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/Paracci/aitreeWrote 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/paracci/aitree/paracci-aitree)<a href="https://agentmods.dev/mcp/paracci/aitree/paracci-aitree"><img src="https://agentmods.dev/badge/mcp/paracci/aitree/paracci-aitree/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/paracci/aitree/paracci-aitree"><img src="https://agentmods.dev/badge/mcp/paracci/aitree/paracci-aitree.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
paracci-aitree 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
{ "paracci-aitree": { "command": "uvx", "args": [ "paracci-aitree" ] } }
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 · 8 lines scan A ee82c4d1ac4e
paracci-aitree is an MCP server published in the GitHub repository Paracci/aitree (0 stars, last pushed 6mo 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-review-graph
MCP server "code-review-graph" as configured in mrwogu/promptscript. Launched with code-review-graph serve.
github
MCP server "github" as configured in crypto-ninja/mcp-server-for-Github. Runs github_mcp with python. Needs 1 environment variable to run.
github-mcp-server
The most AI-optimized GitHub MCP server: 112 tools, code-first architecture (98% token reduction), compact responses (80-97% smaller). Built for efficient AI development. Runs locally from the github-mcp-server Python package.
mcp-server-filesystem
Enhanced MCP Filesystem Server with 12 comprehensive tools: fixed glob pattern search, head+tail file reading, secure file operations, and command execution. Runs locally from the @redf0x1/mcp-server-filesystem npm package.
flashalpha
MCP server "flashalpha", hosted remotely at lab.flashalpha.com, as configured in FlashAlpha-lab/flashalpha-mcp.
pm-copilot
MCP server "pm-copilot" as configured in dkships/pm-copilot. Runs dist/index.js with node.