Assess Agent
assess_agentImmediate 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.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"endpointUrl": "<endpointUrl>"
},
"name": "assess_agent"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| endpointUrl | Yes | 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. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | Yes | ||
| agent | Yes | ||
| status | Yes | ||
| matched | Yes | ||
| decision | Yes | ||
| freshness | Yes | ||
| confidence | Yes | ||
| historical | Yes | ||
| initialRisk | Yes | ||
| limitations | Yes | ||
| reasonCodes | Yes | ||
| reachability | Yes | ||
| assessmentVersion | Yes |