# How to integrate Bugherd MCP with Pydantic AI ```json { "title": "How to integrate Bugherd MCP with Pydantic AI", "toolkit": "Bugherd", "toolkit_slug": "bugherd", "framework": "Pydantic AI", "framework_slug": "pydantic-ai", "url": "https://composio.dev/toolkits/bugherd/framework/pydantic-ai", "markdown_url": "https://composio.dev/toolkits/bugherd/framework/pydantic-ai.md", "updated_at": "2026-05-12T10:04:27.667Z" } ``` ## Introduction This guide walks you through connecting Bugherd to Pydantic AI using the Composio tool router. By the end, you'll have a working Bugherd agent that can list all active bugherd projects, create a new project for website feedback, add a comment to task by id through natural language commands. This guide will help you understand how to give your Pydantic AI agent real control over a Bugherd account through Composio's Bugherd MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Bugherd with - [OpenAI Agents SDK](https://composio.dev/toolkits/bugherd/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/bugherd/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/bugherd/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/bugherd/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/bugherd/framework/codex) - [OpenClaw](https://composio.dev/toolkits/bugherd/framework/openclaw) - [Hermes](https://composio.dev/toolkits/bugherd/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/bugherd/framework/cli) - [Google ADK](https://composio.dev/toolkits/bugherd/framework/google-adk) - [LangChain](https://composio.dev/toolkits/bugherd/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/bugherd/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/bugherd/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/bugherd/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/bugherd/framework/crew-ai) ## TL;DR Here's what you'll learn: - How to set up your Composio API key and User ID - How to create a Composio Tool Router session for Bugherd - How to attach an MCP Server to a Pydantic AI agent - How to stream responses and maintain chat history - How to build a simple REPL-style chat interface to test your Bugherd workflows ## What is Pydantic AI? Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications. Key features include: - Type Safety: Built on Pydantic for automatic data validation - MCP Support: Native support for Model Context Protocol servers - Streaming: Built-in support for streaming responses - Async First: Designed for async/await patterns ## What is the Bugherd MCP server, and what's possible with it? The Bugherd MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Bugherd account. It provides structured and secure access to your Bugherd workspace, so your agent can perform actions like creating tasks, managing projects, posting comments, and inviting team members—all on your behalf. - Visual bug reporting and task creation: Instantly add new tasks to any project, capturing detailed bug reports or website feedback directly from your team or clients. - Project management and workflow customization: Create new projects, add workflow columns, and delete projects when they’re no longer needed to keep your bug tracking organized and up-to-date. - Collaboration and discussion: Add comments to tasks, attach files, and keep all stakeholders in the loop with contextual feedback and documentation. - Team and guest access management: Seamlessly invite members or guests to projects so the right people can track, manage, and resolve issues together. - Webhook automation and notifications: Set up webhooks to receive real-time notifications for events like task creation or new comments, helping you automate downstream workflows. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `BUGHERD_ADD_GUEST_TO_PROJECT` | Add Guest to Project | Tool to add a guest (client) to a project. Use when you want to add an existing client by ID or invite a new client by email. | | `BUGHERD_ADD_MEMBER_TO_PROJECT` | Add Member to Project | Tool to add a member to a project in BugHerd. Use when you need to add an existing user to a specific project. | | `BUGHERD_CREATE_ATTACHMENT` | Create Attachment | Tool to add a new attachment to a task using an existing URL. Use when you have project and task IDs and the external file URL ready. | | `BUGHERD_CREATE_COLUMN` | Create Column | Tool to create a new column in a project. Use when you need to add a custom workflow column after identifying the project ID. | | `BUGHERD_CREATE_COMMENT` | Create Comment | Tool to add a new comment