Convex is a Backend MCP server that lets Claude Code, Cursor, Windsurf and any MCP-compatible AI agent introspect and query apps deployed to Convex. Install in 1 minute with mcpizy install convex.
Backend
Introspect and query apps deployed to Convex. Real-time backend with automatic caching.
mcpizy install convexnpx -y @convex/mcpThe Convex MCP server is an Backend Model Context Protocol server that lets Claude Code, Cursor, Windsurf, VS Code with Copilot, and other MCP-compatible AI agents introspect and query apps deployed to Convex. It exposes Convex's capabilities as tools the AI can call directly from your editor or CLI.
The fastest way is the MCPizy CLI: run `mcpizy install convex` and MCPizy will add the server to your `.claude.json` automatically. You can also install it manually by adding an entry under `mcpServers` in `.claude.json` with the command `npx -y @convex/mcp` and restarting Claude Code.
Yes. The Convex MCP server is free and open source. You may still need a Convex account or API key to connect the server to the underlying service, but the MCP layer itself has no MCPizy subscription cost.
Yes. Any MCP-compatible client works — including Claude Code, Claude Desktop, Cursor (via `.cursor/mcp.json`), Windsurf, VS Code with Copilot Chat, and custom agents built on the MCP SDK. The same install command targets all of them; only the config file path differs.
Once installed, your AI agent can introspect and query apps deployed to Convex directly inside your conversation. Typical use cases include asking Claude Code or Cursor to run Convex operations, inspect results, chain Convex with other MCP servers (see our Workflow Recipes), and automate repetitive backend tasks without leaving your editor.