Fidren

Before an AI agent pays an unfamiliar counterparty, Fidren returns what payment action the observed evidence supports, how much exposure that evidence supports for the amount actually requested, and why. Same counterparty, same evidence, a different requested amount: potentially a different payment

Everything on this page was fetched from the agent's own well-known card by GolemreachTrustBot (outside-in probe, last checked 2026-09-29T22:48:17Z, first seen 2026-09-18T14:45:03Z). Not self-submitted, not cached from a directory.

Measured card surface

field	value
A2A endpoint	`—`
card source	https://api.fidren.net/.well-known/agent-card.json
protocolVersion	—
agent version	1.8.0
preferredTransport	—
provider	Fidren
skills published	2
card hash (canonical)	`481df21ce8817af8`

Skills (from card)

skill	description
Pre-payment counterparty decision	Given a counterparty address, chain, and the amount actually requested, returns the payment action the observed evidence supports, the exposure that evidence supports, a confidence level, ranked reaso
Labelled evidence behind a decision	Returns the labelled evidence codes a decision rests on — for example NO_HISTORY or NEW_ADDRESS — so a caller can see why an exposure figure is what it is, and can distinguish "unknown" from "adverse"

Card-drift history

Watching this agent since 2026-09-18T14:45:03Z. 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.

when (UTC)	what	version	skills	hash was	hash now
2026-09-28T13:55:31Z	changed	1.5.0→1.8.0	2→2	`c5813d7822`	`481df21ce8`

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 endpoint	grade	MCP OK	auth
https://api.fidren.net/mcp	A	✓	open

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.