What is council-signal-mcp?

A local measurement tool for judging AI systems across 13 fixed areas. It produces signed, repeatable results and distinguishes an unmeasured result from a failure.

It is for evaluating AI behaviour, comparing runs, and recording whether checks were performed. It can also monitor containment, meaning limits placed on what an AI system can do.

It gives you consistent measurements without treating them as certification or proof of safety. This helps avoid claiming that a system passed when it was simply not measured.

council-signal-mcp — MCP server for Claude Code and Codex by CSOAI-ORG

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/CSOAI-ORG/csoai-static-deploy2

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/csoai-org/csoai-static-deploy2/council-signal-mcp/github.svg)](https://agentmods.dev/mcp/csoai-org/csoai-static-deploy2/council-signal-mcp)

Your own site

<a href="https://agentmods.dev/mcp/csoai-org/csoai-static-deploy2/council-signal-mcp"><img src="https://agentmods.dev/badge/mcp/csoai-org/csoai-static-deploy2/council-signal-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/mcp/csoai-org/csoai-static-deploy2/council-signal-mcp"><img src="https://agentmods.dev/badge/mcp/csoai-org/csoai-static-deploy2/council-signal-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

Socket warn 14 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Security

Grade A, and why

council-signal-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

csoai_pkg/server.json · 9 lines

What it actually says

{
  "council-signal-mcp": {
    "command": "uvx",
    "args": [
      "council-signal-mcp"
    ],
    "env": {}
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

today First seen · 9 lines scan A 96e62bb346d3

Subscribe to this mod's changes

council-signal-mcp is an MCP server published in the GitHub repository CSOAI-ORG/csoai-static-deploy2 (0 stars, last pushed today), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-14.

Analytics and metrics Building agents ai-compliance ai-governance ai-measurement ed25519 eu-ai-act mcp-server

meok-attestation-verify

Tiny zero-dependency verifier for MEOK AI Labs compliance attestations (DORA, NIS2, CRA, EU AI Act, CSRD, AI-BOM, Gods Eye). Pipe a signed cert on stdin, get VALID/INVALID back. HMAC-SHA256. By MEOK AI Labs. Runs locally from the meok-attestation-verify Python package.

CSOAI-ORG/meok-attestation-verify · not measured

complyedge

Runtime EU AI Act deny for agent I/O (Article 5, Article 50) — ComplyEdge Python SDK. Runs locally from the complyedge Python package.

ComplyEdge/complyedge · not measured

eu-ai-act-compliance-mcp

EU AI Act compliance for AI agents. 410 articles from EUR-Lex via FTS5 search. Instant risk scan, deadline tracker, 42-point audit, documentation generator, penalty calculator. Zero-config free tier. Built by MEOK AI Labs. Runs locally from the eu-ai-act-compliance-mcp Python package.

CSOAI-ORG/eu-ai-act-compliance-mcp · not measured

c2pa-watermark-mcp

C2PA Watermark & Provenance MCP server. Built with c2pa-python. Runs locally from the c2pa-watermark-mcp Python package.

CSOAI-ORG/c2pa-watermark-mcp · not measured

meok-eu-platform-worker-mcp

EU Platform Workers Directive (2024/2831) compliance — employment-status presumption, algorithmic-management disclosure, human oversight of significant decisions, worker data protection, member-state transposition tracking, misclassification-risk forecast. Targets EU gig-economy platforms (€20bn market). Transposition…

CSOAI-ORG/meok-eu-platform-worker-mcp · not measured

meok-ev-recall-transport-mcp

EV-recall transport compliance — ADR Class 9 (UN3480/3481/3536/3556/3557/3558), DGSA workflow, thermal-runaway routing, OEM recall protocols. For UK car transporters under ADR 2025 + ZEV Mandate. By MEOK AI Labs. Runs locally from the meok-ev-recall-transport-mcp Python package.

CSOAI-ORG/meok-ev-recall-transport-mcp · not measured