← all agents · MCP trust index

codefmt

Formats and lints JavaScript, Python, and HubL for automation platforms (Zapier, n8n, Pipedream, Make, HubSpot). Wraps code in each platform's runtime shell before formatting so top-level await, bare return, and injected globals parse cleanly.

Everything on this page was fetched from the agent's own well-known card by GolemreachTrustBot (outside-in probe, last checked 2026-08-29T17:06:33Z, first seen 2026-08-26T05:39:40Z). Not self-submitted, not cached from a directory.

Measured card surface

fieldvalue
A2A endpointhttps://codefmt.dev/api/a2a
card sourcehttps://codefmt.dev/.well-known/agent-card.json
protocolVersion0.3.0
agent version1.0.0
preferredTransportJSONRPC
providercodefmt
skills published1
card hash (canonical)c9ba74c6f1860aa6

Interface URLs

transportURL
JSONRPChttps://codefmt.dev/api/a2a

Skills (from card)

skilldescription
Format and lint automation-platform codeSend a text part containing JSON {"code","platform","language?"}. Returns JSON { formatted_code, diagnostics, error }. platform is one of zapier, n8n, pipedream, make, hubspot, hubl; language is javas

Card-drift history

Watching this agent since 2026-08-26T05:39:40Z. Hash = SHA-256 (16 hex) of the card's canonical JSON (sort_keys, no whitespace), so whitespace-only edits don't count as drift. Feed: api/a2a-drift.json.

No drift recorded yet for this agent — its card hash has been stable across every round since we started watching.

Same host, MCP side

Endpoints on this host that also appear in the official MCP registry, with their live trust grades — one host, two protocols, measured independently.

MCP endpointgradeMCP OKauth
https://codefmt.dev/api/mcpAopen

Golemreach Trust Layer · A2A index · method & opt-out · card re-fetched every sweep round; opt-out per /trust/bot removes the whole host within 48h.