How to Use the BugHerd MCP in CrewAI

Q: How do I assign the BugHerd MCP Server tools to specific CrewAI agents?

Pass the Vinkius endpoint URL directly into the mcps list of your Agent definition. You can let all agents share the entire toolset or use a tool filter to restrict tools like updatetask to your lead coordinator agent.

Deploy a crew of specialized CrewAI agents to manage your BugHerd boards autonomously.

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 CrewAI

Create your Vinkius account to connect BugHerd to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent bug triage and assignment

Let a team of specialized agents clean up your backlog. With CrewAI, you can set up a Triage Agent to pull new issues using `list_feedback`, while an Assignment Agent matches the bugs against your team roster using `list_users`. They collaborate in the background, sharing context to make smart routing decisions. This collaborative approach means the agents don't work in a vacuum. The assignment agent checks who is overloaded before calling `update_task` to assign the ticket, ensuring your team's workload stays balanced.

Autonomous project health monitoring

Keep your client projects on track without constant manual checks. A QA Agent can periodically scan active boards with `list_tasks` to find tickets stuck in QA. If it finds any, it escalates the issue by calling `get_task` to pull full details and notifying the project owner. Because CrewAI supports hierarchical execution, a Manager Agent can oversee this entire process. It coordinates the QA and Assignment Agents, ensuring that stale tickets are reassigned or resolved without you touching a keyboard.

Direct CrewAI team setup with BugHerd MCP Server

Configure your entire agent crew with a single connection. You pass the Vinkius HTTP endpoint directly into your CrewAI agent's `mcps` array, instantly granting your team access to tools like `create_project` and `get_organization_info` via this MCP Server. For advanced setups, you can use the `MCPServerHTTP` class to filter exactly which tools each agent can access. This keeps your QA agent focused on `list_tasks` while restricting project creation tools to your Manager agent.

Setup guide

Set up BugHerd MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke BugHerd tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="BugHerd Analyst",
    goal="Access and analyze BugHerd data via MCP.",
    backstory="Expert analyst with direct BugHerd access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent BugHerd transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="BugHerd Analyst",
        goal="Access and analyze BugHerd data via MCP.",
        backstory="Expert analyst with direct BugHerd access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent BugHerd transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass the Vinkius endpoint URL directly into the `mcps` list of your Agent definition. You can let all agents share the entire toolset or use a tool filter to restrict tools like `update_task` to your lead coordinator agent.

Yes, CrewAI's shared memory allows agents to pass task details between themselves. A researcher agent can run `get_task` to analyze a bug, and then pass that diagnostic data to a developer agent who updates the ticket status.

Vinkius manages the authentication layer, providing you with a single endpoint token. Your CrewAI Python script uses this token to connect to the server, allowing your agents to safely call `list_projects` without managing multiple API keys.

Yes. You can define a sequential process where Agent A calls `create_project` to build the workspace, and Agent B immediately follows up by calling `list_users` to populate the project with the correct team members.

Yes. The integration runs within a secure V8 Isolate Sandbox on Vinkius, which executes your tool calls ephemerally. Your project names, task descriptions, and user directories are processed in real-time and never cached on disk.

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