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/alanbuxton/auto-mcp-server/my-projectgit clone --depth 1 https://github.com/alanbuxton/auto-mcp-serverWrote 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/alanbuxton/auto-mcp-server/my-project)<a href="https://agentmods.dev/mcp/alanbuxton/auto-mcp-server/my-project"><img src="https://agentmods.dev/badge/mcp/alanbuxton/auto-mcp-server/my-project.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
my-project 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 4d 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
{ "my-project": { "command": "uvx", "args": [ "my-project" ] } }
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.
- 4d ago First seen · 8 lines scan A 055c7cf57d0b
my-project is an MCP server published in the GitHub repository alanbuxton/auto-mcp-server (0 stars, last pushed 2mo 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
planday
MCP server "planday" as configured in MVPR-Ext-Projects/planday-bridge. Launched with pnpm tsx apps/mcp/index.ts. Needs 2 environment variables to run.
validate
Deterministic validation for AI-generated artifacts: JSON Schema, OpenAPI response, SQL syntax. Runs locally from the @machinegrade/validate npm package. Needs 2 environment variables to run.
securellm
MCP server "securellm" as configured in VoidNxSEC/securellm-mcp. Runs ${SECURELLM_MCP_BUILD:-build/src/index.js} with node. Needs 2 environment variables to run.
yamcp
MCP server "yamcp" as configured in adamgalmor/yamcp. Runs locally from the @adamgalmor/yamcp npm package.
openapi-mcp-server
A Model Context Protocol (MCP) server that exposes OpenAPI endpoints as MCP tools. Runs locally from the @lucid-spark/openapi-mcp-server npm package.
brewpage-mcp
Publish HTML, Markdown, KV, JSON, and files to brewpage.app from AI assistants. No signup. Runs locally from the brewpage-mcp npm package. Needs 1 environment variable to run.