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.
git clone --depth 1 https://github.com/mentu-ai/metamcpWrote 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.
[](https://agentmods.dev/mcp/mentu-ai/metamcp/metamcp)<a href="https://agentmods.dev/mcp/mentu-ai/metamcp/metamcp"><img src="https://agentmods.dev/badge/mcp/mentu-ai/metamcp/metamcp/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.
<a href="https://agentmods.dev/mcp/mentu-ai/metamcp/metamcp"><img src="https://agentmods.dev/badge/mcp/mentu-ai/metamcp/metamcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
metamcp 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 12d 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.
What it actually says
{
"metamcp": {
"command": "npx",
"args": [
"-y",
"@mentu/metamcp"
],
"env": {}
}
}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.
- 12d ago First seen · 10 lines scan A 29b68ade333b
metamcp is an MCP server published in the GitHub repository mentu-ai/metamcp (17 stars, last pushed 3d 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 2026-08-30.
Other mcp servers, from other repositories
wet-mcp
Open-source MCP Server for web search, extract, crawl, academic research, and library docs with embedded SearXNG. Runs locally from the wet-mcp Python package. Needs 2 environment variables to run.
mnemo-mcp
Open-source MCP Server for persistent AI memory with embedded sync. Runs locally from the mnemo-mcp Python package. Needs 1 environment variable to run.
pixabay-mcp-server
Unofficial MCP server for the Pixabay API: search and fetch royalty-free images and videos. Runs locally from the @hanoak/pixabay-mcp-server npm package. Needs 2 environment variables to run.
windows-system-sounds-mcp
MCP server "windows-system-sounds-mcp" as configured in vasjabrevno-dev/windows-system-sounds-mcp. Runs locally from the windows-system-sounds-mcp Python package.
mcp-ssh-reloaded
MCP server for SSH sessions management. Runs locally from the mcp-ssh-reloaded Python package.
mcp-shellcheck
ShellCheck MCP Server for AI code analysis. Runs locally from the mcp-shellcheck Python package.