Docalyze MCP Server

Read and analyze local documents (PDF, Excel, CSV, Word, PowerPoint, images). No API keys needed.

Local serverstdioPython

What is the Docalyze MCP server?

Read and analyze local documents (PDF, Excel, CSV, Word, PowerPoint, images). No API keys needed. The docalyze mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 4 defined tools rather than through you.

What it actually does

An MCP (Model Context Protocol) server that lets AI assistants read and visually analyze local documents — PDFs, Excel spreadsheets, CSV files, Word documents, PowerPoint presentations, and images.

Its toolset

Everything the assistant can do here goes through one of these:

  • list_documents — List files under a directory, filtered by glob pattern
  • document_info — Get metadata (size, modified date, sheets) for a file
  • read_document — Extract text content from a document with pagination
  • visual_evaluate_document — Return page images inline so the AI can analyze charts, tables, and diagrams

Adding it to your client

Installation goes through your MCP client rather than a global install: point it at docalyze-mcp-server on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

Configuration

You will need 2 environment variables: PYTHONIOENCODING, DOCUMENTS_ROOT. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

When to reach for it

Plenty of file and storage access servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Docalyze's toolset — list_documents, document_info, read_document and 1 more — is a fair guide to whether it matches your workflow. It is maintained by LunarPerovskite; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the docalyze mcp server does with a few real requests.

Available tools

ToolWhat it does
list_documentsList files under a directory, filtered by glob pattern
document_infoGet metadata (size, modified date, sheets) for a file
read_documentExtract text content from a document with pagination
visual_evaluate_documentReturn page images inline so the AI can analyze charts, tables, and diagrams

How to install the Docalyze MCP server

{
  "mcpServers": {
    "docalyze": {
      "command": "npx",
      "args": ["-y", "docalyze-mcp-server"],
      "env": {
        "PYTHONIOENCODING": "your-value",
        "DOCUMENTS_ROOT": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
PYTHONIOENCODINGConfiguration value read at startup.Optional
DOCUMENTS_ROOTConfiguration value read at startup.Optional

Example prompts to try

  • Use Docalyze to list documents.
  • Use Docalyze to document info.
  • Use Docalyze to read document.

Frequently asked questions

It connects Docalyze to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (list_documents, document_info, read_document, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Docalyze directly.