FAQai MCP server
app.faqai/mcp-server·v0.5.1Turn any document into a production-ready RAG dataset from Claude, Cursor, or any MCP host.
24 downloads/wk
Reviews
Write oneNobody has reviewed FAQai yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
FAQai tools (18, 6 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
cancel_processingwrite actionCancel a document that is currently processing. Reserved page quota is released
create_webhookwrite actionCreate a webhook subscription (Pro plan only, max 5 active). FAQai will POST
delete_documentwrite actionPERMANENTLY delete a FAQai document and all its generated datasets. This cannot
delete_webhookwrite actionDelete a webhook subscription (Pro plan only). The endpoint stops receiving
export_datasetExport a dataset in one of 16 formats (json, csv, markdown, jsonl, rag_chunks,
get_dataset_coverageReport how much of the source document a dataset covers: total chunks, chunks
get_documentGet full details for one FAQai document: status, processing phase, page count,
get_processing_statusCheck whether a document has finished processing. Returns a concise status
get_rag_configGet the recommended RAG configuration FAQai generated for a document: a tuned
get_usage_statsGet the user's current FAQai plan, billing period, page quota (used / remaining
ingest_urlwrite actionCreate a FAQai document from a public web page or website, then generate RAG
list_datasetsList the datasets generated for a document: canonical Q&A, query variants,
list_documentsList the user's FAQai documents, newest first. Optionally filter by status
list_export_formatsList the 16 dataset export formats FAQai supports, grouped by category:
list_webhooksList the user's webhook subscriptions (Pro plan only): URL, subscribed events,
process_documentStart dataset generation for an uploaded document that is not yet processed
search_datasetsFull-text search across all of the user's generated dataset items (questions and
upload_documentwrite actionUpload a local document (PDF, DOCX, TXT, or MD) to FAQai and optionally start
Public scan report
scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it
- Code scan31 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancerepository not readable: repo not found3/15
- Maintainer identityverified namespace with website, no repo4/10
How FAQai compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 58/100
- higher than 15% of 4,460 AI and agents servers
- Tools
- 18
- the typical AI and agents server has 6
- Tools that change things
- 33%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 24
- more than 10% of 1,538 AI and agents servers with a package
What its tools let an agent do: 12 read · 2 create · 1 change · 3 delete
Install FAQai in Claude Code, Cursor or VS Code
Runs npx -y @faqai/mcp-server on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add mcp-server -- npx -y @faqai/mcp-server
FAQai: common questions
- Is FAQai MCP server safe?
- With care: it is graded C, so read the findings first (58/100). Read the FAQai safety report
- How do I install FAQai?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does FAQai need an API key?
- Yes. The registry entry asks for
FAQAI_API_KEY. - Is FAQai maintained?
- The latest release is v0.5.1.
- What can I use instead of FAQai?
- Servers from other publishers that do the same job: Local Rag MCP server, Butterbase AI MCP server and DCC-MCP Core MCP server.
- How does FAQai compare with other AI and agents MCP servers?
- safety score 58/100 (higher than 15% of 4,460 AI and agents servers); tools 18 (the typical AI and agents server has 6); tools that change things 33% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to FAQai
Same job from other publishers: the closest match first, then the best rated.
- Local RagEasy-to-setup local RAG server with minimal configurationnot reviewedEstablishedA
- Butterbase AIButterbase MCP server — manage your backend: schemas, auth, functions, storage, RAG, deploys.not reviewedEstablishedA
- DCC-MCP CoreAgent control plane for DCC and engine hosts: one MCP endpoint, one tool contract.not reviewedEstablishedA
GuaardvarkLocal AI studio on your GPU: images, video, music, voice, RAG. Needs the Guaardvark app installed.not reviewedEstablishedB- PDFAgentic RAG over one PDF or a whole folder: hybrid search, selective page reads, tables, OCR.not reviewedEstablishedA