File To JSON Parsing

Available ActionsEach successful request consumes credits as outlined below.

extract-csv^5crextract-html^5crextract-json^5crextract-ics^5crextract-ods^5crextract-pdf^5crextract-rtf^5crextract-text^5crextract-xls^5crextract-xlsx^5crfile-to-base64^5cr

Details

A powerful data extraction tool that converts a wide variety of binary file formats into structured JSON output for seamless processing in automated workflows. This function supports eleven extraction actions covering the most common document and data formats: CSV for tabular data parsing, HTML for extracting text content and table structures using BeautifulSoup, JSON for direct parsing, ICS for calendar event extraction, ODS and XLSX/XLS for spreadsheet processing across LibreOffice and Microsoft Excel formats, PDF for page-by-page text and table extraction using pdfplumber, RTF for rich text conversion, and plain text for basic content retrieval. Users can provide input via base64-encoded content or cloud storage file ID, with support for files up to 100MB and inline base64 returns up to 10MB. Configurable parameters allow fine-tuning of extraction behavior including maximum row limits up to 100,000 for spreadsheets, maximum page counts up to 1,000 for PDFs, and toggles for text and table inclusion in applicable formats. The function automatically handles character encoding detection and returns consistently structured JSON with customizable output field names, making it an essential bridge between raw file uploads and downstream data processing pipelines.

Use Cases

Parsing uploaded CSV files into structured records for database import or API submission, extracting tabular data from HTML reports or web page snapshots for analysis, converting calendar ICS files into event objects for scheduling integrations, processing Excel spreadsheets from user uploads into JSON for data transformation pipelines, extracting text and tables from PDF invoices or contracts for automated document processing, converting legacy XLS files from enterprise systems into modern JSON formats, parsing RTF documents from email attachments into plaintext for content indexing, scraping structured table data from HTML exports for reporting dashboards, extracting event details from shared calendar files for synchronization workflows, converting uploaded spreadsheet data into API-compatible payloads for third-party service integrations

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

curl -X POST "https://api.agentpmt.com/products/purchase" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ********" \
  -d '{
    "product_id": "695c3797767df5adfd9bc872",
    "parameters": {
      "action": "extract-csv",
      "output_field": "data",
      "max_rows": 1000
    }
  }'

import requests
import json

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

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

data = {
    "product_id": "695c3797767df5adfd9bc872",
    "parameters": {
        "action": "extract-csv",
        "output_field": "data",
        "max_rows": 1000
    }
}

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: "695c3797767df5adfd9bc872",
  parameters: {
    "action": "extract-csv",
    "output_field": "data",
    "max_rows": 1000
  }
};

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: "695c3797767df5adfd9bc872",
  parameters: {
    "action": "extract-csv",
    "output_field": "data",
    "max_rows": 1000
  }
};

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>
# action:invoke
# product:695c3797767df5adfd9bc872
# payload:<sha256(canonical_json(parameters))>

curl -s -X POST "https://www.agentpmt.com/api/external/tools/695c3797767df5adfd9bc872/invoke" \
  -H "Content-Type: application/json" \
  -d '{
    "wallet_address": "0xYOUR_WALLET",
    "session_nonce": "<session_nonce>",
    "request_id": "invoke-uuid",
    "signature": "0x<signature>",
    "parameters": {
      "action": "your_action",
      "your_param": "value"
    }
  }'

Actions(11)

extract-csv^5cr4 params

Parse a CSV file into structured row data.

input_base64string

Base64-encoded file content.

file_idstring

File ID from cloud storage.

output_fieldstring

Key name for the extracted data in the response.

Default: data

max_rowsinteger

Maximum rows to extract.

Default: 1000

Range: 1 - 100000

extract-html^5cr6 params

Parse an HTML file, extracting text content and/or table data.

input_base64string

Base64-encoded file content.

file_idstring

File ID from cloud storage.

output_fieldstring

Key name for the extracted data in the response.

Default: data

include_textboolean

Include extracted text content.

Default: true

include_tablesboolean

Include extracted table data.

Default: true

max_rowsinteger

Maximum rows per table.

Default: 1000

Range: 1 - 100000

extract-json^5cr3 params

Parse a JSON file and return its contents as structured data.

input_base64string

Base64-encoded file content.

file_idstring

File ID from cloud storage.

output_fieldstring

Key name for the extracted data in the response.

