A local connection for METTLE reverse-CAPTCHA challenges, which are verification tests designed for automated systems rather than ordinary human CAPTCHA solving. It runs as a Python package.

Use it when an agent needs to interact with METTLE verification challenges and the server is configured.

It provides machine-oriented verification, but the input does not describe the challenge types or available operations in detail.

mettle-mcp — MCP server for Claude Code and Codex by Creed-Space: A local connection for METTLE reverse-CAPTCHA challenges, which are…

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.

agentmods

npx agentmods add mcp/creed-space/mettle/mettle-mcp

Clone the repo

git clone --depth 1 https://github.com/Creed-Space/METTLE

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/creed-space/mettle/mettle-mcp.svg)](https://agentmods.dev/mcp/creed-space/mettle/mettle-mcp)

Your own site

<a href="https://agentmods.dev/mcp/creed-space/mettle/mettle-mcp"><img src="https://agentmods.dev/badge/mcp/creed-space/mettle/mettle-mcp.svg" alt="Measured on agentmods" 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. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

mettle-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 5d ago.

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.

server.json · 9 lines

What it actually says

{
  "mettle-mcp": {
    "command": "uvx",
    "args": [
      "mettle-verifier"
    ],
    "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.

5d ago First seen · 9 lines scan A a964ad8dde87

Subscribe to this mod's changes

mettle-mcp is an MCP server published in the GitHub repository Creed-Space/METTLE (0 stars, last pushed 5d ago), licensed Apache-2.0. 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 2026-08-31.

AI Safety Security agentic-ai ai-agents ai-trust ai-verification captcha

mcp

Authorize consequential AI agent actions before execution. Runs locally from the @decionis/mcp npm package. Needs 1 environment variable to run.

decionis/agent-safe-pipeline · not measured

glassbox-framework

Runtime constitutional verification for AI answers — claim reasoning, ECS, red team, audits. Runs locally from the @glassbox-framework/mcp npm package. Needs 4 environment variables to run.

TheBarmaEffect/glassbox · not measured

sysknife

MCP server "sysknife" as configured in lacs-project/sysknife. Launched with sysknife-cli. Needs 1 environment variable to run.

lacs-project/sysknife · not measured

evopilot-memory

MCP server "evopilot-memory" as configured in sdfdu/evopilot. Runs ${PLUGIN_ROOT}/mcp/server.py with python. Needs 4 environment variables to run.

sdfdu/evopilot · not measured

whitepact

ResponsibleAI — Enterprise AI Governance Platform: trust scoring, bias detection, hallucination detection, guardrails, compliance (NIST AI RMF / EU AI Act / ISO 42001), cost intelligence, drift monitoring. Runs locally from the rai-governance-platform Python package. Needs 1 environment variable to run.

Guruprasath-Annadurai/Whitepact · not measured

saferagenticai-mcp

MCP server exposing the SaferAgenticAI safety framework (canonical criteria + Implementation Patterns layer) to coding assistants. Runs locally from the saferagenticai-mcp Python package.

NellInc/saferagenticai-mcp · not measured