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/mrrlin-dev/external-agentsWrote 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/mrrlin-dev/external-agents/external-agents)<a href="https://agentmods.dev/mcp/mrrlin-dev/external-agents/external-agents"><img src="https://agentmods.dev/badge/mcp/mrrlin-dev/external-agents/external-agents/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/mrrlin-dev/external-agents/external-agents"><img src="https://agentmods.dev/badge/mcp/mrrlin-dev/external-agents/external-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
external-agents 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
{
"external-agents": {
"command": "npx",
"args": [
"-y",
"@mrrlin-dev/external-agents"
],
"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.
- 1mo ago First seen · 10 lines scan A 4d0bd6124c2b
external-agents is an MCP server published in the GitHub repository mrrlin-dev/external-agents (0 stars, last pushed 6d 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
vox-mcp
Multi-model AI gateway for MCP clients — routes prompts to Gemini, OpenAI, Anthropic, xAI, DeepSeek, Moonshot, OpenRouter, Cloudflare AI Gateway, Vercel AI Gateway, and local models with conversation memory. Runs locally from the vox-mcp Python package. Needs 19 environment variables to run.
brainstorm-mcp
Multi-model AI brainstorming debates with code review and quick perspectives. Runs locally from the brainstorm-mcp npm package. Needs 3 environment variables to run.
deepsee-mcp
MCP server "deepsee-mcp" as configured in rikfish163-rgb/deepsee. Runs locally from the deepsee-mcp Python package.
scrapebadger
MCP server for ScrapeBadger - Twitter/X scraping API for AI agents. Runs locally from the scrapebadger-mcp Python package. Needs 1 environment variable to run.
forge-think
MCP server "forge-think" as configured in halflifezyf2680/forge-think. Runs /absolute/path/to/forge-think/server.py with python.
deepseek-delegate-mcp
MCP server "deepseek-delegate-mcp" as configured in trixmix821/deepseek-delegate-mcp. Runs locally from the deepseek-delegate-mcp npm package.