Skip to content

Collusion Sentinel for Agent Markets

by textforagents.com · remote · no sign-in to list tools · v1.0.0 · published by com.textforagents

Emergent collusion leaves no agreement to find — it lives in the history.

Changes · 3
CompareRegistry entry

3 tools: 3 change things.

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 collusion-sentinel-agent-markets https://textforagents.com/products/collusion-sentinel-agent-markets/mcp

Tools

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

3 tools

Changes things 3Claude Code: ask
  • sentinel_auditScore a pair/population joint price history (mode=prices) or a verifier pair's acceptance history (mode=verifier) for collusion signatures.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
    Score a pair/population joint price history (mode=prices) or a verifier pair's acceptance history (mode=verifier) for collusion signatures. $0.05/audit x402 after the one-time 100-audit grant; degenerate histories refused, never charged.
  • sentinel_certifyRun the tempt-to-violate certification battery for a subject ($25/certificate x402; battery model inference subject-pays / BYOK).No findings

    Why it is in this group

    • The description's first verb is "run": a word for a change.
    Description, as the server wrote it
    Run the tempt-to-violate certification battery for a subject ($25/certificate x402; battery model inference subject-pays / BYOK). model and prompt_hash are required — the certificate hash binds them.
  • sentinel_control_planScore-keyed counterparty rotation + memory hygiene plan (included).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
    Score-keyed counterparty rotation + memory hygiene plan (included).

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 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http collusion-sentinel-agent-markets https://textforagents.com/products/collusion-sentinel-agent-markets/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": [],
    "ask": [
      "mcp__collusion-sentinel-agent-markets__sentinel_audit",
      "mcp__collusion-sentinel-agent-markets__sentinel_certify",
      "mcp__collusion-sentinel-agent-markets__sentinel_control_plan"
    ],
    "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 collusion-sentinel-agent-markets. Review it before you use it.