All servers · AI models & agents · Agent payments (x402)

Collusion Sentinel for Agent Markets

com.textforagents/collusion-sentinel-agent-markets · v1.0.0

New (7 days)

Measured by MCP Station

Last check	Reachable
Checked at	—
Check success 7 / 30 days	—
First-try success 30 days	—
Median response	—
Lookups 30 days	—
Authentication	No auth
MCP version	2025-03-26
Rank score	—
Declared risk	Not declared (tools carry no read/destructive hints)
Capabilities declared	tools
Tool definitions	3 tools · with description 100% · input schema is an object 100% · read/destructive hints 0%

Description written by the publisher, not verified

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

Connect

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

claude mcp add --transport http collusion-sentinel-agent-markets https://textforagents.com/products/collusion-sentinel-agent-markets/mcp

{
  "mcpServers": {
    "collusion-sentinel-agent-markets": {
      "url": "https://textforagents.com/products/collusion-sentinel-agent-markets/mcp"
    }
  }
}

Tools as reported by the server

sentinel_audit
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_certify
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_plan
Score-keyed counterparty rotation + memory hygiene plan (included).

Website · JSON · Text for agents · Registry updated 2026-10-21