How to Use the DocBreach MCP in Pydantic AI

Q: What is the best way to handle large PDFs?

docs.read supports PDFs under 5MB, converting them directly into markdown. For larger documentation files, we recommend splitting the document or targeting specific web-based endpoints instead.

Fetch type-safe API specs and docs directly into your Pydantic AI agents with zero silent failures.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DocBreach MCP to Pydantic AI

Create your Vinkius account to connect DocBreach 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 DocBreach with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inject Type-Safe Specs into Pydantic AI

`docs.extract` parses OpenAPI and Swagger specifications directly into structured schemas that your Pydantic AI agent validates at runtime. This tool eliminates silent parser failures by delivering clean, structured data that maps perfectly to your Pydantic models. By validating the extracted endpoint data before execution, your system catches structural changes in external APIs immediately. The agent fails loudly if an endpoint schema changes, preventing corrupted inputs from reaching your downstream application logic.

Map and Read Without Browser Overhead

`docs.map` generates a clean table of contents for any documentation domain to let your agent plan its reading path. Your agent inspects the mapped structure and selects specific URLs to ingest, keeping token consumption highly predictable. After identifying the target pages, `docs.read` converts the target HTML, JSON, or PDF into clean markdown. This raw text parsing avoids heavy browser rendering, giving your agent immediate access to the documentation without the overhead of external headless browsers.

Scoped Search for Precise Context Injection

`docs.search` queries specific documentation sites using a mandatory site parameter to retrieve highly targeted code snippets or error codes. This scoped approach ensures your agent receives only the exact context it needs, preventing model hallucination. For broader queries, `docs.discover` locates the correct documentation homepages based on descriptive search parameters. You register these tools using the unified MCP toolset constructor, allowing your type-safe agents to run live discovery loops securely.

Setup guide

Set up DocBreach 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": {
        "docbreach-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent DocBreach 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 DocBreach. 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 DocBreach 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 DocBreach MCP in Pydantic AI

The server returns strictly structured JSON payloads that your Pydantic AI schemas validate at runtime. If `docs.extract` returns an unexpected schema structure, your agent catches the validation error immediately instead of processing corrupted data.

Yes, you run the MCP server externally on the Vinkius platform and connect using the unified MCPToolset constructor. This setup supports both streamable HTTP and SSE transports, keeping your local agent runtime lightweight.

No, the server processes documentation URLs and API specs without relying on local headless browsers or web drivers. This headless parsing happens entirely on the Vinkius hosting environment, saving local compute resources.

`docs.read` supports PDFs under 5MB, converting them directly into markdown. For larger documentation files, we recommend splitting the document or targeting specific web-based endpoints instead.

All target documentation URLs and parsed API specs are processed in isolated, ephemeral memory blocks that are wiped clean immediately after the tool response is sent. No data is cached or written to disk, ensuring complete isolation for your sensitive integration targets.

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