rag-rat runs on your own machine — the client starts it, so there is no endpoint to ping. 516 installs a week from npm. Last commit 17 Sep 2026.
Repository intelligence, code graph, history, papertrail, and cross-agent memory for coding agents.
We read the source, 20 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
postinstall: node ./install.js
этот файл ставится пользователю, но в репозитории его нет
SELECT path, COUNT(*) AS commits,
SUM(COALESCE(additions, 0) + COALESCE(deletions, 0)) AS lines
const r = spawnSync(p, ["--version"], { encoding: "utf8" });
return subprocess.run(["bash", str(SCRIPT)], env=dict(self.env, **env), capture_output=True, text=True, timeout=10)
USER root
self.env = dict(os.environ, CARGO_TARGET_DIR=str(self.target), CARGO_HOME=str(self.root))
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add rag-rat -- npx -y @rag-rat/bin
{
"mcpServers": {
"rag-rat": {
"args": [
"-y",
"@rag-rat/bin"
],
"command": "npx"
}
}
}
[mcp_servers.rag-rat]
command = "npx"
args = ["-y", "@rag-rat/bin"]
{
"mcpServers": {
"rag-rat": {
"args": [
"-y",
"@rag-rat/bin"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"rag-rat": {
"args": [
"-y",
"@rag-rat/bin"
],
"command": "npx"
}
}
}
Cross-repository semantic code intelligence for AI coding agents, from a local code graph.
Codebase intelligence for AI coding agents — graph, git history, docs, decisions, code health.
PageRank-curated code intelligence for coding agents over an indexed source repository.
Codebase intelligence MCP — index any repo into a property graph; 26 tools for agents.
A graph-native code repository for people and AI agents.
Code Intelligence Platform for AI Coding Agents
Local code-memory graph for AI coding agents.
Intelligent code knowledge graph for AI coding agents — 71% cheaper, 72% faster
Answers built from our own checks of this server.