How to Use the BugHerd MCP in Pydantic AI

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

Install the pydantic-ai-slimmcp package and use the MCPToolset class. Avoid the deprecated MCPServerHTTP class and pass the toolset to your Agent constructor.

Build type-safe bug workflows using BugHerd 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 BugHerd MCP to Pydantic AI

Create your Vinkius account to connect BugHerd 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 BugHerd with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce strict schemas on BugHerd tasks with Pydantic AI

This BugHerd MCP Server integrates with Pydantic AI to ensure every task detail matches your expected types. When your agent calls `get_task` or `list_tasks`, the framework validates the API response against strict schemas at runtime. If the server returns unexpected metadata, Pydantic AI raises a validation error immediately. This prevents your agent from working with corrupt data or hallucinating task properties during execution.

Validate BugHerd updates before execution in Pydantic AI

This MCP Server lets you run type-safe updates using `update_task` and `create_task`. Pydantic AI checks the agent's proposed arguments against the tool's input schema before sending the payload to the server. This front-end validation catches formatting errors early. Your agent won't waste API calls trying to pass malformed dates or invalid user IDs to the BugHerd API.

Map BugHerd organization data to Pydantic models

This BugHerd MCP Server makes it easy to map complex outputs from `get_organization_info` and `list_users` into clean Python objects. Your agent can query user lists and safely extract emails, roles, and project permissions. Because Pydantic AI is model-agnostic, you can use these validated models with OpenAI, Anthropic, or local LLMs. You get the same reliable data parsing no matter which model powers your agent.

Setup guide

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

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

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

Install the pydantic-ai-slim[mcp] package and use the MCPToolset class. Avoid the deprecated MCPServerHTTP class and pass the toolset to your Agent constructor.

Pydantic AI will raise a validation error. The framework catches this mismatch, preventing your agent from executing downstream actions based on unverified data fields.

Yes. The framework automatically parses the tool's schema and validates the agent's input before calling the server, ensuring all required fields are present.

The server supports both Streamable HTTP and SSE transports. You can configure your MCPToolset to connect to your Vinkius HTTP endpoint.

Your BugHerd API keys and task metadata are injected securely at runtime and never exposed in the client-side code. The Vinkius platform processes all tool executions inside isolated, zero-trust sandboxes that discard session data instantly.

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