mcpField
A
Apollo MCP Server

Apollo MCP Server

Local
apollographql.comDeveloper Tools317Updated today
RepositoryVisit website

About Apollo MCP Server

Apollo MCP Server exposes configured GraphQL operations as MCP tools, letting AI models access and orchestrate APIs running with Apollo. It is intended for teams connecting an Apollo graph to MCP clients.

Key features

  1. 01Expose GraphQL operations as MCP tools
  2. 02Configure the graph and server behavior
  3. 03Connect to MCP clients
  4. 04Install from crates.io or build from source

Use cases

  1. 01Let an AI model access an Apollo API
  2. 02Make selected GraphQL operations available to an MCP client

MCP support

The server presents defined GraphQL operations as tools for MCP clients. It requires a configured graph, operation definitions, and an MCP client connection.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "apollo": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/apollographql/apollo-mcp-server:v2.1.0"
      ]
    }
  }
}
Run commanddocker run -i --rm ghcr.io/apollographql/apollo-mcp-server:v2.1.0

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
ocighcr.io/apollographql/apollo-mcp-server:v2.1.0

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP Toplist

Apollo Client

version crates.io ci workflow status release binaries workflow status release container workflow status license codecov

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 install the latest release from crates.io, run:

cargo install --locked apollo-mcp-server

--locked builds with the same dependency versions that were tested for the release.

To build from this repository instead, run cargo build from its root 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:

  1. A graph for the MCP server to sit in front of.
  2. Definitions for the GraphQL operations that should be exposed as MCP tools.
  3. A configuration file describing how the MCP server should run.
  4. 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.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.