to a task. Use when you need to record discussion or feedback on an existing task. | | `BUGHERD_CREATE_PROJECT` | Create Project | Tool to create a new project. Use when you need to initialize a project after gathering its name and URL. Example: "Create a new project named 'My Website' with URL 'http://www.example.com'." | | `BUGHERD_CREATE_TASK` | Create Task | Tool to add a new task in a project. Use when you have the project ID and full task details ready. | | `BUGHERD_CREATE_WEBHOOK` | Create Webhook | Tool to create a new webhook for real-time event notifications. Use when you need to configure a callback endpoint for task or comment events. Example: "Create a webhook for 'task_create' events to be sent to 'https://example.com/webhook'." | | `BUGHERD_DELETE_PROJECT` | Delete Project | Tool to delete a project. Use when you need to permanently remove a project and its associated data. This action cannot be undone, so confirm the project ID before calling. | | `BUGHERD_LIST_ACTIVE_PROJECTS` | List Active Projects | Tool to list all active projects in your BugHerd account. Use when you need to retrieve the active projects list (e.g., for syncing or reporting). | | `BUGHERD_LIST_ATTACHMENTS` | List Attachments | Tool to list all attachments for a task. Use when you need to retrieve file attachments after fetching task details. | | `BUGHERD_LIST_COLUMNS` | List Columns | Tool to list all columns for a project. Use when you need the full set of default and custom columns for a project. | | `BUGHERD_LIST_PROJECTS` | List Projects | Retrieves a paginated list of all projects in your BugHerd account. Returns project details including ID, name, creation date, owner, task status, and associated website URLs. Results are paginated with up to 100 projects per page. Use the meta.count field to determine the total number of projects. | | `BUGHERD_LIST_PROJECT_TASKS` | List Project Tasks | Tool to list tasks within a specific BugHerd project with optional server-side filters (status/column, assignee, tag, priority, date filters) and pagination. Use when you need to retrieve tasks scoped to a single project. | | `BUGHERD_LIST_USERS` | List Users | Tool to list all users in your account. Use after authenticating to fetch the current user roster. Supports pagination via the `page` parameter. | | `BUGHERD_LIST_WEBHOOKS` | List Webhooks | Tool to list all installed webhooks. Use when you need to audit or verify existing webhooks after setup. | | `BUGHERD_SHOW_ATTACHMENT` | Show Attachment | Tool to retrieve details of a specific attachment. Use after you have project_id, task_id, and attachment_id to get filename, URL, and timestamps. | | `BUGHERD_SHOW_COLUMN` | Show Column | Tool to show details of a specific column. Use when you need metadata for a particular column within a project. | | `BUGHERD_SHOW_ORGANIZATION` | Show Organization | Tool to retrieve your BugHerd organization details. Use after authenticating to fetch account metadata. | | `BUGHERD_SHOW_PROJECT` | Show Project Details | Retrieves full details of a specific BugHerd project by ID. Returns comprehensive project information including name, settings, team members, guests, and kanban columns. Use this when you need detailed project data such as member lists, workflow columns, or project configuration settings. Requires a valid project_id obtained from list_projects or another source. | | `BUGHERD_SHOW_USER_PROJECTS` | Show User Projects | Tool to list all projects a specific user has access to. Use after obtaining the user's ID. | | `BUGHERD_SHOW_USER_TASKS` | Show User Tasks | Retrieves all tasks created by or assigned to a specific user, grouped by project. Returns task details including ID, description, priority, status, timestamps, and tags. Requires a valid user_id (obtain from List Users action). Supports pagination via page parameter. | | `BUGHERD_UPDATE_COLUMN` | Update Column | Tool to update a column in a project. Use when you have the project and column IDs and need to rename a column. Use after confirming the correct IDs. | | `BUGHERD_UPDATE_PROJECT` | Update Project | Update settings for an existing BugHerd project. Use this to modify a project's name, URL, visibility settings, or guest permissions. Prerequisites: You need a valid project_id. Use list_projects to find existing project IDs, or create_project to create a new one. Note: Only include fields you want to change - omitted fields will retain their current values. | | `BUGHERD_UPDATE_TASK` | Update Task | Tool to update a task in a project. Use after confirming the project and task IDs. | | `BUGHERD_UPLOAD_ATTACHMENT` | Upload Attachment | Tool to upload a new attachment and add it to a specific task. Use when you have binary file content ready and need to attach it to a BugHerd task. