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/liortesta/ClawdAgentWrote 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/liortesta/clawdagent/filesystem)<a href="https://agentmods.dev/mcp/liortesta/clawdagent/filesystem"><img src="https://agentmods.dev/badge/mcp/liortesta/clawdagent/filesystem/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/liortesta/clawdagent/filesystem"><img src="https://agentmods.dev/badge/mcp/liortesta/clawdagent/filesystem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
filesystem 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 1mo 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
{
"filesystem": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-filesystem",
"/path/to/allowed/directory"
],
"env": {}
}
}What else .mcp.json configures
This page is one entry in a file that holds 9. Installing the file brings all of them; each is measured and scanned on its own page.
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.
- 1mo ago First seen · 11 lines scan A 7b221bed8569
filesystem is an MCP server published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 1mo 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 2026-09-03.
Other mcp servers, from other repositories
specpilot
Generate and validate a .specs/ bundle for your repo, then hand it to your AI coding agent. Remote server at init.specpilot.dev.
raycast
Raycast workflow automation MCP server with 9 tools. Runs locally from the raycast-mcp-server npm package.
habitica
MCP server "habitica" as configured in rodcordeiro/habitica-mcp. Runs ../../dist/index.js with node. Needs 3 environment variables to run.
pomodoro-ai-mcp
Pomodoro Ai MCP server. Tools: start session, stop session, get stats. Built by MEOK AI Labs. Runs locally from the pomodoro-ai-mcp Python package.
weekly-review-skill
MCP server "weekly-review-skill" as configured in testman2025/weekly-review-skill. Runs locally from the weekly-review-skill Python package.
calendly-mcp
MCP server connecting Claude Desktop/Code to Calendly for natural-language scheduling management. Runs locally from the calendly-mcp Python package.