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/ulises-jeremias/agent-toolkit/agent-toolkit-core-githubgit clone --depth 1 https://github.com/ulises-jeremias/agent-toolkitWrote 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/ulises-jeremias/agent-toolkit/agent-toolkit-core-github)<a href="https://agentmods.dev/mcp/ulises-jeremias/agent-toolkit/agent-toolkit-core-github"><img src="https://agentmods.dev/badge/mcp/ulises-jeremias/agent-toolkit/agent-toolkit-core-github.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
github 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 yesterday.
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
{
"github": {
"command": "ghcr.io/github/github-mcp-server",
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "${GITHUB_PERSONAL_ACCESS_TOKEN}"
}
}
}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.
- yesterday First seen · 8 lines scan A bacceda5f0c8
github is an MCP server published in the GitHub repository ulises-jeremias/agent-toolkit (16 stars, last pushed yesterday), 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 2026-09-04.
Other mcp servers, from other repositories
astravue
MCP server "astravue", hosted remotely at api.astravue.com, as configured in AstravueOrg/astravue-mcp-server.
mcp-gsc
Google Search Console MCP for analytics, indexing, sitemaps, and SEO diagnostics. Runs locally from the @digestseo/mcp-gsc npm package.
wander-agent
AI travel agent MCP server - search flights, hotels, plan itineraries, optimize budgets. Import into Claude or any MCP-compatible AI. Runs locally from the wander-agent Python package.
local-mcp
Native macOS MCP server — 82 tools for Mail, Calendar, Teams, OneDrive and more. Runs locally from the local-mcp npm package.
tg-mcp
Local MCP server for your Telegram personal account — channels, digests, messaging, folders and more. Runs locally from the tg-mcp npm package.
interactive-terminal
MCP server for real interactive terminal sessions — REPLs, SSH, databases, Docker. Runs locally from the mcp-interactive-terminal npm package. Needs 3 environment variables to run.