BugHerd MCP. Manage bugs, update status, and track comments from chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
BugHerd MCP lets your agent handle bug tracking, project setup, and task management directly in chat. You can create new projects, list all active tickets, pull specific issue details, update statuses (like priority or assigned user), or add context-specific comments—all without leaving your preferred AI client.
It turns your AI into a full QA assistant for development teams.
What your AI agents can do
Add comment
Adds a comment or update note directly to an existing BugHerd task.
Create project
Establishes and organizes a brand new project within your BugHerd account.
Create task
Generates a new bug report or feature task inside a specific project.
Create new BugHerd workspaces or retrieve details about existing ones.
Generate, list, or pull detailed information on specific bug reports and project tickets.
Update a task's description, priority, or assignee using natural language commands.
Fetch and list all comments associated with any bug task for full context.
List all users currently active within the BugHerd workspace.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
BugHerd: 10 Tools for QA and Dev Teams
These ten tools let your agent interact with every core feature of BugHerd, from creating new projects to updating the smallest task details.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using BugHerd on Vinkius019dd0c7add comment
Adds a comment or update note directly to an existing BugHerd task.
019dd0c7create project
Establishes and organizes a brand new project within your BugHerd account.
019dd0c7create task
Generates a new bug report or feature task inside a specific project.
019dd0c7get project
Retrieves all the core information for one specific BugHerd project.
019dd0c7get task
Pulls up the complete details and current status of a single bug task.
019dd0c7list comments
Fetches all comments left on a particular bug task, giving you full context.
019dd0c7list projects
Provides an overview of every project currently set up in BugHerd.
019dd0c7list tasks
Lists all available tasks for a specific, defined project.
019dd0c7list users
Retrieves an account roster of every member attached to the BugHerd workspace.
019dd0c7update task
Changes key fields on a task, such as its status, priority, or assigned user.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with BugHerd, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,000+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Manually navigating bugs feels like a time sink.
Today, finding the full context on one bug means logging into BugHerd, searching for the project name, clicking through to the task ID, then opening the comment history tab. If you need to update the status or create a related ticket, you often have to switch out of that view and into another module entirely. It's constant clicks and copy-pasting just to get one picture.
With this MCP connection, you skip all those steps. You simply tell your agent what needs doing in plain English—like 'Mark task 456 as ready for QA.' The agent handles the internal navigation, running `update_task` and ensuring the status changes correctly without you touching a single button.
Using BugHerd's API through this MCP.
You don't have to worry about whether the project exists or if the task ID is correct. The system handles all that data lookup for you. You can also use `list_users` and assign ownership instantly, keeping your team accountable without ever leaving the chat.
It just works. Your agent becomes a natural extension of BugHerd's core functions, letting you manage every aspect of bug reporting from one conversation.
What you can do with this MCP connector
Debugging software shouldn't mean jumping between five different tabs and systems just to document an issue. This connector lets you manage the entire bug lifecycle right where you work. Your agent can list projects, create new tasks when you spot a bug, and pull up all the history on any specific ticket with one request.
Need to change something? You don't have to manually edit fields; your agent updates status, priority, or assignment using only natural language instructions. If you use Vinkius, you get this connection added right alongside thousands of other industry tools, making it a central source for all your development needs.
019dd0c7-8917-7368-bfa5-549f0f787bc1 
How BugHerd MCP Works
- 1 Install this MCP on your Vinkius platform and enter your personal BugHerd API key in the credentials.
- 2 Your agent reads your prompt, determines which tool is needed (e.g., 'get task'), and calls it automatically.
- 3 The agent processes the data returned from BugHerd and presents a plain-language summary of the bug's current status or history.
The bottom line is you tell your agent what to do in chat, and it handles all the back-and-forth with BugHerd itself.
Who Is BugHerd MCP For?
QA Engineers who are tired of copy-pasting ticket IDs into Slack threads; Development Leads who need real-time status checks across multiple projects; and Technical Product Managers who run bug triage sessions.
Needs to quickly list all open tasks, get a specific task's history, and add an immediate comment documenting the exact steps that caused a failure.
Uses the tool to check which projects exist, retrieve the details of a bug found in code review, and update its priority status when it's ready for testing.
Needs to list all active users on the team and pull up project summaries to report overall product health during sprint reviews.
