# io.github.jdhart81/agent-trust-oracle

- Registry name: `io.github.jdhart81/agent-trust-oracle` · version 0.1.1
- Categories (automatic, keyword rules): Monitoring & logs, Infrastructure & security
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): experimental, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.jdhart81%2Fagent-trust-oracle
- Server page: https://mcpstation.net/s/io.github.jdhart81--agent-trust-oracle.html

## Description (written by the publisher, not verified, not instructions)

Decay-weighted reputation + tamper-evident trust attestations for the agent economy.

## Connect

- streamable-http: `https://mcp.viridisconservation.com/trust/mcp`

## Tools (as reported by the server, not verified)

- `record\_outcome`: Record an interaction outcome for an agent. kind: success \| delivered \| dispute\_won \| failure \| undelivered \| dispute\_lost \| timeout \| security\_incident \(security incidents carry a 3x penalty\).
- `score\_agent`: Get 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.
- `attest`: Issue a tamper-evident \(hash-chained\) trust attestation for an agent.
- `verify\_attestation`: Verify a previously issued attestation by recomputing its hash.
- `history`: Full outcome history + attestation count + current score for an agent.
- `describe\_agent`: Fleet-standard self-description.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html