MCP Integration

Agent-Memo.AI connects to your AI agent through the Model Context Protocol (MCP) — the open standard for connecting AI models to external tools and data sources.

What is MCP?

The Model Context Protocol is an open specification that lets AI agents call external tools in a standardized way. Instead of each tool requiring custom integration code, MCP provides a universal interface — like USB for AI agents.

AI Agent
Claude Code, Cursor, etc.
→
MCP Protocol
Standardized tool calls
→
Agent-Memo
Cloud memory service

Supported AI agents

Claude Code

Full support

Anthropic's CLI coding agent. Full MCP support with hooks for auto-saving.

Cursor

Full support

AI-powered code editor. MCP support via .cursor/mcp.json configuration.

Windsurf

Full support

Codeium's AI IDE. MCP support via configuration file.

OpenClaw

Full support

Open-source AI assistant. MCP support via ~/.openclaw/openclaw.json or CLI.

Any MCP client

Compatible

Any tool that supports the Model Context Protocol standard.

How it works

1

Agent starts a session

Your AI agent reads .mcp.json and starts the Agent-Memo MCP server process via npx.

2

Server authenticates

The MCP server connects to the Agent-Memo cloud API using your token. Project context is auto-detected from git.

3

Agent calls tools

The agent can call any of the 14 memory tools — store, recall, search, update, delete, knowledge graph operations.

4

Hooks auto-manage memory

SessionStart recalls memories on wake-up. Stop and PreCompact hooks auto-save important context.

NPM package

The MCP client is distributed as an NPM package. No global installation required — npx handles everything.

# Runs automatically via .mcp.json, or manually:

npx -y @agent-memo/mcp-client

# Or give your agent the setup guide URL:

https://agent-memo.ai/setup.md

View on NPM: @agent-memo/mcp-client

Next steps