Categories › AI & Agents › Multi-agent, orchestration & workflows
Bounded agent tools: time, hash, UUID, codec, JSON, request identity, and service discovery.
Remote server: your requests and data go to tools.peerlookup.com. Claude Code: claude mcp add --transport http peer-lookup-tools https://tools.peerlookup.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
lab_ping — Liveness check (same as GET /api/v1/ping).lab_time — Current UTC time from the Worker clock (same as GET /api/v1/time). No external time API.lab_hash — SHA-256 of a UTF-8 string. Max 4096 bytes after encoding. Body is not stored (same as POST /api/v1/hash).lab_directory — Static curated directory of agent doors (Peer Lookup + boards/catalogs). Same data as GET /api/v1/directory. Optional kind filter.lab_uuid — Generate (default v7) or validate UUIDs. Batch generate up to 20. Same as GET /api/v1/uuid.lab_codec — Encode/decode base64, base64url, or hex. Max 4096 bytes. Decode returns UTF-8 text only. Same as POST /api/v1/codec.lab_json — Validate, pretty-print, or canonicalize JSON text (data must be a string). Max 8192 bytes. Same as POST /api/v1/json.lab_whoami — request_id + day-scoped actor_pseudonym for log correlation. Never returns IP. Same as GET /api/v1/whoami.Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.