A local tool that inspects an MCP server and scores its readiness for publication, including its schema and protocol. MCP is a standard for connecting AI applications to tools.

Use it to review and score an MCP server's publishability, schema, and protocol implementation.

It can reveal protocol or interface problems before an MCP server is published for others to use.

mcp-probe — MCP server by Incultnitollc

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/Incultnitollc/mcp-probe

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/incultnitollc/mcp-probe/mcp-mcp-probe/github.svg)](https://agentmods.dev/mcp/incultnitollc/mcp-probe/mcp-mcp-probe)

Your own site

<a href="https://agentmods.dev/mcp/incultnitollc/mcp-probe/mcp-mcp-probe"><img src="https://agentmods.dev/badge/mcp/incultnitollc/mcp-probe/mcp-mcp-probe/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/incultnitollc/mcp-probe/mcp-mcp-probe"><img src="https://agentmods.dev/badge/mcp/incultnitollc/mcp-probe/mcp-mcp-probe.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.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

mcp-probe 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 2mo 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.

.well-known/mcp/server.json · 10 lines

What it actually says

{
  "mcp-probe": {
    "command": "npx",
    "args": [
      "-y",
      "@incultnitollc/mcp-probe"
    ],
    "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.

2mo ago First seen · 10 lines scan A 6bcfe819816c

Subscribe to this mod's changes

mcp-probe is an MCP server published in the GitHub repository Incultnitollc/mcp-probe (2 stars, last pushed 2mo ago), 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 2026-08-31.

Building agents anthropic claude cli developer-tools mcp model-context-protocol

tiktok-agent-publisher

Local-first TikTok Content Posting API for AI agents: OAuth checks, dry-run and live uploads. Runs locally from the tiktok-agent-publisher npm package. Needs 3 environment variables to run.

davidmosiah/tiktok-agent-publisher · not measured

unblockingapi

MCP server "unblockingapi", hosted remotely at mcp.unblockingapi.com, as configured in unblockingapi/mcp.

unblockingapi/mcp · not measured

protocol-conformance

MCP conformance test harness. JSON-RPC, OAuth 2.1 PKCE, schemas, smoke, annotations. CLI + lib. Runs locally from the mcp-protocol-conformance npm package.

studiomeyer-io/mcp-protocol-conformance · not measured

slop-eval

Scores AI-generated UI for genericness ("slop") using an Anthropic LLM-judge rubric, with a --json mode for CI/agent quality gates and a documented programmatic API (scorecomposite, ScoreInput, LLMJudgeSource) for in-process use by agent frameworks. Runs locally from the slop-eval-cli Python package.

RudrenduPaul/slop-eval · not measured

tenant-pair

Multi-user tenancy library for MCP servers. Pairs, groups, bi-temporal shared state, DSGVO erasure. Runs locally from the mcp-tenant-pair-demo npm package.

studiomeyer-io/mcp-tenant-pair · not measured

meok-watermark-attest-mcp

EU AI Act Article 50 watermarking + transparency compliance MCP. Built for the 2 August 2026 cliff. Article 50 transparency obligations apply from 2 Aug 2026; pre-existing systems have until 2 Dec 2026. Classify Art 50 obligations (chatbot disclosure, GPAI synthetic-content marking per C2PA-2.0, deepfake disclosure…

CSOAI-ORG/csoai-watermark-attest-mcp · not measured