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Bugherd MCP server is an implementation of the Model Context Protocol that connects your AI agent to Bugherd. It provides structured and secure access so your agent can perform Bugherd operations on your behalf through a secure, permission-based interface. With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster. ## Step-by-step Guide ### 1. Prerequisites Before starting, make sure you have: - Python 3.9 or higher - A Composio account with an active API key - Basic familiarity with Python and async programming ### 1. Getting API Keys for OpenAI and Composio OpenAI API Key - Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) and create an API key. You'll need credits to use the models, or you can connect to another model provider. - Keep the API key safe. Composio API Key - Log in to the [Composio dashboard](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs). - Navigate to your API settings and generate a new API key. - Store this key securely as you'll need it for authentication. ### 2. Install dependencies Install the required libraries. What's happening: - composio connects your agent to external SaaS tools like Bugherd - pydantic-ai lets you create structured AI agents with tool support - python-dotenv loads your environment variables securely from a .env file ```bash pip install composio pydantic-ai python-dotenv ``` ### 3. Set up environment variables Create a .env file in your project root. What's happening: - COMPOSIO_API_KEY authenticates your agent to Composio's API - USER_ID associates your session with your account for secure tool access - OPENAI_API_KEY to access OpenAI LLMs ```bash COMPOSIO_API_KEY=your_composio_api_key_here USER_ID=your_user_id_here OPENAI_API_KEY=your_openai_api_key ``` ### 4. Import dependencies What's happening: - We load environment variables and import required modules - Composio manages connections to Bugherd - MCPServerStreamableHTTP connects to the Bugherd MCP server endpoint - Agent from Pydantic AI lets you define and run the AI assistant ```python import asyncio import os from dotenv import load_dotenv from composio import Composio from pydantic_ai import Agent from pydantic_ai.mcp import MCPServerStreamableHTTP load_dotenv() ``` ### 5. Create a Tool Router Session What's happening: - We're creating a Tool Router session that gives your agent access to Bugherd tools - The create method takes the user ID and specifies which toolkits should be available - The returned session.mcp.url is the MCP server URL that your agent will use ```python async def main(): api_key = os.getenv("COMPOSIO_API_KEY") user_id = os.getenv("USER_ID") if not api_key or not user_id: raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment") # Create a Composio Tool Router session for Bugherd composio = Composio(api_key=api_key) session = composio.create( user_id=user_id, toolkits=["bugherd"], ) url = session.mcp.url if not url: raise ValueError("Composio session did not return an MCP URL") ``` ### 6. Initialize the Pydantic AI Agent What's happening: - The MCP client connects to the Bugherd endpoint - The agent uses GPT-5 to interpret user commands and perform Bugherd operations - The instructions field defines the agent's role and behavior ```python # Attach the MCP server to a Pydantic AI Agent bugherd_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY}) agent = Agent( "openai:gpt-5", toolsets=[bugherd_mcp], instructions=( "You are a Bugherd assistant. Use Bugherd tools to help users " "with their requests. Ask clarifying questions when needed." ), ) ``` ### 7. Build the chat interface What's happening: - The agent reads input from the terminal and streams its response - Bugherd API calls happen automatically under the hood - The model keeps conversation history to maintain context across turns ```python # Simple REPL with message history history = [] print("Chat started! Type 'exit' or 'quit' to end.\n") print("Try asking the agent to help you with Bugherd.\n") while True: user_input = input("You: ").strip() if user_input.lower() in {"exit", "quit", "bye"}: print("\nGoodbye!") break if not user_input: continue print("\nAgent is thinking...