MarkItDown Hosted Markdown Generator

Function

Available ActionsEach successful request consumes credits as outlined below.

convert^5cr

Details

Turn any file into clean, readable Markdown for Agentic workflows. Accepts, PDF, Word doc, Excel spreadsheet, PowerPoint, HTML page, image, or audio file and sends back structured Markdown text — ready for analysis, indexing, or feeding into your next workflow. Uses Microsoft's official MarkItDown package for premium results that AI Agents can parse and understand.

Use Cases

Convert PDF documents to Markdown, Extract text from Word documents, Convert Excel spreadsheets to readable Markdown, Parse PowerPoint presentations into text, Convert HTML pages to Markdown, Extract content from EPub files, Process ZIP archives of documents

Connect Your Agent In 5 Min

Watch the setup guide for your platform

Or Install Locally

STDIO connector for Claude Code, Codex, Cursor, Zed, and other LLMs that require STDIO or custom connections. This lightweight connector routes requests to https://api.agentpmt.com/mcp. All tool execution happens in the cloud and the server cannot edit any files on your computer.

npm install -g @agentpmt/mcp-routeragentpmt-setup

Actions(1)

convert^5cr4 params

Convert a file to Markdown. Provide the file using exactly one of: url, file_id, or file_base64. Supports PDF, Word, Excel, PowerPoint, HTML, CSV, JSON, XML, images, audio, EPub, and ZIP. Max 50MB.

urlstring

Public URL or signed storage URL of the file to convert

file_idstring

File ID from the file upload tool

file_base64string

Base64-encoded file content

filenamestring

Original filename with extension (helps detect format when using file_base64)

curl -X POST "https://api.agentpmt.com/products/purchase" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ********" \
  -d '{
    "product_id": "6991e8bbaa85db8efed135e4",
    "parameters": {
      "action": "convert"
    }
  }'

import requests
import json

url = "https://api.agentpmt.com/products/purchase"

headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer ********"
}

data = {
    "product_id": "6991e8bbaa85db8efed135e4",
    "parameters": {
        "action": "convert"
    }
}

response = requests.post(url, headers=headers, json=data)
print(response.status_code)
print(response.json())

const url = "https://api.agentpmt.com/products/purchase";

const headers = {
  "Content-Type": "application/json",
  "Authorization": "Bearer ********"
};

const data = {
  product_id: "6991e8bbaa85db8efed135e4",
  parameters: {
    "action": "convert"
  }
};

fetch(url, {
  method: "POST",
  headers,
  body: JSON.stringify(data)
})
  .then(response => response.json())
  .then(data => console.log(data))
  .catch(error => console.error("Error:", error));

const axios = require('axios');

const url = "https://api.agentpmt.com/products/purchase";

const headers = {
  "Content-Type": "application/json",
  "Authorization": "Bearer ********"
};

const data = {
  product_id: "6991e8bbaa85db8efed135e4",
  parameters: {
    "action": "convert"
  }
};

axios.post(url, data, { headers })
  .then(response => {
    console.log(response.status);
    console.log(response.data);
  })
  .catch(error => {
    console.error("Error:", error.message);
  });

Login to view your API and budget keys. The example above uses placeholder values. Sign in to see personalized code with your bearer token.

This tool supports credit-based access for external agents using AgentAddress identities or standard crypto wallets. External agents should use the External Agent API to buy credits with x402 and invoke this tool.

1. Buy Credits

Purchase credits via x402 payment (500 credit minimum, 100 credits = $1).

# Request payment requirements (returns 402 + PAYMENT-REQUIRED header)
curl -i -s -X POST "https://www.agentpmt.com/api/external/credits/purchase" \
  -H "Content-Type: application/json" \
  -d '{ "wallet_address":"0xYOUR_WALLET", "credits": 500, "payment_method":"x402" }'

# Sign the EIP-3009 authorization, then retry with signature header
curl -s -X POST "https://www.agentpmt.com/api/external/credits/purchase" \
  -H "Content-Type: application/json" \
  -H "PAYMENT-SIGNATURE: <base64-json>" \
  -d '{ "wallet_address":"0xYOUR_WALLET", "credits": 500, "payment_method":"x402" }'

2. Create a Session Nonce (nonce used in signed balance/invoke)

curl -s -X POST "https://www.agentpmt.com/api/external/auth/session" \
  -H "Content-Type: application/json" \
  -d '{ "wallet_address":"0xYOUR_WALLET" }'

3. Invoke This Tool

Sign the message with your wallet (EIP-191 personal-sign), then POST to the invoke endpoint.

