FastOCR MCP Server

by fastocr-org Your server? Claim it

local only

FastOCR runs on your own machine — the client starts it, so there is no endpoint to ping. 215 installs a week from pypi. Last commit 25 Oct 2026.

OCR scanned PDFs and images into text or searchable PDFs with the FastOCR API.

Installs per day peak 215 · avg 7

a month agotoday

215

Installs / week

pypi · fastocr-mcp

Stars

0 open issues

25 Oct 2026

Last commit

from GitHub

MIT

License

Python

Nothing serious here today

Today is the operative word: we check FastOCR every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add fastocr-mcp -e 'FASTOCR_API_KEY=<FASTOCR_API_KEY>' -- uvx fastocr-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "fastocr-mcp": {
      "command": "uvx",
      "args": [
        "fastocr-mcp"
      ],
      "env": {
        "FASTOCR_API_KEY": "<FASTOCR_API_KEY>"
      }
    }
  }
}

~/.codex/config.toml

[mcp_servers.fastocr-mcp]
command = "uvx"
args = ["fastocr-mcp"]
env = { FASTOCR_API_KEY = "<FASTOCR_API_KEY>" }

.cursor/mcp.json

{
  "mcpServers": {
    "fastocr-mcp": {
      "command": "uvx",
      "args": [
        "fastocr-mcp"
      ],
      "env": {
        "FASTOCR_API_KEY": "<FASTOCR_API_KEY>"
      }
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "fastocr-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "fastocr-mcp"
      ],
      "env": {
        "FASTOCR_API_KEY": "<FASTOCR_API_KEY>"
      }
    }
  }
}

Put your own value in place of <FASTOCR_API_KEY> (FastOCR API key from https://fastocr.org/developers/keys). The author’s registry entry marks it as required.

Alternatives to FastOCR

same job, measured the same way

PDF to Text & Markdown with OCR

by monietools

PDF, DOCX and image URLs to clean, LLM-ready Markdown or text, with OCR for scanned pages.

answering

PDF Text Extractor

by fernandoguiraud16-coder

Extract text, pages and metadata from PDFs in bulk, with OCR for scanned files.

answering

Image OCR Extractor (Apify Actor)

by truhojunbot-tech

OCR text from images and scanned PDFs; pay-per-event via your Apify account.

answering

Ocrspace

by pipeworx-io

OCR.space MCP — wraps the OCR.space API (ocr.space) for image/PDF → text OCR.

42 tools answering

Parseflow

by libres-coder

PDF parsing server with text extraction, metadata, search, images, and TOC via MCP

21 installs/wk local only

Bulk OCR: Image & Scanned PDF to Text from CSV or Google Sheet

by nero-engine

OCR every image and scanned PDF linked in an Apify dataset, CSV, Excel or Google Sheet, keeping...

answering

PDF Text, Table and OCR Extractor

by bkeller-research

PDF URLs to per-page text, tables as rows, Markdown, metadata and OCR for scanned pages.

answering

PDF Text, Table and OCR Extractor

by brenton-keller

PDF URLs to per-page text, tables as rows, Markdown, metadata and OCR for scanned pages.

answering

FastOCR — questions

Answers built from our own checks of this server.

Why is there no uptime for FastOCR?

FastOCR runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package fastocr-mcp was installed 215 times last week.

How do I connect FastOCR?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls fastocr-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use FastOCR?

The pypi package fastocr-mcp was installed 215 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is FastOCR open source?

Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.