\n", flush=True) async with agent.run_stream(user_input, message_history=history) as stream_result: collected_text = "" async for chunk in stream_result.stream_output(): text_piece = None if isinstance(chunk, str): text_piece = chunk elif hasattr(chunk, "delta") and isinstance(chunk.delta, str): text_piece = chunk.delta elif hasattr(chunk, "text"): text_piece = chunk.text if text_piece: collected_text += text_piece result = stream_result print(f"Agent: {collected_text}\n") history = result.all_messages() ``` ### 8. Run the application What's happening: - The asyncio loop launches the agent and keeps it running until you exit ```python if __name__ == "__main__": asyncio.run(main()) ``` ## Complete Code ```python import asyncio import os from dotenv import load_dotenv from composio import Composio from pydantic_ai import Agent from pydantic_ai.mcp import MCPServerStreamableHTTP load_dotenv() async def main(): api_key = os.getenv("COMPOSIO_API_KEY") user_id = os.getenv("USER_ID") if not api_key or not user_id: raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment") # Create a Composio Tool Router session for Bugherd composio = Composio(api_key=api_key) session = composio.create( user_id=user_id, toolkits=["bugherd"], ) url = session.mcp.url if not url: raise ValueError("Composio session did not return an MCP URL") # Attach the MCP server to a Pydantic AI Agent bugherd_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY}) agent = Agent( "openai:gpt-5", toolsets=[bugherd_mcp], instructions=( "You are a Bugherd assistant. Use Bugherd tools to help users " "with their requests. Ask clarifying questions when needed." ), ) # Simple REPL with message history history = [] print("Chat started! Type 'exit' or 'quit' to end.\n") print("Try asking the agent to help you with Bugherd.\n") while True: user_input = input("You: ").strip() if user_input.lower() in {"exit", "quit", "bye"}: print("\nGoodbye!") break if not user_input: continue print("\nAgent is thinking...\n", flush=True) async with agent.run_stream(user_input, message_history=history) as stream_result: collected_text = "" async for chunk in stream_result.stream_output(): text_piece = None if isinstance(chunk, str): text_piece = chunk elif hasattr(chunk, "delta") and isinstance(chunk.delta, str): text_piece = chunk.delta elif hasattr(chunk, "text"): text_piece = chunk.text if text_piece: collected_text += text_piece result = stream_result print(f"Agent: {collected_text}\n") history = result.all_messages() if __name__ == "__main__": asyncio.run(main()) ``` ## Conclusion You've built a Pydantic AI agent that can interact with Bugherd through Composio's Tool Router. With this setup, your agent can perform real Bugherd actions through natural language. You can extend this further by: - Adding other toolkits like Gmail, HubSpot, or Salesforce - Building a web-based chat interface around this agent - Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Bugherd for workflow automation) This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations. ## How to build Bugherd MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/bugherd/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/bugherd/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/bugherd/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/bugherd/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/bugherd/framework/codex) - [OpenClaw](https://composio.dev/toolkits/bugherd/framework/openclaw) - [Hermes](https://composio.dev/toolkits/bugherd/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/bugherd/framework/cli) - [Google ADK](https://composio.dev/toolkits/bugherd/framework/google-adk) - [LangChain](https://composio.dev/toolkits/bugherd/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/bugherd/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/bugherd/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/bugherd/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/bugherd/framework/crew-ai) ## Related Toolkits - [Google Sheets](https://composio.dev/toolkits/googlesheets) - Google Sheets is a cloud-based spreadsheet tool for real-time collaboration and data analysis. It lets teams work together from anywhere, updating information instantly. - [Notion](https://composio.dev/toolkits/notion) - Notion is a collaborative workspace for notes, docs, wikis, and tasks. It streamlines team knowledge, project tracking, and workflow customization in one place. - [Airtable](https://composio.dev/toolkits/airtable) - Airtable combines the flexibility of spreadsheets with the power of a database for easy project and data management. Teams use Airtable to organize, track, and