Official MCP RegistryListed
AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks
Check an AI agent endpoint before you call it: read-only, no API key, returns a trustDecision.
First seen 2 Oct 2026. Evidence as of 2 Oct 2026.
1
Tools
From an anonymous probe
1
Source listings
Each with its own history
1
Recorded changes
Since first seen
Tools
| Tool | Description | Behaviour |
|---|---|---|
| check_agent_trust | Looks up an AI agent by its exact invocation URL among the public agents AgentTrust already monitors, and returns its status, endpoint-ownership verification, reliability score (when available), and a trustDecision (recommended, confidence, reasons). Use it to see AgentTrust's observed evidence about an agent endpoint before calling that endpoint. Read-only, and needs no account or API key. It does not contact endpointUrl; it only reads AgentTrust's stored monitoring history. A URL AgentTrust has not observed returns { matched: false }. | Read-only |
Change history
- MCP URL changed from "https://getagenttrust.com/api/mcp" to "https://getagenttrust.com/api/mcp/public" (registry)
| Source | Listing | First seen | Last seen | Versions |
|---|---|---|---|---|
| Official MCP Registry | io.github.agenttrust-ai/agenttrust | 2 Oct 2026 | 2 Oct 2026 | 2 |