vynix-mcp-server
OfficialThe Vynix MCP server gives AI coding agents direct access to your Vynix annotation/feedback platform, enabling you to read, analyze, and act on UI annotations without leaving your editor.
Read & Browse
List projects, and list/filter annotations by status, type, or priority
Fetch a single annotation with full captured context: page info, target element (selector, XPath, styles), surrounding DOM, and runtime diagnostics (console + network errors)
Read discussion threads (comments) on any annotation
Get team members (roles, status) and recent activity feeds
AI & Analysis
Read existing AI diagnoses — root causes, confidence scores, suggested fixes, and likely source files
Run the AI Diagnosis Engine on an annotation to generate a fresh diagnosis (calls an external AI provider, uses tokens)
Generate ready-to-paste coding prompts formatted for Claude, Copilot, Cursor, Gemini, Codex, or a generic assistant (deterministic, no AI spend)
Screenshots & Visuals
View attached screenshots of the reported issue region
GitHub Integration
List GitHub issues linked to an annotation (with optional live refresh of open/closed state and linked PRs)
List all tracker issues across an entire project
Create a GitHub issue directly from an annotation, embedding an AI-generated prompt in the issue body
Metrics & Reporting
Get KPI metrics — status breakdowns, daily time series, and activity overviews
Create a public share link for a project so stakeholders can review annotations without an account
Write / Update
Update annotation status (e.g.,
in_progress,completed,rejected)Post comments to an annotation's thread (notifies the team)
Guided Workflow
fix_annotation— a step-by-step prompt that walks the agent from reading an annotation through context → screenshots → AI diagnosis → generating a fix → updating status and posting a comment
Enables creating GitHub issues from Vynix annotations and listing associated issues
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 the projects you own. |
| List a project's annotations, filtered by status / type / priority. |
| Fetch one annotation with full page / element / DOM / diagnostics context. |
| Read an annotation's discussion thread. |
| Read the latest AI diagnosis (root causes, fix, likely files). |
| Return attached screenshots as viewable images. |
| List the GitHub issues opened from an annotation (optionally live). |
| List every tracker issue across a project, with a summary. |
| Produce a ready-to-paste prompt ( |
| KPI counts, status breakdown, time series, recent activity. |
| A project's team members. |
| A project's recent activity feed. |
Writes (a client should confirm these):
Tool | Description |
| Move an annotation to |
| Post a comment to an annotation's thread (notifies the team). |
| Run the AI Diagnosis Engine (uses an AI provider; stores the result). |
| File a GitHub issue from an annotation. |
| Mint a read-only public review link for a project. |
Related MCP server: yo-bug
Prompts
Prompt | Description |
| 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+:
{
"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 (defaulthttps://www.vynix.in).VYNIX_API_TOKEN- a token generated at https://www.vynix.in/mcp, orVYNIX_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:
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 surfaceThen point your client at the built file instead of npx:
{
"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.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityDmaintenanceBug bounty platform for vibe coders. Post bugs from AI-generated code, browse bounties, apply to fix, submit solutions, and run website diagnostics from any MCP client.Last updated1237MIT
- Alicense-qualityCmaintenanceAn MCP server that gives AI coding assistants QA superpowers, enabling users to report bugs by pointing, clicking, or typing while automatically capturing diagnostic data for AI-driven test-feedback-fix loops.Last updated543MIT
- Alicense-qualityDmaintenanceMCP server for visual feedback, video direction, and QA assertions on web pages, enabling AI agents to read, reply, and resolve annotations in real time.Last updated4MIT
- Flicense-qualityAmaintenanceMCP server that exposes web page annotations to AI coding agents, enabling automated implementation of visual feedback and design tweaks.Last updated16120
Related MCP Connectors
Voice-powered bug reporting with 13 MCP tools. Record bugs by talking; let AI find and fix them.
Live browser debugging for AI assistants — DOM, console, network via MCP.
AI QA tester — real browsers scan sites for bugs, SEO, perf, and accessibility issues via chat.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/UseVynix/vynix-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server