collaborate with custom views and automations. - [Asana](https://composio.dev/toolkits/asana) - Asana is a collaborative work management platform for teams to organize and track projects. It streamlines teamwork, boosts productivity, and keeps everyone aligned on goals. - [Google Tasks](https://composio.dev/toolkits/googletasks) - Google Tasks is a to-do list and task management tool integrated into Gmail and Google Calendar. It helps you organize, track, and complete tasks across your Google ecosystem. - [Linear](https://composio.dev/toolkits/linear) - Linear is a modern issue tracking and project planning tool for fast-moving teams. It helps streamline workflows, organize projects, and boost productivity. - [Jira](https://composio.dev/toolkits/jira) - Jira is Atlassian’s platform for bug tracking, issue tracking, and agile project management. It helps teams organize work, prioritize tasks, and deliver projects efficiently. - [Clickup](https://composio.dev/toolkits/clickup) - ClickUp is an all-in-one productivity platform for managing tasks, docs, goals, and team collaboration. It streamlines project workflows so teams can work smarter and stay organized in one place. - [Monday](https://composio.dev/toolkits/monday) - Monday.com is a customizable work management platform for project planning and collaboration. It helps teams organize tasks, automate workflows, and track progress in real time. - [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time. - [Agiled](https://composio.dev/toolkits/agiled) - Agiled is an all-in-one business management platform for CRM, projects, and finance. It helps you streamline workflows, consolidate client data, and manage business processes in one place. - [Ascora](https://composio.dev/toolkits/ascora) - Ascora is a cloud-based field service management platform for service businesses. It streamlines scheduling, invoicing, and customer operations in one place. - [Basecamp](https://composio.dev/toolkits/basecamp) - Basecamp is a project management and team collaboration tool by 37signals. It helps teams organize tasks, share files, and communicate efficiently in one place. - [Beeminder](https://composio.dev/toolkits/beeminder) - Beeminder is an online goal-tracking platform that uses monetary pledges to keep you motivated. Stay accountable and hit your targets with real financial incentives. - [Boxhero](https://composio.dev/toolkits/boxhero) - Boxhero is a cloud-based inventory management platform for SMBs, offering real-time updates, barcode scanning, and team collaboration. It helps businesses streamline stock tracking and analytics for smarter inventory decisions. - [Breathe HR](https://composio.dev/toolkits/breathehr) - Breathe HR is cloud-based HR software for SMEs to manage employee data, absences, and performance. It simplifies HR admin, making it easy to keep employee records accurate and up to date. - [Breeze](https://composio.dev/toolkits/breeze) - Breeze is a project management platform designed to help teams plan, track, and collaborate on projects. It streamlines workflows and keeps everyone on the same page. - [Canny](https://composio.dev/toolkits/canny) - Canny is a platform for managing customer feedback and feature requests. It helps teams prioritize product decisions based on real user insights. - [Chmeetings](https://composio.dev/toolkits/chmeetings) - Chmeetings is a church management platform for events, members, donations, and volunteers. It streamlines church operations and improves community engagement. - [ClickSend](https://composio.dev/toolkits/clicksend) - ClickSend is a cloud-based SMS and email marketing platform for businesses. It streamlines communication by enabling quick message delivery and contact management. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Bugherd MCP? With a standalone Bugherd MCP server, the agents and LLMs can only access a fixed set of Bugherd tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Bugherd and many other apps based on the task at hand, all through a single MCP endpoint. ### Can I use Tool Router MCP with Pydantic AI? Yes, you can. Pydantic AI fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Bugherd tools. ### Can I manage the permissions and scopes for Bugherd while using Tool Router? Yes, absolutely. You can configure which Bugherd scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do. ### How safe is my data with Composio Tool Router? All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Bugherd data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)