# The Vynix MCP Server for AI Agents

> Connect AI agents and IDEs to Vynix over the Model Context Protocol so they can read annotations, run diagnoses and create issues from the captured context.

[Docs](/docs/)/MCP server

Integrations

# The Vynix MCP server

Vynix ships a native Model Context Protocol (MCP) server. Agents like Claude Code, Cursor, Windsurf and GitHub Copilot can read your feedback and context without leaving the IDE.

## What the server exposes

The MCP server exposes your projects and annotations as tools an agent can call: list projects, list and read annotations with their full captured context, run an AI diagnosis, and create a GitHub issue.

This means an agent can answer a request like "show me the open feedback on this project and fix the highest-priority one" using real, structured context rather than a pasted screenshot.

## Connect an AI agent to Vynix over MCP

1.  1
    
    Get an MCP token
    
    Create an MCP access token in the Vynix dashboard. Tokens are revocable.
    
2.  2
    
    Add the server
    
    Add the Vynix MCP server to your agent or IDE config, pointing it at the Vynix API with your token.
    
3.  3
    
    Restart the agent
    
    Restart the MCP client so it loads the server, then enable the Vynix tools.
    
4.  4
    
    Ask for feedback
    
    Ask your agent to list annotations or fix a reported issue. It reads the captured context directly.
    

## Related

[Using the Vynix MCP server](/blog/using-the-vynix-mcp-server-with-your-ai-agent/)[Add an MCP server to Claude Code](/blog/add-mcp-server-claude-code/)[Add an MCP server to Cursor](/blog/add-mcp-server-cursor/)[MCP servers for web development](/blog/mcp-servers-for-web-development/)[How agents get website context via MCP](/blog/how-coding-agents-get-website-context-mcp/)[Model Context Protocol (glossary)](/glossary/model-context-protocol/)[API reference](/docs/api/)

[<- GitHub Copilot](/docs/copilot/)[Browser extension ->](/docs/browser-extension/)

## Stop describing bugs. Point at them.

Add one script tag and give your AI agent the context it has been missing. Free while we grow.

[Get started free](/register)[Read the install guide](/install/)

---

Source: https://www.vynix.in/docs/mcp/ | Markdown version for AI agents. Full site index: https://www.vynix.in/llms.txt