters3

domain	string	required
since	any	optional
limit	integer	optional

Raw schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string"
    },
    "since": {
      "anyOf": [
        {
          "format": "date-time",
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "limit": {
      "default": 20,
      "type": "integer"
    }
  },
  "required": [
    "domain"
  ],
  "additionalProperties": false
}

get_fix_recommendations

Returns copy-paste-ready fix recommendations (nginx, Apache, DNS, shell) for the issues found on a domain the caller has already paid for — either an active Monitor/Compliance subscription covering the domain, OR a purchased one-off Report for the domain. Each recommendation carries a stable issue_id, a priority (high/medium/low), a title, prose instructions, one or more config snippets with the target domain already interpolated, a verify command, and a category tag. Use this when the user asks how to fix an issue, wants the exact config to apply, or needs to verify a fix worked. Pass the optional issue_id to scope the response to one specific finding. The response is read-only — this tool NEVER triggers a fresh scan; fixes are computed from the most recent stored scan (including the Report-included re-scan if that was used). Do NOT use this for domains the caller hasn't purchased coverage for — you'll get an upgrade_required error that links to the pricing page. Do NOT use this to run or trigger a scan; call scan_domain for anonymous checks. Requires a valid API key.

Parameters2

domain	string	required
issue_id	any	optional

Raw schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string"
    },
    "issue_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    }
  },
  "required": [
    "domain"
  ],
  "additionalProperties": false
}

README.md4 KBView on GitHub

SiteGuardian MCP — Examples & Client Configurations

Client configurations, copy-paste examples, and the MCP server manifest for the SiteGuardian Model Context Protocol server.

Note: This repository contains examples and client integration code only. The MCP server itself is hosted at https://mcp.siteguardian.io and is operated as a SaaS — server source is closed. Everything in this repo is MIT-licensed and free to fork.

What is the SiteGuardian MCP server?

A hosted MCP endpoint that lets Claude Desktop, Claude Code, Cursor, Windsurf, and VS Code Copilot query website-monitoring data and run security/compliance scans through natural-language tool calls.

Endpoint: https://mcp.siteguardian.io (or the canonical https://siteguardian.io/mcp)
Transport: Streamable HTTP
Hosting: Hetzner, Germany — EU data residency
Documentation: https://siteguardian.io/docs/mcp

Five tools

Tool	Auth	Purpose
`scan_domain`	anonymous	One-off security scan, A–F grade + top 3 issues + permalink
`list_monitored_domains`	Bearer	Domains under continuous monitoring for the account
`get_domain_status`	Bearer	Current grade + active issues for a monitored domain
`get_drift_events`	Bearer	Recent posture changes (TLS, DNSSEC, headers, cookies, JS hosts)
`get_fix_recommendations`	Bearer + paid plan	nginx/Apache/DNS snippets + verify commands

Try the anonymous tool (no setup required)

bash

curl -X POST https://mcp.siteguardian.io/ \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"scan_domain","arguments":{"domain":"example.com"}}}'

Rate-limited to 10 calls/hour/IP. Cached for 2h per domain. Full curl/Python/JS examples in examples/.

Install in your client

All clients use the same endpoint. Copy-paste configs in clients/:

Claude Desktop — clients/claude-desktop.json
Claude Code (CLI) — clients/claude-code.sh
Cursor — clients/cursor.json
Windsurf — clients/windsurf.json
VS Code / Copilot — clients/vscode.sh

Authentication

The scan_domain tool is anonymous. The four monitoring tools require a Bearer key:

Sign in at https://siteguardian.io
Open Settings → API & Integrations
Click Generate key, name it, copy it

Add to your client config:

json

"headers": {"Authorization": "Bearer sg_live_..."}

API keys are available on the Monitor, Compliance, and Enterprise plans.

Privacy

EU-hosted. Hetzner Germany. No US sub-processor.
No LLM in the response path. Tool answers are deterministic from monitoring data.
No training on your queries. Logged for abuse prevention and billing only.
Audit trail. Every tool call is recorded in the SHA-256 hash chain.

Server manifest

The full machine-readable MCP server manifest is in server.json — this is the file consumed by the Anthropic MCP Registry and the various community directories.

Roadmap

OAuth 2.1 (per current MCP spec)
resources and prompts in addition to tools
Listing in the official Anthropic MCP Registry
Listing on Smithery and mcp.so

License

Examples and client configurations in this repository are released under the MIT License — see LICENSE.

The SiteGuardian MCP server itself is proprietary and hosted as a SaaS. Server source is not distributed.

Support

Documentation: https://siteguardian.io/docs/mcp
Status: https://siteguardian.io/status
Bug or feature request: open an issue or email support@siteguardian.io

Install

Tools (5)

scan_domainlist_monitored_domainsget_domain_statusget_drift_eventsget_fix_recommendations

Remote endpoint

Streamable HTTP

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

url

https://mcp.siteguardian.io

Add to VS Code Add to Cursor

claude_desktop_config.json

json

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

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

SiteGuardian MCP Server (io.github.gweber/siteguardian)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

scan_domain

list_monitored_domains

get_domain_status

get_drift_events

get_fix_recommendations

SiteGuardian MCP — Examples & Client Configurations

What is the SiteGuardian MCP server?

Five tools

Try the anonymous tool (no setup required)

Install in your client

Authentication

Privacy

Server manifest

Roadmap

License

Support

Install

Remote endpoint

Related servers