Apollo
Enables sales intelligence and outreach automation through Apollo.io's 275M+ contact database. Supports prospecting, contact enrichment, email sequences, workflow automation, and pipeline management.
What is Apollo?
Apollo is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables sales intelligence and outreach automation through apollo.io's 275m+ contact database. supports prospecting, contact enrichment, email sequences, workflow automation, and pipeline management.
Enables sales intelligence and outreach automation through Apollo.io's 275M+ contact database. Supports prospecting, contact enrichment, email sequences, workflow automation, and pipeline management.
This server falls under the Business Applications category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables sales intelligence and outreach automation through A
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx apollo-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Apollo
The Apollo MCP Server bridges GraphQL APIs and AI assistants by exposing GraphQL operations as MCP tools, allowing language models to query and mutate your GraphQL graph through a standardized protocol. Built and maintained by Apollo GraphQL, it integrates with Apollo Router and Rover CLI to support both local development and production Kubernetes deployments. Teams that have an existing GraphQL API can use this server to give AI coding assistants or LLM applications structured, type-safe access to their data without building a custom integration layer.
Prerequisites
- Rover CLI v0.37+ installed (the Apollo CLI for managing graphs)
- Node.js 18+ for the rover dev development server
- An Apollo account and graph on GraphOS, or a self-hosted GraphQL endpoint
- APOLLO_KEY (graph API key from Apollo Studio) and APOLLO_GRAPH_REF (graph reference string)
- An MCP client such as Claude Desktop or an LLM application supporting MCP
Install or update the Rover CLI
The Apollo MCP Server is managed through the Rover CLI. Install or update Rover to at least v0.37 to access the MCP features.
# Install Rover
curl -sSL https://rover.apollo.dev/nix/latest | sh
# Or update existing installation
rover updateInitialize a new project with MCP support
Run the interactive init wizard with the --mcp flag to scaffold a new project with MCP configuration files and supergraph setup.
rover init --mcpSet required environment variables
Export your Apollo graph API key and graph reference. These are available from Apollo Studio under your graph's Settings page.
export APOLLO_KEY=your-apollo-api-key
export APOLLO_GRAPH_REF=your-graph-name@currentStart the local development server with MCP enabled
Run rover dev with your supergraph config and the MCP config file generated during init. The MCP server starts on port 8000 by default, and the Router on port 4000.
rover dev --supergraph-config supergraph.yaml --mcp .apollo/mcp.local.yamlDefine GraphQL operations as MCP tools
Open Apollo Sandbox at http://localhost:4000 and create operation collections. Each saved operation automatically becomes an MCP tool available to your AI client. Give operations descriptive names as they become the tool names.
# Example GraphQL operation saved in Sandbox:
query GetProducts {
products {
id
name
description
price
}
}Configure your MCP client to connect
Point your MCP client to the running Apollo MCP Server's HTTP endpoint. The server listens at http://127.0.0.1:8000/mcp by default.
{
"mcpServers": {
"apollo": {
"url": "http://127.0.0.1:8000/mcp"
}
}
}Apollo Examples
Client configuration
Claude Desktop configuration connecting to a locally running Apollo MCP Server via HTTP.
{
"mcpServers": {
"apollo": {
"url": "http://127.0.0.1:8000/mcp"
}
}
}Prompts to try
Example prompts for querying a GraphQL API exposed through the Apollo MCP Server.
- "Get a list of all products with their names and prices."
- "Find the order with ID 'ord_12345' and show me its status and line items."
- "Query the user profile for user ID 'usr_789' and return their name and email."
- "What GraphQL operations are available as tools in this MCP server?"
- "Run the GetProducts query and filter for items with price under $50."Troubleshooting Apollo
rover dev fails with 'APOLLO_KEY or APOLLO_GRAPH_REF not set'
Export both environment variables in the same shell session where you run rover dev: 'export APOLLO_KEY=...' and 'export APOLLO_GRAPH_REF=your-graph@current'. Find these values in Apollo Studio under your graph's Settings > API Keys.
MCP client cannot connect to http://127.0.0.1:8000/mcp
Verify that rover dev is running and shows the MCP server started successfully. Check for port conflicts with 'lsof -i :8000'. If you changed the port, set APOLLO_MCP_TRANSPORT__PORT to your chosen port and update the MCP client URL accordingly.
No MCP tools appear in the AI client after connecting
MCP tools are created from operation collections saved in Apollo Sandbox. Open http://localhost:4000 in your browser, create named GraphQL operations, and save them to a collection. The MCP server reads these collections to generate tool definitions. Restart rover dev after adding new operations.
Frequently Asked Questions about Apollo
What is Apollo?
Apollo is a Model Context Protocol (MCP) server that enables sales intelligence and outreach automation through apollo.io's 275m+ contact database. supports prospecting, contact enrichment, email sequences, workflow automation, and pipeline management. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Apollo?
Follow the installation instructions on the Apollo GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Apollo?
Apollo works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Apollo free to use?
Yes, Apollo is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Apollo Alternatives — Similar Business Applications Servers
Looking for alternatives to Apollo? Here are other popular business applications servers you can use with Claude, Cursor, and VS Code.
n8n
★ 189.1kA comprehensive MCP server that provides full control over n8n automation workflows through natural language. It offers 43 tools for managing workflows, executions, credentials, and data tables, with safety features like write-mode protection and dou
LobeHub
★ 77.5k🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
Jeecgboot
★ 46.4kAI 低代码平台，「低代码 + 零代码」双模式驱动：低代码一键生成前后端代码，零代码 5 分钟搭建系统，AI Skills 一句话画流程、设计表单、生成整套系统。内置 AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领「AI 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，消除 Java 项目 80% 的重复工作，提效而不失灵活。
CowAgent
★ 44.7kCowAgent (chatgpt-on-wechat) 是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入，可选择DeepSeek/OpenAI/Claude/Gemini/ MiniMax/Qwen/GLM/LinkAI，能处理文本、语音、图片和文件，可快速搭建个人AI助理和企业数字员工。
Minds Platform
★ 39.2kPlatform dedicated to building an open foundation for applied Artificial Intelligence, designed for people seeking production-ready AI systems they can truly control, extend and deploy anywhere.
Astrbot
★ 32.8kAI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
Browse More Business Applications MCP Servers
Explore all business applications servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Apollo in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Apollo?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.