How to Use the Dovetail MCP in Pydantic AI

Q: How do I initialize the Dovetail MCP Server toolset in Pydantic AI?

You use the MCPToolset constructor with your server's HTTP endpoint and pass it to your Agent's toolsets list. Avoid the deprecated MCPServerHTTP class to keep your codebase aligned with current framework standards. The toolset automatically registers tools like listprojects for validation.

Run type-safe synthesis on Dovetail research data with Pydantic AI's strict runtime validation and multi-model support.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dovetail MCP to Pydantic AI

Create your Vinkius account to connect Dovetail 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 Dovetail with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate research notes at runtime with Pydantic AI

The `create_note` tool writes new customer feedback with strict schema validation enforced before any data leaves your runtime. If your model attempts to write a note with missing fields or malformed text, the framework blocks the call instantly. This MCP Server integration prevents silent data corruption in your research database. Your agent catches structural errors early, raising explicit Python validation errors instead of writing broken JSON to your active workspace.

Parse structured insights without model hallucination

The `list_insights` tool returns raw research findings that map directly to your custom Pydantic models. Your Pydantic AI agent parses the workspace response, ensuring every field matches your exact type definitions before executing downstream code. Because the framework is model-agnostic, you can swap between OpenAI, Anthropic, or local models without rewriting your parsing logic. The type constraints remain identical, keeping your research synthesis pipeline stable across different LLM providers.

Audit workspace membership with strict type-safety

The `list_workspace_members` tool exposes your user directory to type-safe MCP workflows. Your Pydantic AI agent verifies that the assigned researcher exists in the workspace before running `create_insight` to log a new theme. This strict verification loop ensures your automated research pipelines never assign findings to non-existent users. You catch mapping bugs in your local test suite before they affect your production workspace.

Setup guide

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

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

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

You use the `MCPToolset` constructor with your server's HTTP endpoint and pass it to your Agent's `toolsets` list. Avoid the deprecated `MCPServerHTTP` class to keep your codebase aligned with current framework standards. The toolset automatically registers tools like `list_projects` for validation.

The framework raises a loud validation error at runtime, halting execution before bad data propagates. This strict behavior prevents your agent from processing hallucinated fields or corrupted notes. You get clean, typed data structures every time.

Yes, the toolset fully supports both Streamable HTTP and SSE transports for external MCP servers. You run the server as an independent service and connect your agent securely via the unified client interface. This decoupled setup is ideal for production deployments.

Yes, you can run the agent with Ollama or any local model provider while maintaining full type safety. The framework validates the inputs and outputs of tools like `get_project_details` regardless of which model runs the reasoning loop. This lets you keep your analysis pipeline entirely local.

The framework delegates all connection management to the secure Vinkius gateway, which handles your workspace tokens via single-endpoint authentication. Your raw research notes and project metadata never pass through unencrypted channels. The runtime environment is completely isolated, keeping your customer feedback private.

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