Default: data

extract-ics^5cr3 params

Parse an ICS calendar file and extract events with summary, start, end, location, and description.

input_base64string

Base64-encoded file content.

file_idstring

File ID from cloud storage.

output_fieldstring

Key name for the extracted data in the response.

Default: data

extract-ods^5cr4 params

Parse an OpenDocument Spreadsheet (.ods) file, returning sheets with row data.

input_base64string

Base64-encoded file content.

file_idstring

File ID from cloud storage.

output_fieldstring

Key name for the extracted data in the response.

Default: data

max_rowsinteger

Maximum rows per sheet.

Default: 1000

Range: 1 - 100000

extract-pdf^5cr6 params

Extract text and/or tables from a PDF document, page by page.

input_base64string

Base64-encoded file content.

file_idstring

File ID from cloud storage.

output_fieldstring

Key name for the extracted data in the response.

Default: data

include_textboolean

Include text extraction per page.

Default: true

include_tablesboolean

Include table extraction per page.

Default: true

max_pagesinteger

Maximum pages to process.

Default: 50

Range: 1 - 1000

extract-rtf^5cr3 params

Parse an RTF (Rich Text Format) file and extract plain text.

input_base64string

Base64-encoded file content.

file_idstring

File ID from cloud storage.

output_fieldstring

Key name for the extracted data in the response.

Default: data

extract-text^5cr3 params

Read a plain text file and return its contents.

input_base64string

Base64-encoded file content.

file_idstring

File ID from cloud storage.

output_fieldstring

Key name for the extracted data in the response.

Default: data

extract-xls^5cr4 params

Parse a legacy Excel (.xls) file, returning sheets with row data.

input_base64string

Base64-encoded file content.

file_idstring

File ID from cloud storage.

output_fieldstring

Key name for the extracted data in the response.

Default: data

max_rowsinteger

Maximum rows per sheet.

Default: 1000

Range: 1 - 100000

extract-xlsx^5cr4 params

Parse a modern Excel (.xlsx) file, returning sheets with row data.

input_base64string

Base64-encoded file content.

file_idstring

File ID from cloud storage.

output_fieldstring

Key name for the extracted data in the response.

Default: data

max_rowsinteger

Maximum rows per sheet.

Default: 1000

Range: 1 - 100000

file-to-base64^5cr2 params

Convert a file to base64-encoded string. File must be 10 MB or smaller for inline return.

input_base64string

Base64-encoded file content.

file_idstring

File ID from cloud storage.

Usage Instructions

Usage guidance provided directly by the developer for this product.

File To JSON Parsing - Instructions

Name: File To JSON Parsing
Brand: Apoth3osis
SKU: 695c3797767df5adfd9bc872
Price: 0.05 USD
Availability: InStock

Overview

Extract structured JSON data from a wide range of file formats. Provide a file via base64-encoded content or a cloud storage file ID, and receive parsed, structured output. Supports CSV, HTML, JSON, ICS (calendar), ODS, PDF, RTF, plain text, XLS, and XLSX files. Also supports converting any file to base64.

File Input

Every action (except get_instructions) requires one of the following:

input_base64 (string) - Base64-encoded file content (up to 100 MB raw; 10 MB for file-to-base64 return)
file_id (string) - File ID from cloud storage

Actions

extract-csv

Parse a CSV file into structured row data.

Required: action, plus input_base64 or file_id Optional:

max_rows (integer, default 1000, max 100000) - Maximum rows to extract
output_field (string, default "data") - Key name for the extracted data in the response

Example:

{
  "action": "extract-csv",
  "input_base64": "bmFtZSxhZ2UKQWxpY2UsMzAKQm9iLDI1"
}

extract-html

Parse an HTML file, extracting text content and/or table data.

Required: action, plus input_base64 or file_id Optional:

include_text (boolean, default true) - Include extracted text content
include_tables (boolean, default true) - Include extracted table data
max_rows (integer, default 1000) - Maximum rows per table
output_field (string, default "data")

Example:

{
  "action": "extract-html",
  "file_id": "abc123",
  "include_text": true,
  "include_tables": true
}

extract-json

Parse a JSON file and return its contents as structured data.

Required: action, plus input_base64 or file_id Optional:

output_field (string, default "data")

Example:

{
  "action": "extract-json",
  "input_base64": "eyJrZXkiOiAidmFsdWUifQ=="
}

extract-ics

Parse an ICS calendar file and extract events with summary, start, end, location, and description.

