How to Use the Bounsel MCP in Pydantic AI

Q: Is my Bounsel account info private within Pydantic AI?

Your sensitive account information is fetched via getaccountinfo and validated immediately against your Pydantic models. We treat these responses as transient data that exists only for the duration of the agent's current task.

Enforce strict type safety for your contract workflows using Bounsel and Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bounsel MCP to Pydantic AI

Create your Vinkius account to connect Bounsel 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 Bounsel with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strictly typed contract actions in Pydantic AI

Every call to `get_document` returns a structured response that must match your Pydantic model. If the API response deviates, your agent catches it immediately. You define the expected shape of your data, and the framework enforces it at runtime. This prevents your agent from acting on malformed contract details.

Automate templates using Pydantic AI models

Use `list_templates` to fetch available documents and validate them against your schema. Your agent knows exactly what fields are available before it attempts to generate anything. Calling `create_document` is safer because the input is validated before the server ever sees it. You get clear errors if your agent tries to pass invalid data.

Secure document lifecycle in Pydantic AI

Manage your signature requests with `send_document` while relying on type checks. It ensures that required fields like recipient emails are present and formatted correctly. Audit your user access with `list_users` and have your agent fail gracefully if the response doesn't match your expected model. It eliminates silent data corruption during your agent runs.

Setup guide

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

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

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

You initialize an MCPToolset with your Vinkius HTTP URL. Then, you add it to the toolsets list in your Agent definition.

If the API returns unexpected data, the agent will raise a validation error. This is a feature, as it stops the agent before it processes bad data.

Yes, because the framework is model-agnostic, you can use these tools with OpenAI, Anthropic, or local models. The type safety remains consistent regardless of the underlying LLM.

You can catch the validation errors within your agent loop. This allows you to log the failure and decide whether to retry or abort the task.

Your sensitive account information is fetched via `get_account_info` and validated immediately against your Pydantic models. We treat these responses as transient data that exists only for the duration of the agent's current task.

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