docs MCP server
Commit Oct 24, 2026Converts Word, Excel, PDF, and PowerPoint files into a vector RAG store with vision-based extraction for precise semantic search.
Also known as globalion/docs-mcp
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.1.0
- Last commit
- Oct 24, 2026
- License
- MIT
What is docs MCP?
docs converts Word, Excel, PDF, and PowerPoint files into a vector RAG store with vision-based extraction for precise semantic search.
Summary generated from the project's README
About docs MCP server
Converting complex documents like Word, Excel, PDF, and PowerPoint files into a searchable vector RAG store is the primary function of docs-mcp. It uses vision-based extraction via Google Gemini 2.5 Flash Lite to process scans, charts, and tables, ensuring that even visual data is captured verbatim. This allows developers to perform precise semantic searches where every returned text chunk includes a specific page number for accurate citations.
Users connect to the service using an API key from a dashboard and configure it in MCP clients like Claude Desktop, Cursor, or Zed via a streamable-http connection. The system handles files up to 50 MB and manages ingestion, storage in Postgres with pgvector, and retrieval. While small files can be uploaded programmatically using the docs_upload tool, larger files are managed through a web dashboard. The service operates on a credit system where one credit equals one ingested page, and semantic queries via docs_search are free.
What you can do with it
- 1Extracting data from scanned documentsAsk the AI to find specific information within scanned PDFs or images of charts and tables.
- 2Performing semantic searches with citationsSearch through a large collection of uploaded documents to find relevant text chunks and their exact page numbers.
- 3Automating document ingestion workflowsProgrammatically upload small files to a vector store for asynchronous processing and retrieval.
Written from the project's README. Every use case is checked against a quote from it.
How to install docs MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall docs MCP in Claude Code
$ claude mcp add --transport http docs-mcp https://docs.regiq.in/api/mcpInstall docs MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"docs-mcp": {
"url": "https://docs.regiq.in/api/mcp"
}
}
}Install docs MCP in VS Code
.vscode/mcp.json
{
"servers": {
"docs-mcp": {
"type": "http",
"url": "https://docs.regiq.in/api/mcp"
}
}
}Install docs MCP in VS Code CLI
$ code --add-mcp '{"name":"docs-mcp","type":"http","url":"https://docs.regiq.in/api/mcp"}'Install docs MCP in Codex
$ codex mcp add docs-mcp --url https://docs.regiq.in/api/mcpInstall docs MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.docs-mcp] url = "https://docs.regiq.in/api/mcp"
Install docs MCP in Gemini CLI
$ gemini mcp add -s user --transport http docs-mcp https://docs.regiq.in/api/mcpInstall docs MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"docs-mcp": {
"url": "https://docs.regiq.in/api/mcp",
"type": "http"
}
}
}Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableglobalion/docs-mcp is public and reachablegithub.com/globalion/docs-mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-24github.com/globalion/docs-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeEndpoint did not answer initialize: HTTP 404Finding
README
View on GitHubdocs-mcp
Drop any Word, Excel, PDF or PowerPoint into a vector RAG store. Vision-model extraction handles scans, charts, and tables. Every returned chunk carries its page number for precise citations. Priced at exact break-even via Stripe — we make $0 per credit sold.
Live: docs.regiq.in
What it does
- Ingest — accepts
.pdf,.docx,.xlsx,.pptx,.doc,.xls,.pptup to 50 MB. - Extract — renders every page as an image, runs Google Gemini 2.5 Flash Lite (via OpenRouter) over each page. Text, tables, and figure descriptions come out verbatim.
- Store — chunks (~500 tokens, 50-token overlap), embeds via
openai/text-embedding-3-small(1536 dims), stored in Postgres + pgvector with page-number metadata. - Retrieve — cosine-similarity search returns the top-k chunks; your agent synthesizes the answer.
Tools
| Tool | What it does |
|---|---|
docs_upload({filename, contentBase64, mimeType?}) |
Small (≤~7 MB) programmatic upload. Ingest runs async. |
docs_list() |
All documents owned by the calling key. |
docs_get({id}) |
One doc's metadata + status + chunk count. |
docs_search({query, k?, documentIds?}) |
Semantic search. Returns top-k chunks with page numbers. Free. |
docs_delete({id}) |
Permanent delete. |
docs_balance() |
Credit balance + last 10 transactions. |
Bigger files: upload via the web dashboard at docs.regiq.in/dashboard (max 50 MB).
Pricing
1 credit = 1 page ingested. Queries are free. New accounts get 100 pages free on sign-up.
| Top-up | Pages you get | ~Docs (10-pg avg) |
|---|---|---|
| $5 | 5,700 | 570 |
| $10 | 11,700 | 1,170 |
| $20 | 23,900 | 2,390 |
| $50 | 60,500 | 6,050 |
Per-page underlying cost is roughly $0.0005 vision + $0.00003 embedding via OpenRouter. Prices are set at exact break-even after Stripe's 2.9% + $0.30 fee — that flat fee is why $2 top-ups aren't offered (18% of $2 evaporates to Stripe).
Setup — any MCP client
- Sign in at docs.regiq.in with Google or GitHub.
- Copy your API key from
/dashboard. - Add to your client config:
{
"mcpServers": {
"docs": {
"url": "https://docs.regiq.in/api/mcp",
"headers": {
"Authorization": "Bearer docs_live_..."
}
}
}
}
Works in Claude Desktop, Cursor, Zed, and anything else that speaks streamable-http MCP.
Recommended flow
1. docs_upload({filename, contentBase64}) → { id, status: "processing" }
2. poll docs_get({id}) until status="ready" (~10-60s for 10 pages)
3. docs_search({query: "...", k: 8}) → chunks with page numbers
4. Your LLM synthesizes an answer and cites the page numbers.
Self-host
git clone https://github.com/globalion/docs-mcp
cd docs-mcp
cp .env.example .env # fill in Google OAuth + OpenRouter + (optional) Stripe
docker compose up -d --build
Uses pgvector/pgvector:pg16 image so the vector extension is pre-installed. docker exec docs-mcp-web npx prisma@6.19.2 db push --accept-data-loss --skip-generate on first boot to sync the schema (the container CMD does this automatically).
License
docs MCP questions
How do I add docs MCP to Claude Code?
Run claude mcp add --transport http docs-mcp https://docs.regiq.in/api/mcp in your terminal. Add --scope user to make it available in every project.
How do I add docs MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What file types are supported?
The server accepts .pdf, .docx, .xlsx, .pptx, .doc, .xls, and .ppt files up to 50 MB.
How much does it cost to search documents?
Semantic queries are free; you only pay for page ingestion.
Do I get any free credits?
Yes, new accounts receive 100 pages for free upon signing up.