Apollo MCP Server MCP Server
io.github.apollographql/apollo-mcp-server
Expose GraphQL operations as MCP tools for AI models to access and orchestrate your APIs.
What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the Apollo MCP Server MCP server?
Apollo MCP Server is a Model Context Protocol server that exposes GraphQL operations as MCP tools. It provides a standard way for AI models to access and orchestrate your APIs running with Apollo. The server requires a GraphQL graph, operation definitions, and a configuration file to function.
Apollo MCP Server bridges GraphQL APIs and AI models by exposing GraphQL operations as callable MCP tools. This allows AI agents like Claude to query and interact with your GraphQL endpoints directly, enabling automated API orchestration and data retrieval through natural language.
How to install Apollo MCP Server
Copy-paste configuration for popular MCP clients.
{
"mcpServers": {
"apollo-mcp-server": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/apollographql/apollo-mcp-server:v1.20.0",
"--mount",
"type=bind,src={config_path},dst=/config.yaml,readonly",
"--mount",
"type=bind,src={data_path},dst=/data",
"-p",
"8000:8000",
"/config.yaml"
]
}
}
}Tools & capabilities
Tools this server exposes to the agent.
GraphQL Operations— Exposes configured GraphQL operations as MCP tools that AI models can call to query and interact with your GraphQL APIs.
Use cases
- Query GraphQL APIs through natural language commands in Claude or other AI clients
- Automate API orchestration by chaining multiple GraphQL operations together
- Enable AI agents to fetch and transform data from your Apollo-powered backend
- Build intelligent assistants that interact with your GraphQL schema without manual integration
- Integrate GraphQL endpoints into AI workflows for data-driven decision making
Apollo MCP Server MCP server FAQ
Apollo MCP Server exposes GraphQL operations as MCP tools, allowing AI models to access and orchestrate your GraphQL APIs through a standard protocol.
Yes, Apollo MCP Server is open source and licensed under the MIT License.
You can build from source with Rust (`cargo build`) or use the container image `ghcr.io/apollographql/apollo-mcp-server:v1.20.0`. See the installation guide in the documentation for detailed steps.
You need to configure: a GraphQL graph to sit in front of, definitions for GraphQL operations to expose as tools, a configuration file for the MCP server, and a connection to an MCP client like Claude or the MCP inspector.
Authentication depends on your GraphQL API and configuration. Refer to the config file reference in the documentation for authentication options.
Yes, Apollo MCP Server connects to any MCP client, including Claude and Cursor, once properly configured with your GraphQL operations.
README (reference)
Source of truth, from the repository.
Apollo MCP Server
Apollo MCP Server is a Model Context Protocol server that exposes GraphQL operations as MCP tools. It provides a standard way for AI models to access and orchestrate your APIs running with Apollo.
Documentation
See the documentation for full details. This README shows the basics of getting this MCP server running. More details are available on the documentation site.
Installation
You can either build this server from source, if you have Rust installed on your workstation, or you can follow the installation guide. To build from source, run cargo build from the root of this repository and the server will be built in the target/debug directory.
Getting started
Follow the quickstart tutorial to get started with this server.
Usage
Full usage of Apollo MCP Server is documented on the user guide. There are a few items that are necessary for this server to function. Specifically, the following things must be configured:
- A graph for the MCP server to sit in front of.
- Definitions for the GraphQL operations that should be exposed as MCP tools.
- A configuration file describing how the MCP server should run.
- A connection to an MCP client, such as an LLM or MCP inspector.
These are all described on the user guide. Specific configuration options for the configuration file are documented in the config file reference.
Contributions
Checkout the contributor guidelines for more information.
Licensing
This project is licensed under the MIT License. See the LICENSE file for the full license text.
Security
Refer to our security policy.
[!IMPORTANT]
Do not open up a GitHub issue if a found bug is a security vulnerability, and instead to refer to our security policy.
Related MCP servers
Search Apollo docs, specs, and best practices

GraphOS MCP Tools
Search Apollo GraphQL docs, specs, and best practices directly from your AI agent.

BridgeNode MCP
AI inference via MCP — pay per request with Solana USDC through x402. No API keys.

Vlk MemAct
Stateful memory for AI agents. Temporal awareness, error loop detection, and preventive constraints.

Apollo.io
Prospect, enrich leads, and manage outreach sequences with Apollo.io directly in your AI agent.

io.github.apolloio/mcp
Official Apollo.io MCP server for lead prospecting, enrichment, and sales outreach workflows.