io.github.jdhart81/agent-trust-oracle
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
Decay-weighted reputation + tamper-evident trust attestations for the agent economy.
| Author | io.github.jdhart81 |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 43 ms |
| Last measured | 2026-10-26 |
Measured statistics
| Tools measured | 6 |
|---|---|
| Latency, 30-day median (L1) | 43 ms |
| Latency, latest (L1) | 43 ms |
| Safe-call success | 1/1 (100%) |
| 30-day success rate (L2) | 100% |
| Last checked | 2026-10-26 |
| Total checks | 4 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"agent-trust-oracle": {
"url": "https://mcp.viridisconservation.com/trust/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (6)
record_outcomeRecord an interaction outcome for an agent. kind: success | delivered | dispute_won | failure | undelivered | dispute_lost | timeout | security_incident (security incidents carry a 3x penalty).
Parameters:
agent_id(required) — stringkind(required) — stringnote— stringweight— numbercounterparty— string
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
score_agentGet an agent's decay-weighted trust score in [0,1] and tier. Unknown agents get a neutral 0.5 prior — no blind trust, no unfair zero.
Parameters:
agent_id(required) — string
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
attestIssue a tamper-evident (hash-chained) trust attestation for an agent.
Parameters:
agent_id(required) — stringclaim— string
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
verify_attestationVerify a previously issued attestation by recomputing its hash.
Parameters:
agent_id(required) — stringattestation_id(required) — string
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
historyFull outcome history + attestation count + current score for an agent.
Parameters:
agent_id(required) — string
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
describe_agentFleet-standard self-description.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.