What Changes When You Connect
- Stop context switching. Instead of logging into BugHerd to check a task's priority, you simply ask your agent to run the
get_tasktool, getting the current status right in your chat window. - Keep an auditable trail of decisions using
add_comment. When a developer fixes something, they can use your agent to add a detailed comment that instantly records their fix steps and links it directly to the task record. - When you need to start fresh, generating a new bug report is simple. Just ask your agent to run
create_taskand provide the details; it handles the ticket creation in BugHerd for you. - Never miss a project overview again. You can use
list_projectsorlist_tasksto get an instant snapshot of everything running, making sprint planning much faster than navigating dashboards. - Need to update something? Rather than figuring out which field ID needs changing, you just tell your agent the task's new status and priority, letting it handle the complex
update_taskfunction call.
Real-World Use Cases
Triage: A QA team member finds a regression bug.
The engineer asks their agent to create a new task for 'Login button fails on mobile Safari' in the main project. The agent uses create_task, then runs add_comment immediately to document which specific browser version failed and why.
Project Health Check: A PM wants an overall status report.
The Product Manager asks their agent to list all active projects, running list_projects, then requests the tasks for the highest priority project using list_tasks and finally gets a full user roster via list_users to see who owns which tickets.
Developer handoff: A fix is implemented.
The developer confirms the bug is fixed in staging. They tell their agent, 'Mark task 123 as resolved and assign it to QA.' The agent executes update_task immediately.
Deep dive: Investigating a complex failure.
Instead of digging into the BugHerd UI, the user asks their agent for all comments on task 456. The agent runs list_comments, providing a chronological feed of every discussion point that led to the final fix.
The Tradeoffs
Updating data without context
Trying to change a task's status just by saying 'Change it.' The agent can't know which task you mean, so the command fails.
→
Always start by using get_task or specifying the exact task ID. Once you have that context, your agent can use update_task to safely change the status.
Assuming project structure
Thinking there's only one place for bugs and trying to create a new task without defining a parent area.
→
First, run list_projects to see what workspaces are available. Then use the specific ID when running create_task so it lands in the right place.
Overlooking team members
Finding a bug and adding a comment, but forgetting who was supposed to own the fix.
→
Run list_users first. This gives you the roster of available teammates, so when you run update_task, you can assign it correctly.
When It Fits, When It Doesn't
Use this MCP if your primary pain point is managing complex, structured bug reports and task lifecycles—the kind that require tracking status changes, comments, and assigned users. You need to treat the ticket like a living document.
Don't use it if you just need simple checklists or generic resource management (like 'I need a list of documents'). In those cases, a general wiki or file repository tool is better. If your process involves complex approvals that require human sign-off in steps outside of BugHerd, you might need an external workflow automation tool instead. But for anything related to bug tracking and ticket status changes, this MCP is exactly what you need.
Common Questions About BugHerd MCP
How do I list all my projects using the `list_projects` tool? +
Just ask your agent to 'List all active BugHerd projects.' The MCP runs the list_projects function and gives you a clean, readable summary of every workspace available.
Can I update task details using the `update_task` tool? +
Yes. You tell your agent exactly what to change—for example, 'Change bug 789's priority to critical.' The MCP runs update_task, handling the API calls for you.
What is the best way to add notes on a task? Should I use `add_comment`? +
Yes, using add_comment is the right call. It ensures that your note is permanently attached to the specific bug task and visible in the official history.
How do I create a new ticket? Do I need `create_task`? +
Yep. Tell your agent, 'Create a new high-priority bug for the checkout page.' It runs create_task, generating the whole ticket and setting the initial details.
How do I get all details about a specific bug using the `get_task` tool? +
It fetches comprehensive data for one task ID. You retrieve everything—from its status and description to associated comments and members—in a single call. This is useful when you need a full snapshot of a reported issue.
If I need to see who works in my account, should I use the `list_users` tool? +
Yes, that's correct. The list_users tool pulls a roster of everyone associated with your BugHerd workspace. This lets your agent identify potential assignees or collaborators quickly.
How do I view all existing bugs within a project using the `list_tasks` tool? +
You use list_tasks to pull a list of every bug currently attached to a specific project. This is your primary way to audit and see all open items before you decide to create new ones or update status.
What happens if I try to create a new project with the `create_project` tool but it already exists? +
The tool handles duplicates gracefully by returning an appropriate error message. Your agent reads this feedback and can then suggest that you use the existing project ID instead.
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.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.