How to Use the AlgoDocs MCP in Pydantic AI

Q: How do I connect the AlgoDocs MCP Server to Pydantic AI?

Install pydantic-ai-slimmcp. Initialize an MCPToolset with your HTTP endpoint URL. Pass this toolset into your Agent constructor. Do not use the deprecated MCPServerHTTP class.

Q: Does Pydantic AI validate the AlgoDocs extraction results?

Yes. When your agent calls getdocumentdata, the framework checks the returned JSON against your predefined models. Any missing fields trigger an immediate runtime error.

Q: How do I handle long-running document parses?

Your agent should call uploaddocumentfromurl and then enter a polling loop. It can check getdocumentstatus periodically until the API returns a completed state.

Force AlgoDocs extractions into strict Pydantic models to guarantee your parsed PDFs match your exact schema requirements.

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 Pydantic AI

Create your Vinkius account to connect AlgoDocs to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe document parsing via MCP Server

The `upload_document_from_url` tool initiates the parsing job inside your Pydantic AI framework. Your agent requests the extraction, and the framework ensures the URL parameter matches the expected string format before sending the request. Retrieving the final text requires `get_document_data`. If the API returns a malformed response or missing fields, Pydantic AI fails loudly with a validation error, preventing silent data corruption in your pipeline.

Validate folder and extractor metadata

Navigating your document storage relies on the `list_folders` tool exposed by the MCP Server. Every folder ID and metadata field returned from `get_folder_details` gets validated against your Pydantic schemas at runtime. The same strict typing applies to `list_extractors`. Your agent queries the available AI parsers, and the framework guarantees that the returned extractor IDs are valid integers or strings before your system attempts to use them.

Track usage and recent files strictly

Monitoring your MCP Server quota involves calling `get_api_usage` and `get_my_account`. Your agent pulls these metrics, and Pydantic AI verifies the integer limits so your billing logic never receives a null value. You can audit recent activity using `list_recent_documents`. If a bulk job finishes, `list_extractor_data` pulls the results, with every single extracted record passing through strict runtime validation.

Setup guide

Set up AlgoDocs MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "algodocs-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to AlgoDocs tools.",
)

result = await agent.run("List recent AlgoDocs transactions")
print(result.output)

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 Pydantic AI

Install `pydantic-ai-slim[mcp]`. Initialize an `MCPToolset` with your HTTP endpoint URL. Pass this toolset into your Agent constructor. Do not use the deprecated `MCPServerHTTP` class.

Yes. When your agent calls `get_document_data`, the framework checks the returned JSON against your predefined models. Any missing fields trigger an immediate runtime error.

Yes. Pydantic AI is model-agnostic. You can route the extracted PDF text to Anthropic, OpenAI, or a local model running on your own hardware.

Your agent should call `upload_document_from_url` and then enter a polling loop. It can check `get_document_status` periodically until the API returns a completed state.

Vinkius routes your API calls through an isolated V8 sandbox. Your uploaded images and extracted text exist only in memory during the request. The environment terminates as soon as the transport layer disconnects.

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