# BugHerd MCP MCP > 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. ## Overview - **Category:** developer-tools - **Price:** Free - **Tags:** bug-tracking, website-feedback, task-management, issue-reporting, collaboration, project-tracking ## Description 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. ## Tools ### 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. ### get_project Retrieves all the core information for one specific BugHerd project. ### get_task Pulls up the complete details and current status of a single bug task. ### list_comments Fetches all comments left on a particular bug task, giving you full context. ### list_projects Provides an overview of every project currently set up in BugHerd. ### list_tasks Lists all available tasks for a specific, defined project. ### list_users Retrieves an account roster of every member attached to the BugHerd workspace. ### update_task Changes key fields on a task, such as its status, priority, or assigned user. ## Prompt Examples **Prompt:** ``` List all active projects in BugHerd. ``` **Response:** ``` Here are your active BugHerd projects... ``` **Prompt:** ``` Create a new bug task in project 123 saying 'Login button is broken'. ``` **Response:** ``` I've successfully created the new bug task for the broken login button. ``` **Prompt:** ``` Read the comments on task 456 in project 123. ``` **Response:** ``` Fetching comments for task 456... ``` ## Capabilities ### Manage projects Create new BugHerd workspaces or retrieve details about existing ones. ### Handle tasks and bugs Generate, list, or pull detailed information on specific bug reports and project tickets. ### Change ticket status Update a task's description, priority, or assignee using natural language commands. ### View conversation history Fetch and list all comments associated with any bug task for full context. ### Identify team members List all users currently active within the BugHerd workspace. ## 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. ## Benefits - Stop context switching. Instead of logging into BugHerd to check a task's priority, you simply ask your agent to run the `get_task` tool, 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_task` and provide the details; it handles the ticket creation in BugHerd for you. - Never miss a project overview again. You can use `list_projects` or `list_tasks` to 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_task` function call. ## How It Works The bottom line is you tell your agent what to do in chat, and it handles all the back-and-forth with BugHerd itself. 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. ## Frequently Asked Questions **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.