Skip to content
Agentmart
Submit a tool

Docs MCP

Vector RAG store for Word/Excel/PDF/PowerPoint.

Connector by Shreyas-Profile · GitHub account verified by the MCP Registry

IndexedMITRemote (HTTP)
Write a review

Chalk Labs

Need help deploying Docs MCP?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, VS Code, Cursor, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install connector/shreyas-profile-docs-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Remote endpoint

  • https://docs.regiq.in/api/mcp Remote (HTTP)

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Vector RAG store for Word/Excel/PDF/PowerPoint. Break-even pricing, $5 per 5,700 pages.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
4 read · 1 write · 1 delete
Secrets
1 (API keys, tokens or passwords)
Install scripts
Nothing to install (hosted)
Runs as
Hosted (remote endpoint)

Tools by what they do 6

Read from the source code; the running server may list different tools.

Read 4 · Look things up without changing anything.

  • docs_balance
  • docs_get
  • docs_list
  • docs_search

Write 1 · Create, change, send or run things.

  • docs_upload

Delete 1 · Delete, drop, revoke or wipe things.

  • docs_delete

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • Authorization

Network hosts it talks to 1

  • docs.regiq.in · found in remote endpoint, install command

Files it touches

  • Any path the agent passes to its tools

Tools (6)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • docs_balance

    Return the caller's current credit balance and a summary of the last 10 credit transactions. Use this to check whether the user needs to top up before a large upload.

  • docs_delete

    Permanently delete a document. Removes the DB row, all embedded chunks, and the raw file on disk. Spent credits are NOT refunded — if you want to keep the vectors around, don't delete.

  • docs_get

    Fetch one document's metadata: id, filename, mimeType, status ('pending'|'processing'|'ready'|'failed'), pageCount, chunkCount, creditsSpent, errorMsg (if failed). Poll this after docs_upload until status='ready' before calling docs_search.

  • docs_list

    List all documents owned by the calling API key. Returns id, filename, mimeType, status, pageCount, creditsSpent, createdAt. Cheap — no chunk content, no vectors.

  • docs_search

    Semantic search across the caller's documents. Returns the top-k most-relevant chunks with { chunkId, documentId, filename, pageNumber, content, similarity (0..1) }. Free — queries cost no credits. Restrict to specific docs via documentIds. Chain: (1) run docs_search, (2) synthesize an answer from the returned chunks in your own LLM, (3) show the user the answer plus the page-number citations we returned. We deliberately don't synthesize — you bring the model.

  • docs_upload

    Upload a document (PDF / .docx / .xlsx / .pptx / .doc / .xls / .ppt) as base64 bytes. Costs 1 credit per page. Returns the docId immediately; ingest runs async — poll docs_get({id}) until status='ready' (usually 10-60s for a 10-page doc). Max ~10 MB base64 encoded (~7 MB raw). For bigger files, upload via the web dashboard at https://docs.regiq.in/dashboard.

Signals

Stars
0
Forks
0
Open issues
0
Last commit
Jul 17, 2026 (3 months ago)
Last release
Jul 17, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.Shreyas-Profile/docs-mcp
Version
0.1.0
Auth
Bearer token
License
MIT
Repository
github.com/globalion/docs-mcp
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql

More from Shreyas-Profile

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get Docs MCP running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying Docs MCP?

CallGet help
Cite this page

Docs MCP. Agent Mart. https://agentmart.dev/connectors/shreyas-profile-docs-mcp (last updated 2026-10-24)