LifeClaw

Install LifeClaw in your MCP client

LifeClaw is a Model Context Protocol server. Add it to your MCP client config once, restart, and the server's tools become available to your AI assistant. The same JSON snippet below works across all four major clients — only the config file path differs.

1. Locate your client's MCP config file.
   • Cursor: ~/.cursor/mcp.json
   • Claude Desktop (macOS): ~/Library/Application Support/Claude/claude_desktop_config.json
   • Claude Desktop (Windows): %APPDATA%\Claude\claude_desktop_config.json
   • VS Code: Settings → Extensions → MCP
   • Windsurf: Settings → MCP Servers
2. Add LifeClaw to the mcpServers map — paste the snippet below into your config file. If you already have other MCP servers, merge the entry into the existing mcpServers object.
3. Restart your client so it picks up the new server.
4. Verify — ask the assistant to list available tools; LifeClaw's tools should appear.

{
  "mcpServers": {
    "lifeclaw": {
      "command": "npx",
      "args": [
        "-y",
        "@lifeclaw/mcp-server"
      ],
      "note": "Replace with the actual package name from the server's documentation."
    }
  }
}

Tools exposed by LifeClaw

Once installed, LifeClaw exposes the following MCP tools to your AI assistant. Each tool can be called directly by the assistant whenever its capability is relevant to your prompt.

• search_places

  Search businesses (restaurants, salons, clinics, hotels…) by free text. `location` is REQUIRED and decides which country is searched — a city or country name ("Tokyo", "Singapore"). Returns up to `limit` places with a `cid` to pass to get_place. Costs 5 points.

• get_place

  Full details for one place from search_places: phone, hours, rating, website, booking link. Pass the same `location` you searched with. `phone_ref` is the handle call_business needs; when it is null the place cannot be called and `phone_ref_unavailable_reason` says why — show the user `detail.phone` / `detail.booking_url` instead. Costs 15 points.

• call_business

  Phone a business and wait for the outcome. `action="book"`: reserve. Required: merchant_name, date (YYYY-MM-DD), time_ (HH:MM, 24h), party_size, name; recommended: contact_phone (E.164). Both are the MERCHANT's local time. `action="inquiry"`: ask something — put the question in `purpose`; the answer comes back in `result.summary`. `reply_language` is the language of the result fields (the call itself is spoken in the merchant's language). `idempotency_key`: reuse the same key to recover this a

• modify_booking

  Phone the venue to cancel or reschedule a confirmed booking from list_bookings. `action` is "cancel" or "reschedule"; reschedule needs new_date and/or new_time (merchant local). When the venue confirms, the booking record is updated for you. Same waiting and idempotency rules as call_business.

• wait_for_call

  Keep waiting for a call that call_business / modify_booking / call_person / call_me reported as in_progress. Returns the flat result once the call ends, or in_progress again — just call it again.

• list_bookings

  The account's bookings (confirmed, cancelled, answered inquiries). `status` filters: "confirmed", "cancelled", "answered", or "" for all.

• account_status

  Points balance, display name, and the selected receiving number for call_me (masked). Use receiving_phone_status for setup and caller_id_status for outbound display and outbound-display state. 300 points ≈ one minute of calling.

• receiving_phone_status

  Check where call_me would ring (masked). A number must be explicitly selected and verified by voice; SMS login alone does not qualify. The user can set it in the web app without enabling outbound Caller ID. Direct them to setup_url if no receiving number is ready.

• caller_id_status

  Check the owner's outbound Caller ID. Verified plus enabled display enables call_person. call_me uses a separate receiving number. If setup is needed, direct the user to `setup_url`: Settings → Caller ID, bind their own phone, answer Twilio's verification call and enter its code. Then check again. Business calls do not need this setup.

• list_contacts

  List the token owner's saved contacts with masked phone numbers. Each contact_ref pins the current name and number for call_contact. If two names could match a request, ask the user to choose one exact name. Never repeat a full contact number in chat.

• save_contact

  Add or update one contact after confirming name and number with the user. phone_number must be E.164, e.g. +85291234567. This updates the same address book used by the web app. The result masks the number; do not echo the full number in a chat reply. Set user_confirmed only after agreement.

• update_contact

  Edit a saved contact's name and/or E.164 phone number atomically. Confirm the existing contact and proposed change with the user first. A name conflict refuses instead of overwriting another person. Return values mask the number; do not repeat a full number in chat.

• delete_contact

  Delete a saved contact by exact name after the user confirms deletion.

• call_person

  Call one private person and relay one message from the user. Ask the user to confirm the recipient, E.164 number and exact spoken message first, then set user_confirmed=true. `original_message` is the user's unedited request; `message` is the faithful sentence spoken aloud. Both are screened. The AI identifies itself and passes on the message; this tool is not an open-ended conversation or a broadcast tool. Requires the user's verified, enabled outbound Caller ID. Call caller_id_status for rea

• call_contact

  Call a saved private contact without passing their full number. First list_contacts and confirm the chosen name, masked number and exact spoken message with the user. Pass that contact_ref and user_confirmed=true. If the contact changes before dialing, re-list and confirm again. This uses call_person's screening, verified Caller ID, daily cap and strict no-platform-number-fallback policy. Check caller_id_status first. Its no-answer retry decision and idempotency rules are the same as call_perso

• call_me

  Ring the user's own phone, read them `message`, and bring back what they say. A phone call interrupts the user. Follow their explicit instructions about whether and when to call, including an immediate call or a call when a job finishes. Otherwise prefer chat for routine updates; call for a time-sensitive decision only they can make after chat has no explicit answer, or for a still-active important event after the workflow's chosen wait if nobody has acknowledged it. There is no fixed waiting p

Transport

LifeClaw supports the following MCP transports. Most AI clients use stdio by default for locally-installed servers.

More build.protocol_tooling.mcp MCP servers

Other Model Context Protocol servers in the same space as LifeClaw. Each one adds different capabilities to your AI assistant — pick based on the data sources or workflows you need.

• Horse Truth Machine Intelligence

  Australian thoroughbred racing intelligence for AI agents and developers. Provides horse profiles, race rankings and race-day analysis through MCP, with free discovery tools and paid machine-readable data.

• open-meteo-mcp-server

  Model Context Protocol server for Open-Meteo weather APIs

• mcp

  Marrow AI MCP server: a named yes before your AI agent acts, and proof the next agent can reuse.

• Proofsource

  AI visibility: which buyer questions name your brand in ChatGPT, Perplexity, Claude, AI Overviews.

• MissedTakes

  Graded track records of NFL and election pundits: records, leaderboards, takes, game and race calls.

• FootballGPT

  Football coaching advice, session plans and animated practices from your AI assistant.

• Feeder

  Read, search and organize the RSS feeds you follow in Feeder. Tool calls need Feeder Plus.

• dopost

  Schedule and analyze posts on 12 networks, incl. Bluesky, Mastodon and Telegram, from any AI agent

Browse the full MCP server directory or use Stork's one-line install to let your agent pick the right server automatically.