What is an MCP Server?

An MCP (Model Context Protocol) server acts as a bridge, allowing AI models to access and interact with external data sources and tools. MCP is an open protocol that standardizes how applications provide context to LLMs.

What is mcp-graphql?

mcp-graphql is a Model Context Protocol (MCP) server that enables Large Language Models (LLMs) to interact with GraphQL APIs. It provides schema introspection and query execution capabilities.

How do I install mcp-graphql?

You can install it via Smithery using the command npx -y @smithery/cli install mcp-graphql --client claude or manually by configuring your Claude environment with the provided JSON.

What environment variables are used to configure mcp-graphql?

The key environment variables are ENDPOINT (GraphQL endpoint URL), HEADERS (JSON string for request headers), ALLOW_MUTATIONS (enables mutation operations), NAME (name of the MCP server), and SCHEMA (path to a local GraphQL schema file).

What are the security considerations when using mcp-graphql?

Mutations are disabled by default to prevent LLMs from modifying your database. Exercise caution and consider access controls before enabling mutations in production environments.

Can I customize mcp-graphql for my specific server?

Yes, you can create your own MCP server implementation and lock down tool calling for clients to specific query fields and/or variables. Use mcp-graphql as a reference.

What tools does mcp-graphql provide?

It provides introspect-schema to retrieve the GraphQL schema and query-graphql to execute GraphQL queries against the endpoint.

Why use UBOS with mcp-graphql?

UBOS is a full-stack AI Agent Development Platform. The UBOS platform helps you orchestrate AI Agents, connect them with your enterprise data, build custom AI Agents with your LLM model and Multi-Agent Systems.