Docs

Setup in two minutes

AI Babysitter is a remote MCP server. Connect your agent by URL, authenticate in your browser, and every session starts with battle-tested context.

1. Connect by URL (recommended)

Subscribe, then add the server to your harness — no API key needed. In Claude Code:

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

Then run /mcp, select aibabysitter, and choose Authenticate — log in with your AI Babysitter email and password and click Approve. Subscribers get per-harness instructions in the setup guide.

2. Headless servers & CI (API key method)

No browser available, or your harness doesn't support remote MCP with OAuth? Generate an API key from your dashboard (shown once — save it; regenerate anytime) and run the stdio package instead. Claude Code: add this to ~/.claude/mcp.json. Any MCP-capable harness (Cursor, Windsurf, custom agents) works the same way.

{
  "mcpServers": {
    "aibabysitter": {
      "command": "npx",
      "args": ["-y", "@aibabysitter/mcp-server"],
      "env": {
        "AIBABYSITTER_API_KEY": "aibab_...your key...",
        "AIBABYSITTER_API_URL": "https://api.aibabysitter.ai"
      }
    }
  }
}

3. Tell your agent to use it

Add this to your project's AGENTS.md / CLAUDE.md so the agent consults the knowledge base automatically:

## Knowledge Base (Required)
Before any coding or planning task:
1. Call query_knowledge_base with the task description.
2. Use returned lessons to ground your approach.
3. After completing a task, call push_lesson with the key lesson learned.

The tools

query_knowledge_base(query, partition?)

Full-text search over curated lessons. Returns up to 5 ranked results with title, content, and tags.

push_lesson(title, content, tags?, partition?)

Write a lesson back to your tenant's partition — your agents compound what they learn across sessions.

get_usage()

Current plan, monthly call usage, and quota reset date.

Troubleshooting

Stuck? Email support@aibabysitter.ai.