What it does

Introspects a GraphQL endpoint and lets the agent compose queries against the real schema, including variable handling and per-request headers. That last part matters for authenticated APIs. Use a read-only token: a schema-aware agent with mutation access will eventually try one.

Install

Terminal

npx -y @letoribo/mcp-graphql-enhanced

Client configuration

Paste this into your MCP client config (Claude Desktop, Cursor, or any client that reads mcpServers), then restart the client.

mcp.json

{
  "mcpServers": {
    "graphql": {
      "command": "npx",
      "args": [
        "-y",
        "@letoribo/mcp-graphql-enhanced"
      ]
    }
  }
}

Use it for

Exploring a GraphQL API from its schema before writing queries

Skip it if

Production writes; introspection plus mutation is a permission problem

When to use it

Reach for this when the task needs graphql inside the agent loop. Skip it if a plain shell command or a one-off script is enough — every server you add costs context and adds a failure mode.

Other TypeScript servers

Filesystem — Gives an agent scoped read, write, and search access to directories you explicitly allow
Memory — A persistent knowledge graph stored in a local JSON file, exposed through entities, relations, and observations
Sequential Thinking — Gives the model a scratchpad for structured, revisable reasoning: numbered thoughts that can branch, revise, and conclude

GraphQL MCP