# Sign this message (wallet MUST be lowercased):
# agentpmt-external
# wallet:0xyourwallet...
# session:<session_nonce>
# request:<request_id>
# method:POST
# path:/external/tools/markitdown/actions/<actionSlug>/invoke
# payload:<sha256(canonical_json(parameters))>

curl -s -X POST "https://www.agentpmt.com/api/external/tools/markitdown/actions/<actionSlug>/invoke" \
  -H "Content-Type: application/json" \
  -d '{
    "wallet_address": "0xYOUR_WALLET",
    "session_nonce": "<session_nonce>",
    "request_id": "invoke-uuid",
    "signature": "0x<signature>",
    "parameters": {
      "your_param": "value"
    }
  }'

Usage Instructions

Usage guidance provided directly by the developer for this product.

MarkItDown

Convert files and URLs to Markdown using Microsoft's MarkItDown library. Supports PDF, Word (.docx), Excel (.xlsx), PowerPoint (.pptx), HTML, CSV, JSON, XML, images (PNG, JPG), audio (MP3, WAV -- transcription), EPub, ZIP archives, and plain text. Maximum file size: 50 MB.

Actions

convert

Convert a file to Markdown. Provide the file using exactly ONE of three input methods.

Required Parameters (one of):

url (string) -- Public URL or signed storage URL of the file to convert. The tool follows redirects and detects file format from the URL path or Content-Type header.
file_id (string) -- File ID from the AgentPMT file upload tool. The tool retrieves the file from cloud storage and uses the stored original filename to detect format.
file_base64 (string) -- Base64-encoded file content for direct inline submission.

Optional Parameters:

filename (string) -- Original filename including extension (e.g., "report.pdf"). Helps detect the correct format when using file_base64. Also useful when the URL or file_id does not clearly indicate the file type.

Response Fields:

action (string) -- Always "convert"
source (string) -- Input method used: "url", "file_id", or "file_base64"
markdown (string) -- The converted Markdown text content
length (integer) -- Character count of the Markdown output

Example -- Convert from URL:

{
  "action": "convert",
  "url": "https://example.com/report.pdf"
}

Example -- Convert from file upload:

{
  "action": "convert",
  "file_id": "abc123-def456"
}

Example -- Convert from base64 with filename hint:

{
  "action": "convert",
  "file_base64": "JVBERi0xLjQK...",
  "filename": "quarterly_report.pdf"
}

Example Response:

{
  "action": "convert",
  "source": "url",
  "markdown": "# Report Title\n\nSection content here...",
  "length": 4521
}

Workflows

Document analysis pipeline -- Upload a file using the file upload tool, then pass the returned file_id to MarkItDown to convert it to Markdown for further processing or summarization by an AI agent.
Web page to Markdown -- Provide a public URL of an HTML page to extract its content as clean Markdown, useful for archiving or content repurposing.
Spreadsheet data extraction -- Convert Excel or CSV files to Markdown tables for readable display or further data analysis.
Presentation content extraction -- Convert PowerPoint files to Markdown to extract slide content, speaker notes, and structure for review or repurposing.
Archive inspection -- Convert a ZIP file to get a Markdown listing/extraction of its contents.

Notes

Exactly one input method must be provided per request (url, file_id, or file_base64). Providing none will result in a validation error.
The maximum file size is 50 MB regardless of input method. Files exceeding this limit are rejected.
When using file_base64, providing filename with the correct extension significantly improves format detection accuracy.
When using url, the tool auto-detects format from the URL file extension first, then falls back to the HTTP Content-Type header.
For file_id input, the file must not be deleted or expired, and must belong to the same budget context.
Audio files (MP3, WAV) are transcribed to text and returned as Markdown.
Image files are processed for any text content (OCR-style extraction via MarkItDown).
If format cannot be determined, the file is treated as a binary file with extension .bin.
The conversion runs asynchronously on the server; large files may take longer to process.

Dependencies

3 dependencies will be automatically added when you enable this product.

File Management