How to Use the BugHerd MCP in OpenAI Agents SDK

Q: What happens if an agent tries to edit a non-existent project?

The updatetask tool will return an error message. The SDK passes this error back to your agent, which can then use listprojects to find the correct ID and try again.

Run BugHerd actions through the OpenAI Agents SDK with built-in safety guardrails and multi-agent tracing.

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 OpenAI Agents SDK

Create your Vinkius account to connect BugHerd to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safely dispatch BugHerd edits via OpenAI Agents SDK

This BugHerd MCP Server connects your OpenAI agents directly to your feedback queues. Your agent uses `update_task` to resolve bugs and `create_task` to log new visual feedback without leaving the execution loop. Because the OpenAI Agents SDK enforces strict runtime validation, you can inspect these tool calls on your dashboard before they hit your live project. Setting this up takes seconds. Your agent discovers the tool schemas automatically, allowing you to hand off task creation to a specialized QA agent while keeping your main routing agent clean.

Automate project setup with OpenAI Agents SDK

This MCP Server exposes `create_project` and `list_projects` to let your OpenAI agents build out new tracking spaces on demand. When a new client site goes live, your agent creates the project and instantly populates it with default tasks. The SDK's built-in tracing shows you exactly when and why the agent decided to spin up a new project. You get a clear execution graph of every API call, making it easy to debug agent behavior when project configurations change.

Coordinate bug triage across specialized OpenAI Agents

This BugHerd MCP Server lets you build a multi-agent system where one agent fetches tasks using `list_tasks` and another assigns them using `update_task`. The OpenAI Agents SDK manages the handoff between these specialized agents so they don't step on each other's toes. You can track this entire triage process through the OpenAI dashboard. It shows you the exact conversation flow and tool execution history, ensuring your automated bug triager never goes rogue.

Setup guide

Set up BugHerd MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all BugHerd tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives BugHerd tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate BugHerd tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="BugHerd Agent",
            instructions="You have access to BugHerd tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the SDK first, then use MCPServerStreamableHttp to point to the server URL. Pass this server instance in the mcp_servers list when initializing your Agent constructor.

Yes. The OpenAI Agents SDK lets you intercept tool calls before they run. You can inspect the arguments for update_task in your guardrail logic before the server executes the change.

Yes, you can set cacheToolsList=True in your server parameters. This prevents the SDK from refetching the schemas for list_tasks and create_task on every single agent run, lowering latency.

The update_task tool will return an error message. The SDK passes this error back to your agent, which can then use list_projects to find the correct ID and try again.

Your BugHerd project configurations and task descriptions never persist on the Vinkius platform. The MCP Server acts as an ephemeral gateway, passing your API tokens directly through secure V8 sandboxes that wipe their memory after every request.

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