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/MukundaKatta/agentfit-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/mukundakatta/agentfit-mcp/agentfit)<a href="https://agentmods.dev/mcp/mukundakatta/agentfit-mcp/agentfit"><img src="https://agentmods.dev/badge/mcp/mukundakatta/agentfit-mcp/agentfit/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/mukundakatta/agentfit-mcp/agentfit"><img src="https://agentmods.dev/badge/mcp/mukundakatta/agentfit-mcp/agentfit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agentfit 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 9d 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
{
"agentfit": {
"command": "npx",
"args": [
"-y",
"@mukundakatta/agentfit-mcp"
],
"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.
- 9d ago First seen · 10 lines scan A c3941af0d4e3
agentfit is an MCP server published in the GitHub repository MukundaKatta/agentfit-mcp (1 stars, last pushed 1mo 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
agentvet
Validate tool-call args before execution. Returns LLM-friendly retry hints. Runs locally from the @mukundakatta/agentvet-mcp npm package.
agentcast
Structured-output enforcer: extract and validate JSON from messy LLM text. Runs locally from the @mukundakatta/agentcast-mcp npm package.
agentguard
Network-egress firewall for agent tools: check URLs against a declarative policy. Runs locally from the @mukundakatta/agentguard-mcp npm package.
distil
Compression with a quality contract — cache-aware, causally-pruned context compression for agentic runtimes, gated by a statistical non-inferiority test. Runs locally from the distil-llm Python package.
agentsnap
Snapshot tests for AI tool-call traces: diff, validate, and catch silent regressions. Runs locally from the @mukundakatta/agentsnap-mcp npm package.
openaiDeveloperDocs
MCP server "openaiDeveloperDocs", hosted remotely at developers.openai.com, as configured in petekp/claude-code-setup.