pickfit

BrowseMCP servers

MCP Document Reader

MCP server that lets AI assistants read DOCX, PDF, Excel, and TXT files.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: python>=3.10
  1. install via uv tool

    uv tool install mcp-documents-reader
  2. pin mcp v1 for FastMCP compatibility

    uv pip install --python "$HOME"/.local/share/uv/tools/mcp-documents-reader/bin/python "mcp<2"
Where the README and reality differ
  • README: pip install mcp-documents-reader / uvx mcp-documents-reader works
    What worked: pin mcp<2 in the tool env (uv pip install --python ~/.local/share/uv/tools/mcp-documents-reader/bin/python 'mcp<2' giving mcp 1.30.0) before launching
Verified in pickfit: the commands exactly as its sandbox ran them

For the record only: they name the sandbox's home, /home/sbx.

uv tool install mcp-documents-reader 2>&1
uv pip install --python /home/sbx/.local/share/uv/tools/mcp-documents-reader/bin/python "mcp<2" 2>&1

Add it to your agent

claude mcp add mcp-documents-reader -- mcp-documents-reader
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "mcp-documents-reader": {
      "command": "mcp-documents-reader",
      "args": []
    }
  }
}

Add mcp-documents-reader as an MCP server in your AI assistant's settings, then ask the assistant to read a document by its file path.

What it does

  • Get sheet and cell data from Excel files
    How to use it
    1. Connect mcp-documents-reader to your MCP client.
    2. Ask the assistant to call read_document with filename set to <path to .xlsx file>.
    3. Read the sheet and cell text it returns.
    Tested
  • Get text and structure from DOCX files
    How to use it
    1. Connect mcp-documents-reader to your MCP client.
    2. Ask the assistant to call read_document with filename set to <path to .docx file>.
    3. Read the headings and paragraphs it returns as text.
    Tested
  • Read any supported document with one tool
    How to use it
    1. Connect mcp-documents-reader to your MCP client.
    2. Call read_document with filename set to <path to your file>, for example a PDF.
    3. The tool returns the document's text, whatever the file type.
    Tested
  • Read DOCX, PDF, Excel and TXT documents
    Not shown working

How far pickfit got

Linux x86_64

  1. Installs
  2. Connects
  3. 3 of 4 features work
  4. Works offline

Good for

  • read a DOCX file
  • read a PDF file
  • read an Excel file
  • read a text file

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

An MCP client called one of its tools

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 1.3.1

An MCP client handshake over stdio listed 1 tool, and a call to read_document returned a result.

Differences the test machine hit

  • README: README config uses uvx mcp-documents-reader
    In the test: launch via installed binary mcp-documents-reader instead of uvx so replay works with network off

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.