GraphQL MCPTurn your GraphQL API into AI-ready tools

MCP (Model Context Protocol) lets AI agents call external tools. GraphQL MCP reads your schema and generates those tools automatically — no boilerplate, no manual definitions.

Your schema becomes AI tools ​

type Query {
  tasks(status: Status, priority: Priority): [Task!]!
  task(id: UUID!): Task
}

type Mutation {
  createTask(title: String!, priority: Priority): Task!
  deleteTask(id: UUID!): Boolean!
}

enum Status { TODO, IN_PROGRESS, DONE }
enum Priority { LOW, MEDIUM, HIGH, CRITICAL }

tasks(status?, priority?) → [Task]
  List all tasks, filtered by status or priority.

task(id) → Task
  Get a single task by ID.

create_task(title, priority?) → Task
  Create a new task.

delete_task(id) → bool
  Delete a task by ID.

From a Python schema ​

from graphql_mcp import GraphQLMCP

api = ...  # your Strawberry, Ariadne, Graphene, or graphql-api schema
server = GraphQLMCP.from_api(api, name="My API")
app = server.http_app()

From any existing GraphQL API ​

from graphql_mcp import GraphQLMCP

server = GraphQLMCP.from_remote_url("https://api.example.com/graphql")
app = server.http_app()

Works with ​

StrawberryAriadneGraphenegraphql-apiAny graphql-core schemaRemote GraphQL endpoints