apollo-mcp-server

Connect AI agents to GraphQL APIs through the Model Context Protocol with built-in introspection and operation tools. Exposes GraphQL operations as MCP tools; supports three operation sources: local files, GraphOS Studio collections, and persisted query manifests Provides four introspection tools (introspect, search, validate, execute) for schema exploration and ad-hoc query testing; minification mode reduces token usage with compact notation Configurable authentication via static headers,...

npx skills add https://github.com/apollographql/skills --skill apollo-mcp-server

Apollo MCP Server Guide

Apollo MCP Server exposes GraphQL operations as MCP tools, enabling AI agents to interact with GraphQL APIs through the Model Context Protocol.

Quick Start

Step 1: Install

# Linux / MacOS
curl -sSL https://mcp.apollo.dev/download/nix/latest | sh

# Windows
iwr 'https://mcp.apollo.dev/download/win/latest' | iex

Step 2: Configure

Create config.yaml in your project root:

# config.yaml
transport:
  type: streamable_http
schema:
  source: local
  path: ./schema.graphql
operations:
  source: local
  paths:
    - ./operations/
introspection:
  introspect:
    enabled: true
  search:
    enabled: true
  validate:
    enabled: true
  execute:
    enabled: true

Start the server:

apollo-mcp-server ./config.yaml

The MCP endpoint is available at http://127.0.0.1:8000/mcp (streamable_http defaults: address 127.0.0.1, port 8000). The GraphQL endpoint defaults to http://localhost:4000/ — override with the endpoint key if your API runs elsewhere.

Step 3: Connect

Add to your MCP client configuration:

Streamable HTTP (recommended):

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "graphql-api": {
      "command": "npx",
      "args": ["mcp-remote", "http://127.0.0.1:8000/mcp"]
    }
  }
}

Claude Code:

claude mcp add graphql-api -- npx mcp-remote http://127.0.0.1:8000/mcp

Stdio (client launches the server directly):

Claude Desktop (claude_desktop_config.json) or Claude Code (.mcp.json):

{
  "mcpServers": {
    "graphql-api": {
      "command": "./apollo-mcp-server",
      "args": ["./config.yaml"]
    }
  }
}

Built-in Tools

Apollo MCP Server provides four introspection tools:

ToolPurposeWhen to Use
introspectExplore schema types in detailNeed type definitions, fields, relationships
searchFind types in schemaLooking for specific types or fields
validateCheck operation validityBefore executing operations
executeRun ad-hoc GraphQL operationsTesting or one-off queries

Defining Custom Tools

MCP tools are created from GraphQL operations. Three methods:

1. Operation Files (Recommended)

operations:
  source: local
  paths:
    - ./operations/

Each file must contain exactly one operation. Each named operation becomes an MCP tool.

# operations/GetUser.graphql
query GetUser($id: ID!) {
  user(id: $id) {
    id
    name
    email
  }
}
# operations/CreateUser.graphql
mutation CreateUser($input: CreateUserInput!) {
  createUser(input: $input) {
    id
    name
  }
}

2. Operation Collections

operations:
  source: collection
  id: your-collection-id

Use GraphOS Studio to manage operations collaboratively.

3. Persisted Queries

operations:
  source: manifest
  path: ./persisted-query-manifest.json

For production environments with pre-approved operations.

Reference Files

Detailed documentation for specific topics:

Key Rules

Security

  • Never expose sensitive operations without authentication
  • Use headers configuration for API keys and tokens
  • Disable introspection tools in production (they are disabled by default)
  • Set overrides.mutation_mode: explicit to require confirmation for mutations

Authentication

# Static header
headers:
  Authorization: "Bearer ${env.API_TOKEN}"

# Dynamic header forwarding
forward_headers:
  - x-forwarded-token

# OAuth (streamable_http transport)
transport:
  type: streamable_http
  auth:
    servers:
      - https://auth.example.com/.well-known/openid-configuration
    audiences:
      - https://api.example.com

Token Optimization

Enable minification to reduce token usage:

introspection:
  introspect:
    minify: true
  search:
    minify: true

Minified output uses compact notation:

  • T = type, I = input, E = enum
  • s = String, i = Int, b = Boolean, f = Float, d = ID
  • ! = required, [] = list

