Skip to content
MCP server

AgentPlaybooks

Keep skills, MCP references, memory and secrets in one portable playbook for any agent

Install
Pricing
Open source
Platforms
API, self-hosted
Runs
Remotely
Version
0.10.1
Listing updated
3 days ago

About AgentPlaybooks

AgentPlaybooks is an open-source MCP server for ai models and llm tooling. It runs as a hosted remote server, so there is nothing to install locally.

The idea is a playbook as an agent's portable work profile: a persona, skills, MCP server references, canvas documents, key-value memory and credentials that agents use without seeing. One command deploys it to Claude Code, Cursor, Codex, Antigravity and Hermes, and the site says it also syncs across ChatGPT, Gemini and local models.

This registry entry points at the manage endpoint, agentplaybooks.ai/api/mcp/manage over Streamable HTTP, through which an agent can read and edit the playbook. Skills can carry files or timestamped recordings of a task, aimed at agents that learn by watching, including future robots. A secret proxy tool called use_secret lets an agent use a credential without exposing it. Sharing a playbook URL gives a team consistent behaviour across platforms.

The project is open source and self-hostable, with private versioned recovery of agent configuration.

Install

Run in a terminal

claude mcp add --transport http agentplaybooks https://agentplaybooks.ai/api/mcp/manage

Add to Settings → Connectors → Add custom connector

https://agentplaybooks.ai/api/mcp/manage
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "agentplaybooks": {
      "url": "https://agentplaybooks.ai/api/mcp/manage"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "agentplaybooks": {
      "type": "http",
      "url": "https://agentplaybooks.ai/api/mcp/manage"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "agentplaybooks": {
      "serverUrl": "https://agentplaybooks.ai/api/mcp/manage"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "agentplaybooks": {
      "type": "http",
      "url": "https://agentplaybooks.ai/api/mcp/manage"
    }
  }
}

Tools this server provides (1)

Taken from the project documentation; the running server may differ.

use_secret
Lets an agent use a stored credential through the proxy without seeing it.

What it does

Portable playbook
Persona, skills, MCP references and instructions in one place.
Multi-agent deploy
One command to Claude Code, Cursor, Codex, Antigravity and Hermes.
Memory store
Key-value memory across sessions.
Canvas documents
Structured markdown the agent reads and writes.
Secret proxy
Agents use credentials without seeing them.
Self-hostable
Open source with standard formats.
Versioned recovery
Private history for configuration.

Good for

  • Move agent setup between Claude Code and Cursor
  • Share one playbook across a team
  • Give an agent credentials without exposing them
  • Back up skills and project instructions

Pricing

Open source

Open source and self-hostable; hosted plan prices not published

Prices change. Check agentplaybooks.ai before you buy.

AgentPlaybooks FAQ

Is it open source?

The site says it is open source and self-hostable.

Which agents are supported?

Claude Code, Cursor, Codex, Antigravity and Hermes for deployment.

Can agents see my secrets?

The site says credentials are used without the agent seeing them.

Does it store memory?

Yes, key-value memory across sessions.

Is AgentPlaybooks free?

Yes. AgentPlaybooks is open source, so you can use and self-host it for free.

How do I add AgentPlaybooks to Claude Code?

Run this command in your terminal: claude mcp add --transport http agentplaybooks https://agentplaybooks.ai/api/mcp/manage

What are the best alternatives to AgentPlaybooks?

The closest alternatives to AgentPlaybooks are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and note1.

Alternatives to AgentPlaybooks

  1. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  2. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  3. MCP server for searching the Claude Code Ultimate Guide from any MCP client

    Runs locally
    • Open source
    • 6.5K GitHub stars
    • AI models and LLM tooling
  4. Local-first long-term memory layer for AI agents, served over MCP

    Not checked yet
    • 5 tools
    • Remote
    • Open source
    • 1.3K GitHub stars
    • Knowledge and memory
  5. note1

    MCP server

    MCP server giving AI assistants search and summaries across your note1 meetings

    • 4 tools
    • Remote
    • Free trial
    • 1 GitHub star
    • Productivity