Can the AI Agent resolve or close a task automatically?

Yes, using the `update_task` tool, the agent can change the task status to 'closed' or 'done' within BugHerd.

Are attachments or screenshots supported?

Currently, the MCP Server manages text-based tasks, comments, and project structures. Adding direct screenshot files via AI is not supported in this version.

Can I read comments from any ticket?

Yes! The agent can fetch and read all comments attached to a specific task using the `list_comments` tool, provided you supply the Project ID and Task ID.

INSTANT PLUG AND PLAY

BugHerd MCP Server for OpenAI Agents SDKGive OpenAI Agents SDK instant access to 10 tools to Add Comment, Create Project, Create Task, and more

Name: BugHerd
Availability: InStock
Author: Vinkius

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect BugHerd through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Use with Your AI Agent

Ask AI about this App Connector for OpenAI Agents SDK

Open in ChatGPT Open in Claude Open in Perplexity

The BugHerd app connector for OpenAI Agents SDK is a standout in the Developer Tools category — giving your AI agent 10 tools to work with, ready to go from day one.

Vinkius delivers Streamable HTTP and SSE to any MCP client

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="BugHerd Assistant",
            instructions=(
                "You help users interact with BugHerd. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from BugHerd"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About BugHerd MCP Server

O que você pode fazer

Create and list your BugHerd projects.
Manage tasks seamlessly inside projects.
Retrieve, add, and monitor comments on specific bug tasks.
View all members within your BugHerd workspace.

Como funciona

1. Install the BugHerd MCP Server on your Vinkius Edge. 2. Add your personal BugHerd API key in the credentials page. 3. Empower your AI agent to fetch bugs, add comments, and triage tickets naturally via chat.

Para quem é?

Ideal for development and QA teams looking to interact with BugHerd tickets directly via Cursor, Claude, or any MCP-enabled agent. Turn your AI into a full-fledged QA assistant.

The OpenAI Agents SDK auto-discovers all 10 tools from BugHerd through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries BugHerd, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

The BugHerd MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

All 10 BugHerd tools available for OpenAI Agents SDK

When OpenAI Agents SDK connects to BugHerd through Vinkius, your AI agent gets direct access to every tool listed below — spanning bug-tracking, website-feedback, task-management, and more. Every call is secured with network, filesystem, subprocess, and code evaluation entitlements inside a sandboxed runtime. Beyond a simple connection, you get a full AI Gateway with real-time visibility into agent activity, enterprise governance, and optimized token usage.

add_comment

Add a comment to a BugHerd task

create_project

Create a new project in BugHerd

create_task

Create a new task in a BugHerd project

get_project

Get a specific project in BugHerd

get_task

Get a specific task in BugHerd

list_comments

List comments on a BugHerd task

list_projects

List projects in BugHerd

list_tasks

List tasks for a project in BugHerd

list_users

List users in the BugHerd account

update_task

Can update description, status, priority, or assigned_to_id. Update a task in BugHerd

Connect BugHerd to OpenAI Agents SDK via MCP

Follow these steps to wire BugHerd into OpenAI Agents SDK. The entire setup takes under two minutes — your credentials stay safe behind the Vinkius.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from BugHerd

Why Use OpenAI Agents SDK with the BugHerd MCP Server

OpenAI Agents SDK provides unique advantages when paired with BugHerd through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

BugHerd + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the BugHerd MCP Server delivers measurable value.

Automated workflows: build agents that query BugHerd, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries BugHerd, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through BugHerd tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query BugHerd to resolve tickets, look up records, and update statuses without human intervention

Example Prompts for BugHerd in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with BugHerd immediately.

"List all active projects in BugHerd."

"Create a new bug task in project 123 saying 'Login button is broken'."

"Read the comments on task 456 in project 123."

Troubleshooting BugHerd MCP Server with OpenAI Agents SDK

Common issues when connecting BugHerd to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

BugHerd + OpenAI Agents SDK FAQ

Common questions about integrating BugHerd MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.

Can I use multiple MCP servers in one agent?

Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.

Does the SDK support streaming responses?

Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.