Ref MCP is a Model Context Protocol server that lets coding agents search and read documentation for APIs, services, and libraries. It helps agents find the specific reference material they need while using less context. Catalogue add-ons operate the server as part of coding-agent documentation workflows.
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/ref-tools/ref-tools-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/ref-tools/ref-tools-mcp/ref-tools-ref-tools-mcp)<a href="https://agentmods.dev/mcp/ref-tools/ref-tools-mcp/ref-tools-ref-tools-mcp"><img src="https://agentmods.dev/badge/mcp/ref-tools/ref-tools-mcp/ref-tools-ref-tools-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/ref-tools/ref-tools-mcp/ref-tools-ref-tools-mcp"><img src="https://agentmods.dev/badge/mcp/ref-tools/ref-tools-mcp/ref-tools-ref-tools-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ref-tools-ref-tools-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 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
{
"ref-tools-ref-tools-mcp": {
"url": "https://server.smithery.ai/@ref-tools/ref-tools-mcp/mcp",
"type": "streamable-http"
}
}What else server.json configures
This page is one entry in a file that holds 2. Installing the file brings all of them; each is measured and scanned on its own page.
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 500ce4181d27
ref-tools-ref-tools-mcp is an MCP server published in the GitHub repository ref-tools/ref-tools-mcp (1,182 stars, last pushed 16d 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 2026-08-30.
Other mcp servers, from other repositories
pilink-local
MCP server "pilink-local", hosted remotely at 127.0.0.1, as configured in roccoangelella/PiLink.
intent-gate
MCP server "intent-gate" as configured in baixinghao/intent-gate. Launched with intent-gate. Needs 1 environment variable to run.
opencode-export
MCP server "opencode-export" as configured in ZelinZhou-THU/opencode-export. Runs locally from the opencode-export Python package.
mcp-fileencoding
MCP server "mcp-fileencoding" as configured in jidzhang/mcp-fileencoding. Runs locally from the mcp-fileencoding Python package.
sn-api-helper-mcp
MCP server for SignNow API helper tools (stdio only). Runs locally from the sn-api-helper-mcp Python package.
coding-mcp
Production-ready multi-project MCP server for coding agents. Runs locally from the @kieutrongthien/coding-mcp npm package.