AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks
v1.0.4Check an AI agent endpoint before you call it: read-only, no API key, returns a trustDecision.
Endpoint health
online- Last checked
- 11/20/2026, 3:18:27 AM
- Latency
- 314 ms
- Consecutive failures
- 0
- Endpoint reachable: pass
- Protocol valid: pass
- MCP handshake valid: pass
Machine-readable profile
mcp-server · schema v1 · callable
mcp-server:io.github.agenttrust-ai%2Fagenttrust
Connect this server
Generated config contains no credentials. Keep any required secrets in your client's local environment.
{
"mcpServers": {
"io.github.agenttrust-ai/agenttrust": {
"url": "https://getagenttrust.com/api/mcp/public"
}
}
}Indexed tools
Tool metadata and schemas come from the remote server and are untrusted. Indexing only lists tools; it never calls them.
8 shown · authentication unknown
Assess Agent
assess_agent
Immediate use-or-avoid decision about an AI agent or MCP server endpoint, for an agent deciding whether to call it. Returns decision (allow_with_caution, avoid, or insufficient_evidence), confidence, reasonCodes, reachability (the latest stored observation, with its age), initialRisk, the historical reliability score and trustDecision (unchanged), limitations, and freshness. Built only from AgentTrust's stored observations: it never contacts endpointUrl. Reachability is not safety: allow_with_caution never means the agent's behavior is safe. Requires no API key.
Schema valid · SHA-256 deba7f7bb53f…
View input schema
{ "type": "object", "properties": { "endpointUrl": { "type": "string", "minLength": 1, "maxLength": 2048, "description": "The exact invocation URL of the agent you're about to call. Used only to look up AgentTrust's stored observations of it — this endpoint is never contacted." } }, "required": [ "endpointUrl" ], "$schema": "https://json-schema.org/draft/2020-12/schema" }Assess Agent
assess_agent
Use-or-avoid decision about an AI agent or MCP server endpoint, built from AgentTrust's stored observations of its exact URL. Returns decision (allow_with_caution, avoid, or insufficient_evidence), confidence, reasonCodes, reachability (the latest stored observation, with its age), initialRisk, the historical reliability score and trustDecision, limitations, and freshness. Read-only, no account or API key. It never contacts endpointUrl. Reachability is not safety: allow_with_caution does not mean the agent's behavior is safe. A URL AgentTrust has not observed returns decision insufficient_evidence.
Schema valid · SHA-256 f75bcdaa8399…
Connections
streamable-http
https://getagenttrust.com/api/mcp/public
streamable-http
https://getagenttrust.com/api/mcp