Mutations

Control mutation behavior via the overrides section:

overrides:
  mutation_mode: all       # Execute mutations directly
  # mutation_mode: explicit  # Require explicit confirmation
  # mutation_mode: none      # Block all mutations (default)

Common Patterns

GraphOS Cloud Schema

# schema.source defaults to uplink — can be omitted when graphos is configured
graphos:
  apollo_key: ${env.APOLLO_KEY}
  apollo_graph_ref: my-graph@production

Local Development

transport:
  type: streamable_http
schema:
  source: local
  path: ./schema.graphql
introspection:
  introspect:
    enabled: true
  search:
    enabled: true
  validate:
    enabled: true
  execute:
    enabled: true
overrides:
  mutation_mode: all

Production Setup

transport:
  type: streamable_http
endpoint: https://api.production.com/graphql
operations:
  source: manifest
  path: ./persisted-query-manifest.json
graphos:
  apollo_key: ${env.APOLLO_KEY}
  apollo_graph_ref: ${env.APOLLO_GRAPH_REF}
headers:
  Authorization: "Bearer ${env.API_TOKEN}"
health_check:
  enabled: true

Docker

transport:
  type: streamable_http
  address: 0.0.0.0
  port: 8000
endpoint: ${env.GRAPHQL_ENDPOINT}
graphos:
  apollo_key: ${env.APOLLO_KEY}
  apollo_graph_ref: ${env.APOLLO_GRAPH_REF}
health_check:
  enabled: true

Ground Rules

  • ALWAYS configure authentication before exposing to AI agents
  • ALWAYS use mutation_mode: explicit or mutation_mode: none in shared environments
  • NEVER expose introspection tools with write access to production data
  • PREFER operation files over ad-hoc execute for predictable behavior
  • PREFER streamable_http transport for remote and multi-client deployments
  • USE stdio only when the MCP client launches the server process directly
  • USE GraphOS Studio collections for team collaboration

More skills from apollographql

apollo-federation
apollographql
Apollo Federation enables composing multiple GraphQL APIs (subgraphs) into a unified supergraph.
apollo-ios
apollographql
Apollo iOS is a strongly-typed GraphQL client for Apple platforms. It generates Swift types from your GraphQL operations and schema, and ships an async/await client, a normalized cache (in-memory or SQLite-backed), a pluggable interceptor-based HTTP transport that handles queries, mutations, and multipart subscriptions, and an optional WebSocket transport ( graphql-transport-ws ) that can carry any operation type.
apollo-router
apollographql
Apollo Router is a high-performance graph router written in Rust for running Apollo Federation 2 supergraphs. It sits in front of your subgraphs and handles query planning, execution, and response composition.
apollo-router-plugin-creator
apollographql
Create native Rust plugins for Apollo Router.
apollo-server
apollographql
Complete guide for building GraphQL servers with Apollo Server 5.x across frameworks. Covers schema definition, resolvers, context setup, and error handling with TypeScript support Supports standalone mode for prototyping and integrations with Express, Fastify, Koa, and serverless environments Includes resolver patterns, authentication/authorization, plugins, DataLoader for N+1 prevention, and performance optimization techniques Provides reference documentation for data sources, error...
graphql-operations
apollographql
Best practices guide for writing efficient, type-safe GraphQL operations and organizing them with fragments. Covers queries, mutations, subscriptions, and fragments with naming conventions, variable syntax, and directive usage Emphasizes core principles: request only needed fields, name all operations, use variables instead of hardcoded values, and include id fields for cacheability Recommends colocating fragments with components and using @include / @skip directives for conditional field...
graphql-schema
apollographql
Industry best practices guide for designing intuitive, performant, and maintainable GraphQL schemas. Covers core design principles including client-centric type organization, explicit nullability patterns, and backwards-compatible evolution strategies Provides reference documentation on types, naming conventions, cursor-based pagination, error modeling, and security considerations Includes practical patterns for interfaces, unions, input types, mutations, and ID strategies with code examples...
rover
apollographql
Apollo Rover CLI for managing GraphQL schemas, federation, and local supergraph development. Publish, fetch, and validate subgraph schemas; compose federated supergraphs locally or via GraphOS Includes schema checking (pre-deploy validation), linting, and introspection from running servers rover dev command starts a local Router with automatic schema composition for development workflows Supports CI/CD patterns with check-before-publish validation and JSON output for scripting Requires...