in.vynix/vynix-mcp Model Context Protocol (MCP) Server

The in.vynix/vynix-mcp MCP server enables AI coding agents to access Vynix visual feedback, bug reports, and AI diagnosis. It is intended to connect agent workflows with those Vynix sources, based on the server’s provided description.

🛠️ Key Features

Access to Vynix visual feedback
Access to Vynix bug reports
Access to AI diagnosis

🚀 Use Cases

Agent-assisted review of visual feedback from Vynix
Troubleshooting using Vynix bug reports
Diagnosis workflows that rely on AI diagnosis information

⚡ Developer Benefits

Provides an MCP interface for integrating Vynix feedback, reports, and diagnosis into agent tooling

⚠️ Limitations

Available details only describe access to visual feedback, bug reports, and AI diagnosis; no additional capabilities or tooling specifics are provided.

Vynix MCP server

A Model Context Protocol server that gives AI coding agents (Claude, Copilot, Cursor and more) direct access to your Vynix annotations, so an agent can read the feedback, see the captured context and screenshots, run an AI diagnosis, generate a fix prompt, open a GitHub issue, update status, and comment, all without leaving the editor.

Every tool carries MCP annotations (read-only / idempotent / open-world hints) so a client can auto-approve safe reads and confirm before writes, AI spend, or GitHub calls.

Tools

Read-only:

Tool	Description
`list_projects`	List the projects you own.
`list_annotations`	List a project's annotations, filtered by status / type / priority.
`get_annotation`	Fetch one annotation with full page / element / DOM / diagnostics context.
`list_comments`	Read an annotation's discussion thread.
`get_annotation_analysis`	Read the latest AI diagnosis (root causes, fix, likely files).
`get_annotation_screenshots`	Return attached screenshots as viewable images.
`list_annotation_issues`	List the GitHub issues opened from an annotation (optionally live).
`list_project_issues`	List every tracker issue across a project, with a summary.
`generate_prompt`	Produce a ready-to-paste prompt (`claude`/`copilot`/`cursor`/`gemini`/`codex`/`generic`).
`get_metrics`	KPI counts, status breakdown, time series, recent activity.
`list_members`	A project's team members.
`get_activity`	A project's recent activity feed.

Writes (a client should confirm these):

Tool	Description
`update_annotation_status`	Move an annotation to `in_progress`, `completed`, etc.
`add_comment`	Post a comment to an annotation's thread (notifies the team).
`diagnose_annotation`	Run the AI Diagnosis Engine (uses an AI provider; stores the result).
`create_github_issue`	File a GitHub issue from an annotation.
`create_share_link`	Mint a read-only public review link for a project.

Prompts

Prompt	Description
`fix_annotation`	A guided, step-by-step workflow that walks the agent from an annotation through context → screenshots → AI diagnosis → fix → status + comment.

Install

The server is published on npm. Most MCP clients (Cursor, VS Code, Claude Desktop and more) just need a command and a token, and npx fetches and runs it automatically with no global install. Requires Node.js 18+:

json

{
  "mcpServers": {
    "vynix": {
      "command": "npx",
      "args": ["-y", "@usevynix/mcp-server"],
      "env": {
        "VYNIX_API_URL": "https://www.vynix.in",
        "VYNIX_API_TOKEN": "PASTE_YOUR_TOKEN_HERE"
      }
    }
  }
}

Generate your token from the Vynix dashboard at https://www.vynix.in/mcp. Config file locations: Cursor ~/.cursor/mcp.json, VS Code .vscode/mcp.json, Claude Desktop claude_desktop_config.json. VS Code uses a top-level "servers" key instead of "mcpServers"; everything else is identical.

Configure

Authenticate with either a token (recommended) or email and password:

VYNIX_API_URL - your Vynix API base URL (default https://www.vynix.in).
VYNIX_API_TOKEN - a token generated at https://www.vynix.in/mcp, or
VYNIX_API_EMAIL + VYNIX_API_PASSWORD - the server logs in on demand and refreshes the token automatically when it expires.

Build from source

For contributors who want to run the server from a local checkout:

bash

git clone https://github.com/UseVynix/vynix-mcp.git
cd vynix-mcp
npm install
npm run build
npm start          # runs dist/index.js over stdio
npm run dev        # watch mode with tsx
npm test           # smoke test: launches the server and verifies the tool + prompt surface

Then point your client at the built file instead of npx:

json

{
  "mcpServers": {
    "vynix": {
      "command": "node",
      "args": ["/absolute/path/to/vynix-mcp/dist/index.js"],
      "env": {
        "VYNIX_API_URL": "https://www.vynix.in",
        "VYNIX_API_TOKEN": "PASTE_YOUR_TOKEN_HERE"
      }
    }
  }
}

Diagnostics are written to stderr; stdout is reserved for the protocol stream.

project_id	string	required	The id of the project to list annotations for.
status	string	optional
type	string	optional
priority	string	optional
limit	integer	optional	Page size, 1-200 (default 50).
offset	integer	optional

annotation_id	string	required
refresh	boolean	optional	Reconcile live state from GitHub. Optional.

annotation_id	string	required	The id of the annotation to turn into a prompt.
target	string	optional	Which assistant to format for. Defaults to generic.

annotation_id	string	required
status	string	required

annotation_id	string	required
body	string	required	The comment text.

Vynix

in.vynix/vynix-mcp Model Context Protocol (MCP) Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

list_projects

list_annotations

get_annotation

list_comments

get_annotation_analysis

get_annotation_screenshots

list_annotation_issues

list_project_issues

generate_prompt

get_metrics

list_members

get_activity

update_annotation_status

add_comment

diagnose_annotation

create_github_issue

create_share_link

Vynix MCP server

Tools

Prompts

Install

Configure

Build from source

Install

Configuration

project_id	string	required
expires_in_days	integer	optional	Days until the link expires. 0 or omitted means it never expires.