# doc-convert-mcp [Verified owner] [Health: Active]

**Category:** 💻 Developer Tools  
**Repository:** https://ioconnex.dev  
**Views:** 4  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/doc-convert-mcp

## Description
Document conversion and OCR for AI agents: PDF, Office docs, images to text.

## Tools
Capabilities this server exposes over MCP:

- **pdf_to_markdown** — Convert a PDF (base64-encoded bytes) to Markdown, one section per page.
- **ocr_image** — Run OCR on an image (base64-encoded bytes) and return recognized text.
- **parse_spreadsheet** — Parse a CSV or XLSX file (base64-encoded bytes) into Markdown tables.
- **url_to_clean_text** — Fetch a public http(s) URL and return its main text content as plain text.

## Claude Desktop Quick Installation
No generated config for this server: it installs through its own setup steps.

The project's own setup steps (from https://ioconnex.dev), copied verbatim. Run them in order; they are not an mcpServers config.

1. Add to Claude Code:

```sh
claude mcp add --transport http ioconnex-convert https://convert.ioconnex.dev/mcp
```

2. Add to Claude Code:

```sh
claude mcp add --transport http ioconnex-prices https://prices.ioconnex.dev/mcp
```

## Documentation

## What doc-convert-mcp does

The doc-convert-mcp MCP server is intended for AI agents that need text from document files. Its stated scope covers conversion and OCR for three input categories: PDF files, Office documents, and images. The resulting text can be used by an agent for tasks that depend on document contents.

Those details should be confirmed from the project’s own documentation before implementation.

## How it works

An agent sends a supported document type to the doc-convert-mcp MCP server, which performs document conversion or optical character recognition and returns text. Conversion applies to PDFs and Office documents, while OCR is relevant to images and may also be used where a document requires text recognition.

It may fit document intake, extraction, or indexing steps, provided the required file types and transport are supported by the deployment.

## Tools and capabilities

- Converting PDF content to text
- Converting Office document content to text
- Applying OCR to images
- Providing document text for AI agent workflows

No tool identifiers, parameters, authentication requirements, maximum file sizes, language coverage, or output details are provided. Avoid depending on those characteristics without checking the source documentation.

## Setup and configuration

It also does not state whether the doc-convert-mcp MCP server runs over standard input/output, streamable HTTP, or another transport.

Client configuration, runtime prerequisites, dependency installation, and file-passing procedures therefore remain unspecified. Developers should consult the project source before adding this server to an agent configuration.

## Limitations and notes

The description establishes document conversion and OCR as the core scope, but it does not provide a complete compatibility matrix. In particular, supported Office formats, OCR languages, image formats, error behavior, and preservation of layout are unknown. The material also does not name any MCP clients or state whether processing is local or remote.

Use the doc-convert-mcp MCP server when its documented input and output behavior matches the workflow. Treat claims about specific file extensions, client compatibility, deployment models, or performance as unverified until confirmed by the project documentation.

_Full upstream README: https://allmcps.com/mcp/doc-convert-mcp/readme_