A GraphQL server that supports the Model Context Protocol (MCP), enabling Large Language Models (LLMs) to interact with GraphQL APIs through schema introspection and query execution.
A Model Context Protocol server that enables LLMs to interact with GraphQL APIs. This implementation provides schema introspection and query execution capabilities, allowing models to discover and use GraphQL APIs dynamically.
Run mcp-graphql
with the correct endpoint, it will automatically try to introspect your queries.
Argument | Description | Default |
---|---|---|
--endpoint | GraphQL endpoint URL | http://localhost:4000/graphql |
--headers | JSON string containing headers for requests | {} |
--enable-mutations | Enable mutation operations (disabled by default) | false |
--name | Name of the MCP server | mcp-graphql |
--schema | Path to a local GraphQL schema file (optional) | - |
# Basic usage with a local GraphQL server
npx mcp-graphql --endpoint http://localhost:3000/graphql
# Using with custom headers
npx mcp-graphql --endpoint https://api.example.com/graphql --headers '{"Authorization":"Bearer token123"}'
# Enable mutation operations
npx mcp-graphql --endpoint http://localhost:3000/graphql --enable-mutations
# Using a local schema file instead of introspection
npx mcp-graphql --endpoint http://localhost:3000/graphql --schema ./schema.graphql
The server provides two main tools:
introspect-schema: This tool retrieves the GraphQL schema. Use this first if you don't have access to the schema as a resource. This uses either the local schema file or an introspection query.
query-graphql: Execute GraphQL queries against the endpoint. By default, mutations are disabled unless --enable-mutations
is specified.
To install GraphQL MCP Toolkit for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install mcp-graphql --client claude
It can be manually installed to Claude:
{
"mcpServers": {
"mcp-graphql": {
"command": "npx",
"args": ["mcp-graphql", "--endpoint", "http://localhost:3000/graphql"]
}
}
}
Mutations are disabled by default as a security measure to prevent an LLM from modifying your database or service data. Consider carefully before enabling mutations in production environments.
This is a very generic implementation where it allows for complete introspection and for your users to do whatever (including mutations). If you need a more specific implementation I'd suggest to just create your own MCP and lock down tool calling for clients to only input specific query fields and/or variables. You can use this as a reference.
The definitive Vibe Coder's sanity check MCP server: Prevents cascading errors by calling a "Vibe-check" agent to ensure alignment and prevent scope creep
A universal control plane for managing MCP servers and providing intelligent tool discovery for AI agents.
A toolkit for interacting with the Sui blockchain and integrating MCP SDK features, with support for multiple network environments.
Integrates with Microsoft's AutoGen framework to enable sophisticated multi-agent conversations via the Model Context Protocol.
Search for and run Yeoman generator templates programmatically.
Remote server (SSE/Streamable) for the latest Svelte and SvelteKit documentation
An MCP server for managing the software development lifecycle, with support for an optional external SQLite database.
Execute terminal commands through a secure shell interface using an AI assistant.
A minimal, containerized base for building MCP servers with the Python SDK, featuring a standardized Docker image and local development setup.
Integrates with Language Server Protocol (LSP) to provide features like code completion, diagnostics, and hover information.