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.
npx agentmods add mcp/amr-dev-ps/numertel-mcp/numertelgit clone --depth 1 https://github.com/AMR-DEV-PS/numertel-mcpWrote 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/amr-dev-ps/numertel-mcp/numertel)<a href="https://agentmods.dev/mcp/amr-dev-ps/numertel-mcp/numertel"><img src="https://agentmods.dev/badge/mcp/amr-dev-ps/numertel-mcp/numertel.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
numertel 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 4d 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
{
"numertel": {
"url": "https://numertel.pl/api/mcp",
"type": "streamable-http"
}
}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.
- 4d ago First seen · 6 lines scan A 9bb838714c97
numertel is an MCP server published in the GitHub repository AMR-DEV-PS/numertel-mcp (1 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.
Other mcp servers, from other repositories
code-context-engine
Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Cursor, Codex, Copilot, Gemini CLI. Local MCP server, free, open source. Runs locally from the code-context-engine Python package.
easy-notion
Markdown-first Notion MCP server. 6-7x fewer response tokens vs official Notion MCP. 43 tools. Runs locally from the easy-notion-mcp npm package. Needs 2 environment variables to run.
pyobfus-mcp
Model Context Protocol server for pyobfus — the Python obfuscator. Lets Claude Desktop, Claude Code, Cursor, GitHub Copilot, Windsurf, Zed, Codex, and CodeBuddy call pyobfus tools (preflight risk check, zero-config init, reverse stack-trace mapping) directly from an agent conversation. PyArmor alternative with…
google-maps
Google Maps places, reviews, contributor history, photos and posts as JSON. No Google Cloud. Runs locally from the @hasdata/google-maps-mcp npm package. Needs 1 environment variable to run.
airbnb
Airbnb stays by location and dates, and full listing details, as structured JSON. Runs locally from the @hasdata/airbnb-mcp npm package. Needs 1 environment variable to run.
google-trends
Google Trends: Search, Images, News, Shopping over time, growth metrics. Free key at trendsmcp.ai. Remote server at google-trends.api.trendsmcp.ai.