Back to blog
Guide
Apr 4, 20264 min read

Connect Claude Desktop to your documents in minutes

A quick setup guide for turning a knowledge base into an MCP server that Claude can query with page-level citations.

By 3meel.ai team
MCP
Claude Desktop

The fastest path to value with 3meel.ai is simple: upload a PDF, generate an API key, paste one config block into Claude Desktop, and start asking questions.

What you need

  • A 3meel.ai account with at least one knowledge base
  • A PDF uploaded and fully indexed
  • An API key from the dashboard
  • Claude Desktop installed locally

The workflow

  • Create a knowledge base for the document set you want Claude to search.
  • Upload your PDFs and wait for indexing to finish so citations can resolve back to real pages.
  • Open the MCP configuration page in 3meel.ai and copy the Claude Desktop config block for your API key.
  • Paste the config into Claude Desktop, restart the app if needed, and confirm the tools appear.
  • Ask a targeted question like 'What are the payment terms?' and verify that the answer links back to the right pages.

Why this setup works well

  • There is no custom integration code to maintain.
  • Claude can query the same knowledge base your team sees in the dashboard.
  • Every answer can point back to document pages instead of vague chunks.

If you are evaluating the product, this is the setup path to optimize. It gets users from sign-up to a working assistant experience with almost no friction.

More from the blog

Apr 2, 2026
Announcement
Accounts, API keys, and billing are live

Pricing, authentication, usage controls, and key management now live under the same Blog section as product releases, but tracked as announcements instead of release notes.

Mar 28, 2026
Release
3meel.ai v1.0: document brains for MCP clients

The first platform release focuses on document upload, tree indexing, MCP tools, dashboard workflows, citations, and the core infrastructure behind them.

Mar 18, 2026
Engineering
We never used vector embeddings. Here's why.

For our target use case, a tree-structured index gives better transparency, simpler operations, and cleaner citations than a traditional vector database stack.