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/PyModel/claude-agy-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/pymodel/claude-agy-mcp/claude-agy-mcp)<a href="https://agentmods.dev/mcp/pymodel/claude-agy-mcp/claude-agy-mcp"><img src="https://agentmods.dev/badge/mcp/pymodel/claude-agy-mcp/claude-agy-mcp/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/pymodel/claude-agy-mcp/claude-agy-mcp"><img src="https://agentmods.dev/badge/mcp/pymodel/claude-agy-mcp/claude-agy-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
claude-agy-mcp 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
{
"claude-agy-mcp": {
"command": "npx",
"args": [
"-y",
"@pymodel/claude-agy-mcp"
],
"env": {
"AGY_PATH": "",
"AGY_TIMEOUT": "",
"AGY_MAX_RUNTIME": "",
"AGY_MAX_OUTPUT_CHARS": "",
"AGY_DEFAULT_MODEL": "",
"AGY_ON_FAILURE": ""
}
}
}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 · 17 lines scan A a40d2d156cee
claude-agy-mcp is an MCP server published in the GitHub repository PyModel/claude-agy-mcp (0 stars, last pushed 5d 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
mcp-server-google-antigravity
MCP server exposing Google Antigravity (agy CLI / Gemini): jobs, codebase analysis, file tools. Runs locally from the mcp-server-google-antigravity npm package.
code-review-graph
Local-first knowledge graph for token-efficient code review through MCP and CLI. Runs locally from the code-review-graph Python package.
agy-plugins
MCP server "agy-plugins" as configured in fledgeling-co/agy-plugins. Runs locally from the agy-plugins npm package.
antigravity
Use Google Antigravity (Gemini 3 Pro, Claude, GPT-OSS) as an independent second-opinion / code-review model inside Claude Code — via MCP, one command, zero dependencies. Runs locally from the antigravity-claude-mcp npm package. Needs 2 environment variables to run.
agy-mcp
MCP server for Antigravity CLI (agy) - one-shot execution with session persistence. Runs locally from the agy-mcp npm package.
docs-langchain
MCP server "docs-langchain", hosted remotely at docs.langchain.com, as configured in langchain-ai/langchain.