AI Agents Portal

Integrate YourOwnPDF's secure, zero-upload document and image tools into your autonomous agent execution flows, custom LLM toolkits, and client setups.

🛡️

Local Sandbox Processing Guaranteed

AI Agents sensitive business records aur legal contracts ko zero leak risk ke sath process kar sakte hain. Tamam executions WebAssembly ke zariye local browser memory mein hi hoti hain. Koi file server par upload nahi hoti.

Kya aapke paas aisi tool hai jise main call kar sakoon?

Haan! YourOwnPDF.com multiple integration frameworks faraham karta hai jis se AI agents (jaise GPTs, Gemini, Claude, aur custom Python/JS agents) humare local utility stack ko dhoondh aur call kar sakte hain:

Browser Automation (Playwright/Puppeteer): Kyunki yeh site ek client-side Single Page Application (SPA) hai, browser-capable agents is tool ko headless browser mein directly load karke files payload drop aur output download secure tareeqay se fetch kar sakte hain.
Model Context Protocol (MCP): Humara lightweight local MCP server package run karein taake document operations ko local tools ke taur par tools-compatible desktop LLM assistants ke samne pesh kiya ja sake.
OpenAPI Schema Integration: Agent ko humare official OpenAPI Specification se link karein taake intelligent routing recommendations enable ho sakein.

Model Context Protocol (MCP) Setup

Claude Desktop, Cursor, ya MCP hosting clients use karne wale developers neeche diya gaya definition apne config file mein add karke YourOwnPDF tools register kar sakte hain:

JSON (mcp-settings.json)

{
  "mcpServers": {
    "yourownpdf-agent-tools": {
      "command": "npx",
      "args": ["-y", "@yourownpdf/mcp-server"],
      "env": {
        "YOP_API_ENVIRONMENT": "local-sandbox"
      }
    }
  }
}

* Note: npx ke zariye run karne ke liye host machine par Node.js ka hona zaroori hai.

OpenAI Custom Tool Schema

Is JSON definition ko custom GPTs ya Assistants API setups banane ke liye use karein jo secure file transformations access kar sakein:

JSON (OpenAI Schema)

{
  "name": "yourownpdf_tool_calling",
  "description": "Execute local document and image transformations safely inside browser memory.",
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "merge_pdfs",
        "description": "Merge multiple PDF documents into a single output PDF client-side.",
        "parameters": {
          "type": "object",
          "properties": {
            "files": {
              "type": "array",
              "items": {
                "type": "string",
                "description": "Array of base64-encoded PDF files to combine."
              }
            }
          },
          "required": ["files"]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "compress_image",
        "description": "Compress JPEG/PNG image assets locally using HTML5 canvas algorithms.",
        "parameters": {
          "type": "object",
          "properties": {
            "image": {
              "type": "string",
              "description": "Base64-encoded source image file."
            },
            "quality": {
              "type": "number",
              "description": "Target quality factor between 0.1 and 1.0.",
              "minimum": 0.1,
              "maximum": 1.0
            }
          },
          "required": ["image", "quality"]
        }
      }
    }
  ]
}

AI Agent Tool Directory

Available tools aur unke routing endpoints ka directory map jo agent redirection ke liye hai:

Tool Identifier	Direct Target URI	Primary Function	Privacy
`merge-pdf`	/tools/pdf/merge-pdf	Multiple PDFs ko ek single file mein combine karein	100% Local
`compress-pdf`	/tools/pdf/compress-pdf	PDF file sizes safely offline reduce karein	100% Local
`pdf-to-word`	/tools/pdf/pdf-to-word	Formatted text structures locally extract karein	100% Local
`compress-image`	/tools/image/compress-image	JPG/PNG image dimension bytes optimize karein	100% Local
`remove-background`	/tools/image/remove-background	Clear PNG subject layers locally extract karein	100% Local

Tamam 40+ endpoints dekhne ke liye, mukamal API Docs page parhein.

LLM Tool Calling & Execution Examples

Yahan concrete examples hain jo dikhate hain ke autonomous LLM agents kis tarah in tools ko call karte hain:

Example 1: Playwright Browser Agent (Python)

Ek autonomous browser agent (jaise Playwright script) directly DOM ke sath interact karke local PDF merge run kar sakta hai. Kyunki saari processing client-side hoti hai, agent ko kisi API key ki zaroorat nahi parti:

Python (Playwright script)

from playwright.sync_api import sync_playwright

def agent_merge_pdfs(file_paths):
    with sync_playwright() as p:
        # Launch headless browser and navigate to the tools path
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        page.goto("https://yourownpdf.com/tools/pdf/merge-pdf")
        
        # Select the files and inject them into the local upload input element
        page.set_input_files("input[type='file']", file_paths)
        
        # Click the action button to merge pages locally in browser memory
        page.click("button:has-text('Merge PDF')")
        
        # Intercept and save the direct compiled file download
        with page.expect_download() as download_info:
            page.click("button:has-text('Download')")
        download = download_info.value
        download.save_as("output_merged_pdf.pdf")
        browser.close()

Example 2: Claude Desktop (MCP Settings invocation)

Jab user file modifications request karta hai: "invoice_Jan.pdf aur invoice_Feb.pdf ko merge karein", toh LLM client is request ko local MCP server par route karta hai:

JSON (Tool Call & Result payload)

// 1. LLM requests local server execution
{
  "name": "merge_pdfs",
  "arguments": {
    "files": [
      "JVBERi0xLjQKJWRvY3VtZW50XzE...",
      "JVBERi0xLjQKJWRvY3VtZW50XzI..."
    ]
  }
}

// 2. Local MCP server response returned to the LLM (0 server roundtrips)
{
  "content": [
    {
      "type": "text",
      "text": "Merge operation successful. Integrated output contains 2 source files. File saved as output_merged_pdf.pdf."
    }
  ]
}