Servers Playground How we check Add a server Log in

Doc Convert Mcp

Working · 1.1 s

io.github.Anon2052/doc-convert-mcpv4.0.5

Document conversion MCP server: PDF to Markdown, image OCR, spreadsheet parsing.

Utilities Productivity

Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://doc-convert-mcp.onrender.com/mcp/

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

ocr_image Read-only

Run OCR on an image (base64-encoded bytes) and return recognized text.

image_base64string, required

The image file contents, base64-encoded.

langstring

Tesseract language code (default 'eng').

Tools (4)

ocr_image

Run OCR on an image (base64-encoded bytes) and return recognized text.

read-only

Doc Convert Mcp MCP server | mcptry

Argument	Type	Description
lang	string	Tesseract language code (default 'eng').
image_base64*	string	The image file contents, base64-encoded.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "image_base64"
  ],
  "properties": {
    "lang": {
      "type": "string",
      "default": "eng",
      "description": "Tesseract language code (default 'eng')."
    },
    "image_base64": {
      "type": "string",
      "description": "The image file contents, base64-encoded."
    }
  },
  "additionalProperties": false
}

parse_spreadsheet

Parse a CSV or XLSX file (base64-encoded bytes) into Markdown tables.

read-only

Argument	Type	Description
filename*	string	Original filename (used to detect .csv vs .xlsx).
file_base64*	string	The spreadsheet file contents, base64-encoded.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "file_base64",
    "filename"
  ],
  "properties": {
    "filename": {
      "type": "string",
      "description": "Original filename (used to detect .csv vs .xlsx)."
    },
    "file_base64": {
      "type": "string",
      "description": "The spreadsheet file contents, base64-encoded."
    }
  },
  "additionalProperties": false
}

pdf_to_markdown

Convert a PDF (base64-encoded bytes) to Markdown, one section per page.

read-only

Argument	Type	Description
max_pages	integer	Maximum pages to extract (default 100).
pdf_base64*	string	The PDF file contents, base64-encoded.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "pdf_base64"
  ],
  "properties": {
    "max_pages": {
      "type": "integer",
      "default": 100,
      "description": "Maximum pages to extract (default 100)."
    },
    "pdf_base64": {
      "type": "string",
      "description": "The PDF file contents, base64-encoded."
    }
  },
  "additionalProperties": false
}

url_to_clean_text

Fetch a public http(s) URL and return its main text content as plain text.

read-only

Argument	Type	Description
url*	string	The http(s) URL to fetch. Private/loopback hosts are rejected.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "The http(s) URL to fetch. Private/loopback hosts are rejected."
    }
  },
  "additionalProperties": false
}