# Using GraphQL Operations as MCP Tools for LLM API Interaction

DevFeed: [Using GraphQL Operations as MCP Tools for LLM API Interaction](<https://devfeed.tech/articles/building-mcp-tools-with-graphql-a-better-way-to-connect-llms-to-your-api-23246.md>)

Original publisher: [Read original article](<https://www.apollographql.com/blog/building-mcp-tools-with-graphql-a-better-way-to-connect-llms-to-your-api>)

Author: Michael Watson

Published: 2025-05-22T12:59:07Z

Content type: tutorial

Language: en

Sources: [Apollo Blog](<https://devfeed.tech/sources/apollo-blog.md>)

Topics: [GraphQL](<https://devfeed.tech/topics/graphql.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [API](<https://devfeed.tech/topics/api.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [apollo-mcp-server](<https://devfeed.tech/tags/apollo-mcp-server.md>), [graphql](<https://devfeed.tech/tags/graphql.md>), [llms](<https://devfeed.tech/tags/llms.md>), [mcp](<https://devfeed.tech/tags/mcp.md>)

## AI overview

This tutorial examines MCP server development with Python and TypeScript, using a Python community launch-library server based on the Launch Library REST API. It contrasts endpoint-specific REST tools with GraphQL operations, noting that multiple REST tools can add code, context-window noise, and tool-call overhead for LLMs.

## Source excerpt

After Apollo recently released the Apollo MCP Server that allows you to generate tools for any GraphQL API, I have been investigating MCP server development within Python and Typescript frameworks. It's easy enough to build a simple tool, but I found myself feeling déjà vu as if I were building applications before GraphQL was released. Each tool I wrote started to get more complex and I quickly started seeing multiple API fetches happen in the same tool.