Required: action, plus input_base64 or file_id Optional:

output_field (string, default "data")

Example:

{
  "action": "extract-ics",
  "file_id": "calendar_file_id"
}

extract-ods

Parse an OpenDocument Spreadsheet (.ods) file, returning sheets with row data.

Required: action, plus input_base64 or file_id Optional:

max_rows (integer, default 1000, max 100000) - Maximum rows per sheet
output_field (string, default "data")

Example:

{
  "action": "extract-ods",
  "file_id": "spreadsheet_file_id",
  "max_rows": 500
}

extract-pdf

Extract text and/or tables from a PDF document, page by page.

Required: action, plus input_base64 or file_id Optional:

include_text (boolean, default true) - Include text extraction per page
include_tables (boolean, default true) - Include table extraction per page
max_pages (integer, default 50, max 1000) - Maximum pages to process
output_field (string, default "data")

Example:

{
  "action": "extract-pdf",
  "file_id": "report_pdf_id",
  "max_pages": 10,
  "include_text": true,
  "include_tables": false
}

extract-rtf

Parse an RTF (Rich Text Format) file and extract plain text.

Required: action, plus input_base64 or file_id Optional:

output_field (string, default "data")

Example:

{
  "action": "extract-rtf",
  "input_base64": "e1xydGYxIEhlbGxvIFdvcmxkfQ=="
}

extract-text

Read a plain text file and return its contents.

Required: action, plus input_base64 or file_id Optional:

output_field (string, default "data")

Example:

{
  "action": "extract-text",
  "file_id": "text_file_id"
}

extract-xls

Parse a legacy Excel (.xls) file, returning sheets with row data.

Required: action, plus input_base64 or file_id Optional:

max_rows (integer, default 1000, max 100000) - Maximum rows per sheet
output_field (string, default "data")

Example:

{
  "action": "extract-xls",
  "file_id": "legacy_excel_id",
  "max_rows": 2000
}

extract-xlsx

Parse a modern Excel (.xlsx) file, returning sheets with row data.

Required: action, plus input_base64 or file_id Optional:

max_rows (integer, default 1000, max 100000) - Maximum rows per sheet
output_field (string, default "data")

Example:

{
  "action": "extract-xlsx",
  "input_base64": "<base64_encoded_xlsx>",
  "max_rows": 5000
}

file-to-base64

Convert a cloud-stored file to base64 for inline use. The file must be 10 MB or smaller.

Required: action, plus input_base64 or file_id

Example:

{
  "action": "file-to-base64",
  "file_id": "image_file_id"
}

Common Workflows

Parse an uploaded spreadsheet: Use extract-xlsx or extract-xls with a file_id to get structured row data from each sheet.
Extract text from a PDF report: Use extract-pdf with include_text: true and include_tables: false for text-only extraction.
Convert HTML to structured data: Use extract-html to pull both readable text and any embedded tables from an HTML file.
Read calendar events: Use extract-ics to get a list of events from an ICS calendar export.
Retrieve a file as base64: Use file-to-base64 with a file_id to get the raw file content encoded for inline transfer.

Important Notes

Every extraction action requires either input_base64 or file_id -- at least one must be provided.
Maximum file size is 100 MB. The file-to-base64 action has a stricter 10 MB limit for the returned content.
The max_rows parameter applies to CSV, HTML tables, ODS, XLS, and XLSX extractions.
The max_pages parameter applies only to PDF extraction.
The include_text and include_tables options apply to HTML and PDF extraction.
The output_field parameter lets you customize the key name in the response (default is "data").
Text files are decoded as UTF-8, falling back to Latin-1 if needed.
Spreadsheet actions (ODS, XLS, XLSX) return data organized by sheet, each with a name and rows array.

About The Developer

Apoth3osis

★15 stars

Joined Agent Payment: August 14, 2025

We build tools that enable AI agents to excel in the mathematical realm.

Our small team develops experimental and unique solutions in the AI arena, with a strong focus on modular computing for agentic applications and custom model deployment. We have handled projects for a variety of applications across many sectors, from algorithmic trading and financial analysis, to molecular simulations and predictions, to habitat and biodiversity monitoring and wildlife conservation.

Dependencies

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

Dependencies are not available to view right now.

File To JSON Parsing

Description