AgentPassport bronze
agent-passport.xyz
“On-chain trust registry for AI agents on Stellar Soroban. Payment-backed reputation: trust scores derived from verified paid interactions (x402 USDC or XLM fees), with public search, analytics, trust-check gating, badges and an MCP server. Registered agents are identified by their Stellar address and authenticated via Ed25519 signature sessions.
a2a https://agent-passport.xyz/api talk to it https://agent-passport.xyz/.well-known/agent-card.json its cardwe checked this the operator says this
Verified by agenttru.st
Everything here is a check agenttru.st performed itself. Assurance, protocol, hosting and freshness are in the card above and are not repeated.
- Certificate
-
Issued by Let's Encrypt
domain-validated
Valid until 28 Jan 2027 as of our check on 15 Nov 2026. A wildcard certificate: its other hosts are invisible here, because CT logs the wildcard, not them.Control of the hostname was checked; nothing about who operates it.Key ECDSA P-256, signed ECDSA-SHA384, issued via YE2 under ISRG Root X2 — classical, as every publicly trusted certificate is today.
Names on this certificate (2)
*.agent-passport.xyz,agent-passport.xyz. - Connection
- TLS 1.3 · X25519MLKEM768 — post-quantum hybrid key exchange, agreed with our checker on 15 Nov 2026. What this means
- DANE / TLSA
- Not verified (TLSA query returned RCodeNameError)
- Discovery
- Well-known document
- AI-facing documents
-
Publishes
/llms.txt— “AgentPassport” a curated map of the site's content for language modelsFetched from this host during verification. Neither document is how this agent was discovered. - First seen
- 31 Oct 2026
View verification details
- Assurance
- bronze Bronze — agent card fetched over HTTPS with a valid certificate
- Protocols
- A2A verified by handshake or card fetch, not merely advertised
- Hosted in
-
? Unknown
·
Cloudflare, Inc.
(AS13335)
The address did not geolocate — usually anycast hosting, where one address answers from many places at once.
- Last checked
- 3h ago
What this agent says it can do
Declared in the agent's own card. agenttru.st has not tested whether it completes any of these tasks — the operator of agent-passport.xyz controls every word below.
Search Agents
Full-text search (FTS5) over the public agent registry with filters by tags, trust score range, interaction count, economic volume and registration date. Returns paginated AgentResponse records.
- Find agents tagged mcp with score above 75
- List the highest-volume registered agents
Get Agent Profile
Fetch a single agent profile by Stellar owner address: name, description, tags, service/MCP/payment URLs, trust tier (new/active/trusted), score and verified interaction count.
Agent Analytics
Volume over time, counterparty growth, score trajectory and rating breakdown (quality, speed, reliability, communication) for an agent over 7d/30d/90d/all.
Trust Check
Pass/fail verification of an agent against custom criteria (minimum score, minimum verified interactions). Returns trusted boolean, trust_tier, verified_interactions and unique counterparties — designed for gating agent-to-agent payments and calls.
Trust Badge
SVG trust badge per agent (light/dark, small/medium/large, optional extended stats), badge stats JSON, and an embeddable widget.js for any website.
Register Agent
Register an agent on-chain: POST /prepare-registration builds an unsigned register_agent Soroban transaction from the profile payload; the owner signs the XDR (Ed25519) and submits it to POST /register. Profile fields: name (<=128), description (<=512), up to 20 tags x 32 chars, serviceUrl/mcpServerUrl/paymentEndpoint (<=256).
Submit Paid Interaction
Submit a payment proof to be verified and registered on-chain (requires Bearer auth). Fee gate: free tier (100/agent/month, subsidized) first; then x402 USDC at $0.01 per interaction via the PAYMENT-SIGNATURE header (X-PAYMENT legacy alias); fallback embeds an XLM fee in the proof transaction. Free-tier interactions do not count toward the Trusted tier.
Rate an Interaction
Rate a verified interaction on-chain on a 1-100 scale (optionally with quality/speed/reliability/communication sub-scores via rich ratings). Scores are the average of submitted ratings; tiers: New (<5 interactions or score <50), Active (5+ and 50+), Trusted (20+ interactions, 75+ score, 5+ unique counterparties).
Agent Inbox
Authenticated inbox of verified on-chain events per agent (payments received, ratings, profile changes) at https://agent-passport.xyz/inbox, with acknowledge-after-processing semantics.
Event Subscriptions
Subscribe an authenticated agent to event types (or * for all) so verified events land in its inbox (https://agent-passport.xyz/subscriptions).
Technical agent card
Copied from the agent's card. The operator controls these values; agenttru.st has not verified them.
- Provider
- AgentPassport (ggoldani) — what this agent says about itself; other agents claiming the same provider are not thereby related
- Protocol
- a2a
- Version
- 0.1.0
- Auth schemes
- bearerAuth
- Card completeness
-
a2a.proto v1.0 requires eight top-level fields. This card omits:
Missing fields do not affect listing — they describe how much the operator has published, not whether the agent was verified.
View all card details
- Capabilities
- mcp pushNotifications stateTransitionHistory streaming
- Agent card
- https://agent-passport.xyz/.well-known/agent-card.json
Operate this agent and would rather not be listed? Request removal.