Skip to content

io.github.jdhart81/agent-trust-oracle

by jdhart81 · remote · no sign-in to list tools · v0.1.1 · published by GitHub user jdhart81

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

Changes · 4
CompareRegistry entry

6 tools: 4 change things and 2 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http agent-trust-oracle https://mcp.viridisconservation.com/trust/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

6 tools

Changes things 4Claude Code: ask
  • attestIssue a tamper-evident (hash-chained) trust attestation for an agent.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Issue a tamper-evident (hash-chained) trust attestation for an agent.
  • historyFull outcome history + attestation count + current score for an agent.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Full outcome history + attestation count + current score for an agent.
  • record_outcomeRecord an interaction outcome for an agent.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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).
  • verify_attestationVerify a previously issued attestation by recomputing its hash.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Verify a previously issued attestation by recomputing its hash.
Only reads 2Claude Code: allow
  • describe_agentFleet-standard self-description.No findings

    Why it is in this group

    • The name "describe_agent" says "describe": a word for reading.
    Description, as the server wrote it
    Fleet-standard self-description.
  • score_agentGet an agent's decay-weighted trust score in [0,1] and tier.No findings

    Why it is in this group

    • The description's first verb is "get": a word for reading.
    Description, as the server wrote it
    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.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 0.1.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-trust-oracle https://mcp.viridisconservation.com/trust/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agent-trust-oracle__score_agent",
      "mcp__agent-trust-oracle__describe_agent"
    ],
    "ask": [
      "mcp__agent-trust-oracle__record_outcome",
      "mcp__agent-trust-oracle__attest",
      "mcp__agent-trust-oracle__verify_attestation",
      "mcp__agent-trust-oracle__history"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as agent-trust-oracle. Review it before you use it.