A security tool for checking Model Context Protocol servers, which let AI agents connect to external tools and data. It verifies trust, scans for security issues, and searches a directory of more than 4,200 servers.

Use it to check server trust scores, look for security problems, and find MCP servers for a project.

It helps developers assess whether an external MCP server is trustworthy before connecting it to an agent.

mcp-shield — MCP server for Claude Code and Codex by cybercraftsolutio

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/cybercraftsolutionsllc/trust-gated-agent-example

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/cybercraftsolutionsllc/trust-gated-agent-example/mcp-shield.svg)](https://agentmods.dev/mcp/cybercraftsolutionsllc/trust-gated-agent-example/mcp-shield)

Your own site

<a href="https://agentmods.dev/mcp/cybercraftsolutionsllc/trust-gated-agent-example/mcp-shield"><img src="https://agentmods.dev/badge/mcp/cybercraftsolutionsllc/trust-gated-agent-example/mcp-shield.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. 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-shield 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 7d 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.

listed in the official MCP registry · 6 lines

What it actually says

{ "mcp-shield": { "url": "https://mcp.craftedtrust.com/api/v1/mcp", "type": "streamable-http" } }

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.

7d ago First seen · 6 lines scan A 8a08ad880a8b

Subscribe to this mod's changes

mcp-shield is an MCP server published in the GitHub repository cybercraftsolutionsllc/trust-gated-agent-example (0 stars, last pushed 5mo 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.

Security ai-agents ai-security langgraph mcp mcp-server

agent-security-scanner-mcp

Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities. Runs locally from the agent-security-scanner-mcp npm package.

sinewaveai/agent-security-scanner-mcp · not measured

calllint

Static preflight safety gate for MCP servers — scan configs before you run them. Never executes. Runs locally from the calllint-mcp npm package.

calllint/calllint · not measured

mastyf.ai

Runtime proxy for MCP security, cost governance & audit. Runs locally from the @mastyf_ai/server npm package. Needs 3 environment variables to run.

mastyf-ai/mastyf.ai · not measured

owasp-agentic-mcp

OWASP Top 10 for AI Agents security assessment tools. Capabilities: full agent security scan, prompt injection detection, tool poisoning check, excessive agency, data leakage. Built by MEOK AI Labs. Runs locally from the owasp-agentic-mcp Python package.

CSOAI-ORG/owasp-agentic-mcp · not measured

zugawatch

MCP server "zugawatch" as configured in Zuga-luga/zugawatch. Runs locally from the zugawatch Python package.

Zuga-luga/zugawatch · not measured

euvd-mcp

MCP server "euvd-mcp" as configured in TLDart/EUVD-MCP. Runs locally from the euvd-mcp Python package.

TLDart/EUVD-MCP · not measured