What is mcp-graphql?

mcp-graphql is a Model Context Protocol (MCP) server that enables LLMs (Large Language Models) to interact with GraphQL APIs. It allows models to discover and use GraphQL APIs dynamically.

How does mcp-graphql work?

mcp-graphql works by providing schema introspection and query execution capabilities. It retrieves the GraphQL schema, either through introspection or from a local file, and allows LLMs to execute queries against the specified endpoint.

What is the Model Context Protocol (MCP)?

MCP is an open protocol that standardizes how applications provide context to LLMs. It acts as a bridge, allowing AI models to access and interact with external data sources and tools.

How do I install mcp-graphql?

You can install mcp-graphql either via Smithery or manually. Use the provided commands in the documentation.

What command-line arguments are available for mcp-graphql?

The available arguments include --endpoint (GraphQL endpoint URL), --headers (JSON string containing headers), --enable-mutations (enable mutation operations), --name (name of the MCP server), and --schema (path to a local GraphQL schema file).

What tools does mcp-graphql provide?

mcp-graphql provides two main tools: introspect-schema (to retrieve the GraphQL schema) and query-graphql (to execute GraphQL queries).

How do I enable mutations in mcp-graphql?

To enable mutations, use the --enable-mutations flag when running mcp-graphql. However, exercise caution as mutations can modify data.

What are the security considerations when using mcp-graphql?

Mutations are disabled by default for security reasons. Consider carefully before enabling mutations in production environments to prevent unintended data modifications by LLMs.

Can I customize mcp-graphql for my own server?

Yes, you can customize mcp-graphql. If you need a more specific implementation, it’s suggested to create your own MCP and lock down tool calling for clients to only input specific query fields and/or variables. You can use the generic implementation as a reference.

How does mcp-graphql integrate with UBOS?

mcp-graphql seamlessly integrates into the UBOS ecosystem, providing a powerful mechanism for connecting your AI agents with external data sources, automate tasks, and personalize user experiences.

What is UBOS?

UBOS is a full-stack AI Agent development platform focused on bringing AI Agents to every business department. Our platform helps you orchestrate AI Agents, connect them with your enterprise data, build custom AI Agents with your LLM model and Multi-Agent Systems.