FAQai runs on your own machine — the client starts it, so there is no endpoint to ping. 286 installs a week from npm.
Turn any document into a production-ready RAG dataset from Claude, Cursor, or any MCP host.
The linked repository no longer exists on GitHub — it was deleted or made private.
This one has been quiet for a while
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
Connect this server
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 mcp-server -e 'FAQAI_API_KEY=<FAQAI_API_KEY>' -- npx -y @faqai/mcp-server{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@faqai/mcp-server"
],
"env": {
"FAQAI_API_KEY": "<FAQAI_API_KEY>"
}
}
}
}[mcp_servers.mcp-server]
command = "npx"
args = ["-y", "@faqai/mcp-server"]
env = { FAQAI_API_KEY = "<FAQAI_API_KEY>" }{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@faqai/mcp-server"
],
"env": {
"FAQAI_API_KEY": "<FAQAI_API_KEY>"
}
}
}
}{
"servers": {
"mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@faqai/mcp-server"
],
"env": {
"FAQAI_API_KEY": "<FAQAI_API_KEY>"
}
}
}
}Put your own value in place of
<FAQAI_API_KEY> (FAQai API key (requires a paid plan). Create one at https://faqai.app/settings/api-keys).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
FAQAI_BASE_URL (Override the FAQai API base URL (defaults to https://faqai.app). Rarely needed).
Alternatives to FAQai
same job, measured the same wayMCP server: convert PNG/JPG to SVG from Claude, Cursor & any MCP client. By Pic2Vector.
Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
Turn documents into structured, AI-ready data by parsing, enriching, chunking, and embedding.
Local RAG MCP for markdown documentation. Retrieval only; host synthesizes answers.
Crawl any documentation site and return heading-bounded, LLM-ready chunks with source metadata.
Production-ready RAG + MCP demo: eval-in-CI merge gate, Langfuse traces, structure-aware chunking.
Ingest, manage, and retrieve documents for RAG-powered AI applications
Classify documents, extract structured fields, mask PII, export JSONL/RAG datasets for AI agents.
FAQai — questions
Answers built from our own checks of this server.