RAG for your documents runs on your own machine — the client starts it, so there is no endpoint to ping. 158 installs a week from npm. Last commit 7 Nov 2026.
Search a folder of documents and check answers against them. Offline: no API key or database.
We read the source, 22 h ago · rules 995398eba69f
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
? JSON.parse(fs.readFileSync(manifestPath, 'utf8'))
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
await fs.access(path.join("node_modules", depName));
`Failed to update permissions: ${chmodError.message}`,
execFile(
const result = await context.eval(wrapperCode, {
COPY .npmrc* ./
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
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-mcp-server -- npx -y @devilsdev/rag-mcp-server
{
"mcpServers": {
"rag-mcp-server": {
"command": "npx",
"args": [
"-y",
"@devilsdev/rag-mcp-server"
]
}
}
}
[mcp_servers.rag-mcp-server]
command = "npx"
args = ["-y", "@devilsdev/rag-mcp-server"]
{
"mcpServers": {
"rag-mcp-server": {
"command": "npx",
"args": [
"-y",
"@devilsdev/rag-mcp-server"
]
}
}
}
{
"servers": {
"rag-mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@devilsdev/rag-mcp-server"
]
}
}
}
The engine of your second brain: Markdown notes as database tables, for you and your agents.
Encrypted store for API keys and database URLs your code needs. Use them without reading them.
Database guardrails for AI agents: check SQL against your Vericto rules before it runs.
An app builder for agents. Your agent creates screens, a Postgres database, and a live URL.
Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
Search public documentary film reference pages and check which titles stream on GuideDoc.
Every Syncro PSA and RMM workflow in your terminal, plus a local database, offline search, and
Record a flow through your app, check it after every change, and attack a copy of your database.
Answers built from our own checks of this server.