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/lightwheel10/mdapi-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/lightwheel10/mdapi-mcp/mdapi)<a href="https://agentmods.dev/mcp/lightwheel10/mdapi-mcp/mdapi"><img src="https://agentmods.dev/badge/mcp/lightwheel10/mdapi-mcp/mdapi/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/lightwheel10/mdapi-mcp/mdapi"><img src="https://agentmods.dev/badge/mcp/lightwheel10/mdapi-mcp/mdapi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mdapi 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
{
"mdapi": {
"url": "https://md.fastdb.in/mcp",
"type": "streamable-http"
}
}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 · 6 lines scan A 6255d75c3b49
mdapi is an MCP server published in the GitHub repository lightwheel10/mdapi-mcp (0 stars, last pushed 3mo 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
web-scraper
Extract clean markdown from any URL. Removes boilerplate. For RAG pipelines. x402. Remote server at web-scraper.api.klymax402.com.
anybrowse
Converts any URL to clean, LLM-ready Markdown using real Chrome browsers. Remote server at anybrowse.dev.
tokensqueezer
LangChain.js client for the TokenSqueezer x402 LLM token compression API. Runs locally from the @nodeproxy/tokensqueezer npm package.
vectorcache
LangChain.js client for the VectorCache x402 semantic vector cache API. Runs locally from the @nodeproxy/vectorcache npm package.
nodeproxy
Python clients for NodeProxy, TokenSqueezer, and VectorCache x402 agent APIs. Runs locally from the nodeproxy-tools Python package.
blockrun-mcp
Live data for AI agents: search, research, markets, crypto, X/Twitter. Pay per call. Runs locally from the @blockrun/mcp npm package. Needs 1 environment variable to run.