How to Use the AlgoDocs MCP in OpenAI Agents SDK

Q: How do I install the AlgoDocs MCP Server for OpenAI Agents SDK?

Run pip install openai-agents and define a MCPServerStreamableHttp object with your endpoint URL. Pass this instance in the mcpservers list when initializing your Agent. Set cacheToolsList=True to speed up tool discovery.

Q: Can OpenAI Agents SDK check my AlgoDocs account limits?

Yes, your agent can call getmyaccount and getapiusage. You can set up guardrails that prevent the agent from starting new jobs if you are close to your quota.

Q: Does the AlgoDocs integration work with OpenAI Agents SDK handoffs?

It does. One agent can run uploaddocumentfromurl and then hand the job ID over to a specialized data extraction agent. That second agent then calls getdocumentdata when the file finishes processing.

Q: How does the agent know which AI extractor to use?

The system auto-discovers the listextractors tool on startup. Your agent reads the available extractors and selects the correct ID based on the document type.

Connect AlgoDocs to your OpenAI Agents SDK system to parse PDFs and route extracted text through specialized agent handoffs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AlgoDocs MCP to OpenAI Agents SDK

Create your Vinkius account to connect AlgoDocs to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup AlgoDocs with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build extraction pipelines with OpenAI Agents SDK

The `upload_document_from_url` tool feeds raw PDFs directly into your OpenAI agent system. You pass a file link, and the agent triggers the parsing job while built-in guardrails validate the request parameters before execution. Once the job starts, your agent polls `get_document_status` until completion. The system then pulls the parsed text via `get_document_data`, allowing you to trace the entire extraction process in your OpenAI dashboard.

Manage bulk extraction and storage

Your specialized agents can navigate the AlgoDocs folder structure using `list_folders` and `get_folder_details`. This lets a sorting agent find specific directories before handing off the task to a processing agent. For high-volume tasks, the `list_extractor_data` tool pulls bulk results from specific AI extractors. You avoid hitting rate limits by checking `get_api_usage` inside your agent logic, keeping your production deployment stable.

Discover extractors dynamically

Agents auto-discover available parsing models via the `list_extractors` tool. Instead of hardcoding model IDs, your OpenAI agent queries the AlgoDocs MCP Server at runtime to find the right extractor for a given document type. You can also track recent pipeline activity with `list_recent_documents`. This gives your supervisory agents visibility into what the system processed over the last hour.

Setup guide

Set up AlgoDocs MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all AlgoDocs tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives AlgoDocs tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate AlgoDocs tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="AlgoDocs Agent",
            instructions="You have access to AlgoDocs tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by AlgoDocs. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect AlgoDocs now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about AlgoDocs MCP in OpenAI Agents SDK

Run `pip install openai-agents` and define a `MCPServerStreamableHttp` object with your endpoint URL. Pass this instance in the `mcp_servers` list when initializing your Agent. Set `cacheToolsList=True` to speed up tool discovery.

Yes, your agent can call `get_my_account` and `get_api_usage`. You can set up guardrails that prevent the agent from starting new jobs if you are close to your quota.

It does. One agent can run `upload_document_from_url` and then hand the job ID over to a specialized data extraction agent. That second agent then calls `get_document_data` when the file finishes processing.

The system auto-discovers the `list_extractors` tool on startup. Your agent reads the available extractors and selects the correct ID based on the document type.

Vinkius runs the endpoint inside a V8 Isolate Sandbox. Your uploaded PDFs and extracted Word document data exist only during the active session. The ephemeral environment destroys all memory the moment your API call completes.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript