# Claude Code
Source: https://jira.xaviercollantes.dev/ai-tools/claude-code

Configure Claude Code CLI to use Jira MCP

Set up Jira MCP with Claude Code to manage Jira tickets directly from the command line using natural language.

## Prerequisites

* Claude Code CLI installed (`npm install -g @anthropic-ai/claude-code`)
* Active Claude subscription (Pro, Max, or API access)
* Jira MCP installed (see [Quickstart](/quickstart))
* jira-cli configured and authenticated

## Configuration

<Steps>
  <Step title="Locate Claude Code config">
    Claude Code stores its MCP configuration in `~/.claude/claude_desktop_config.json` or a similar location depending on your setup.
  </Step>

  <Step title="Add Jira MCP server">
    Add the following to your Claude Code MCP configuration:

    <Tabs>
      <Tab title="Binary installation">
        ```json theme={null}
        {
          "mcpServers": {
            "jira": {
              "command": "/usr/local/bin/jira-mcp",
              "env": {
                "JIRA_API_TOKEN": "your-api-token",
                "JIRA_AUTH_TYPE": "basic"
              }
            }
          }
        }
        ```

        <Note>
          Replace `/usr/local/bin/jira-mcp` with the actual path to your jira-mcp binary.
        </Note>
      </Tab>

      <Tab title="Development setup (uv)">
        ```json theme={null}
        {
          "mcpServers": {
            "jira": {
              "command": "uv",
              "args": ["--directory", "/ABSOLUTE/PATH/TO/jira-mcp", "run", "python", "-m", "src.main"],
              "env": {
                "JIRA_API_TOKEN": "your-api-token",
                "JIRA_AUTH_TYPE": "basic"
              }
            }
          }
        }
        ```

        <Note>
          Replace `/ABSOLUTE/PATH/TO/jira-mcp` with the actual path to your cloned repository.
        </Note>
      </Tab>
    </Tabs>
  </Step>

  <Step title="Restart Claude Code">
    Restart Claude Code to apply the changes.
  </Step>
</Steps>

## Usage examples

Once configured, you can interact with Jira using natural language:

* "Show me my assigned tickets"
* "Create a bug ticket for the login page issue"
* "Move PROJ-123 to In Progress"
* "Add a comment to PROJ-456 explaining the fix"
* "What tickets are in the current sprint?"

## Troubleshooting

<AccordionGroup>
  <Accordion title="MCP server not connecting">
    1. Verify the path to your jira-mcp binary is correct.
    2. Make sure jira-cli is properly configured by running `jira issue list` in your terminal.
    3. Check Claude Code's logs for error messages.
  </Accordion>

  <Accordion title="Authentication errors">
    Ensure your Jira credentials are set in the MCP configuration's `env` field:

    ```json theme={null}
    {
      "mcpServers": {
        "jira": {
          "command": "/usr/local/bin/jira-mcp",
          "env": {
            "JIRA_API_TOKEN": "your-api-token",
            "JIRA_AUTH_TYPE": "basic"
          }
        }
      }
    }
    ```

    <Note>
      GUI applications and CLI tools may not inherit shell environment variables from `.bashrc` or `.zshrc`. Using the `env` field in the MCP configuration is the recommended approach.
    </Note>
  </Accordion>
</AccordionGroup>


# Cursor
Source: https://jira.xaviercollantes.dev/ai-tools/cursor

Configure Cursor IDE to use Jira MCP

Set up Jira MCP in Cursor to manage Jira tickets directly from your IDE using natural language.

## Prerequisites

* Cursor IDE installed
* Jira MCP installed (see [Quickstart](/quickstart))
* jira-cli configured and authenticated

## Configuration

<Steps>
  <Step title="Open MCP settings">
    In Cursor, go to **Settings > MCP** or open the command palette and search for "MCP".
  </Step>

  <Step title="Add Jira MCP server">
    Add the following configuration to your MCP servers:

    <Tabs>
      <Tab title="Binary installation">
        ```json theme={null}
        {
          "mcpServers": {
            "jira": {
              "command": "/usr/local/bin/jira-mcp",
              "env": {
                "JIRA_API_TOKEN": "your-api-token",
                "JIRA_AUTH_TYPE": "basic"
              }
            }
          }
        }
        ```

        <Note>
          Replace `/usr/local/bin/jira-mcp` with the actual path to your jira-mcp binary.
        </Note>
      </Tab>

      <Tab title="Development setup (uv)">
        ```json theme={null}
        {
          "mcpServers": {
            "jira": {
              "command": "uv",
              "args": ["--directory", "/ABSOLUTE/PATH/TO/jira-mcp", "run", "python", "-m", "src.main"],
              "env": {
                "JIRA_API_TOKEN": "your-api-token",
                "JIRA_AUTH_TYPE": "basic"
              }
            }
          }
        }
        ```

        <Note>
          Replace `/ABSOLUTE/PATH/TO/jira-mcp` with the actual path to your cloned repository.
        </Note>
      </Tab>
    </Tabs>
  </Step>

  <Step title="Restart Cursor">
    Restart Cursor or reload the window to apply the changes.
  </Step>
</Steps>

## Usage examples

Once configured, you can interact with Jira using natural language in Cursor:

* "Show me my assigned tickets"
* "Create a bug ticket for the login page issue"
* "Move PROJ-123 to In Progress"
* "Add a comment to PROJ-456 explaining the fix"
* "What tickets are in the current sprint?"

## Troubleshooting

<AccordionGroup>
  <Accordion title="MCP server not connecting">
    1. Verify the path to your jira-mcp binary is correct.
    2. Make sure jira-cli is properly configured by running `jira issue list` in your terminal.
    3. Check Cursor's MCP logs for error messages.
  </Accordion>

  <Accordion title="Authentication errors">
    Ensure your Jira credentials are set in the MCP configuration's `env` field:

    ```json theme={null}
    {
      "mcpServers": {
        "jira": {
          "command": "/usr/local/bin/jira-mcp",
          "env": {
            "JIRA_API_TOKEN": "your-api-token",
            "JIRA_AUTH_TYPE": "basic"
          }
        }
      }
    }
    ```

    <Note>
      GUI applications like Cursor do not inherit shell environment variables from `.bashrc` or `.zshrc`. Using the `env` field in the MCP configuration is the recommended approach.
    </Note>
  </Accordion>
</AccordionGroup>


# Windsurf
Source: https://jira.xaviercollantes.dev/ai-tools/windsurf

Configure Windsurf to use Jira MCP

Set up Jira MCP in Windsurf to manage Jira tickets directly from your IDE using natural language with Cascade AI.

## Prerequisites

* Windsurf editor installed
* Jira MCP installed (see [Quickstart](/quickstart))
* jira-cli configured and authenticated

## Configuration

<Steps>
  <Step title="Open MCP settings">
    In Windsurf, go to **Settings > MCP** or open the command palette and search for "MCP".
  </Step>

  <Step title="Add Jira MCP server">
    Add the following configuration to your MCP servers:

    <Tabs>
      <Tab title="Binary installation">
        ```json theme={null}
        {
          "mcpServers": {
            "jira": {
              "command": "/usr/local/bin/jira-mcp",
              "env": {
                "JIRA_API_TOKEN": "your-api-token",
                "JIRA_AUTH_TYPE": "basic"
              }
            }
          }
        }
        ```

        <Note>
          Replace `/usr/local/bin/jira-mcp` with the actual path to your jira-mcp binary.
        </Note>
      </Tab>

      <Tab title="Development setup (uv)">
        ```json theme={null}
        {
          "mcpServers": {
            "jira": {
              "command": "uv",
              "args": ["--directory", "/ABSOLUTE/PATH/TO/jira-mcp", "run", "python", "-m", "src.main"],
              "env": {
                "JIRA_API_TOKEN": "your-api-token",
                "JIRA_AUTH_TYPE": "basic"
              }
            }
          }
        }
        ```

        <Note>
          Replace `/ABSOLUTE/PATH/TO/jira-mcp` with the actual path to your cloned repository.
        </Note>
      </Tab>
    </Tabs>
  </Step>

  <Step title="Restart Windsurf">
    Restart Windsurf or reload the window to apply the changes.
  </Step>
</Steps>

## Usage examples

Once configured, you can interact with Jira using natural language in Windsurf's Cascade AI:

* "Show me my assigned tickets"
* "Create a bug ticket for the login page issue"
* "Move PROJ-123 to In Progress"
* "Add a comment to PROJ-456 explaining the fix"
* "What tickets are in the current sprint?"

## Troubleshooting

<AccordionGroup>
  <Accordion title="MCP server not connecting">
    1. Verify the path to your jira-mcp binary is correct.
    2. Make sure jira-cli is properly configured by running `jira issue list` in your terminal.
    3. Check Windsurf's MCP logs for error messages.
  </Accordion>

  <Accordion title="Authentication errors">
    Ensure your Jira credentials are set in the MCP configuration's `env` field:

    ```json theme={null}
    {
      "mcpServers": {
        "jira": {
          "command": "/usr/local/bin/jira-mcp",
          "env": {
            "JIRA_API_TOKEN": "your-api-token",
            "JIRA_AUTH_TYPE": "basic"
          }
        }
      }
    }
    ```

    <Note>
      GUI applications like Windsurf do not inherit shell environment variables from `.bashrc` or `.zshrc`. Using the `env` field in the MCP configuration is the recommended approach.
    </Note>
  </Accordion>
</AccordionGroup>


# Contributing
Source: https://jira.xaviercollantes.dev/contributing

Help improve Jira MCP through bug reports, feature requests, and code contributions

## Ways to contribute

We welcome contributions from the community! Whether you're reporting a bug, suggesting a new feature, or helping with development, your input helps make Jira MCP better for everyone.

## Report issues and suggest features

<CardGroup>
  <Card title="Report a Bug" icon="bug" href="/report-bug">
    Found an issue? Help us fix it by providing detailed bug reports with
    reproduction steps.
  </Card>

  <Card title="Feature Request" icon="lightbulb" href="/feature-request">
    Have an idea for improvement? Suggest new features and enhancements to the
    project.
  </Card>
</CardGroup>

## Contribute code

Interested in contributing code to Jira MCP? Check out our [Development guide](/development) to get started with the codebase.

## Development contributions

Interested in contributing code? Check out our [Development guide](/development) to get started with the codebase.

## Community guidelines

* Be respectful and constructive in your communications
* Use clear, descriptive titles for issues
* Provide sufficient context and details
* Follow up on issues you've created if more information is requested
* Help others by sharing your experiences and solutions

## Get help

Need help or have questions? You can:

* Check the [documentation](/quickstart) for answers
* Search existing [issues](https://github.com/xcollantes/jira-mcp/issues) and [discussions](https://github.com/xcollantes/jira-mcp/discussions)
* Start a [new discussion](https://github.com/xcollantes/jira-mcp/discussions) for questions

Thank you for helping make Jira MCP better! 🚀


# Development
Source: https://jira.xaviercollantes.dev/development

Contribute to Jira MCP development

<Info>
  **Prerequisites**: - Python 3.11 or higher - UV package manager - jira-cli
  installed and configured
</Info>

## Getting started

Clone the repository and set up your development environment:

```bash theme={null}
git clone https://github.com/xcollantes/jira-mcp.git
cd jira-mcp
uv sync
```

## Pre-commit hooks

This project uses [pre-commit](https://pre-commit.com/) to run [ruff](https://docs.astral.sh/ruff/) linting and formatting checks, and [pytest](https://docs.pytest.org/) tests before each commit.

<Steps>
  <Step title="Install pre-commit hooks">
    ```bash theme={null}
    uv sync
    uv run pre-commit install
    ```
  </Step>

  <Step title="Run checks manually">
    Once installed, ruff and pytest will automatically run when you commit. To run checks manually on all files:

    ```bash theme={null}
    uv run pre-commit run --all-files
    ```
  </Step>
</Steps>

## Logging

<Warning>
  Do not use `print` statements for logging. Use the logging module instead.
  Writing to stdout will corrupt the JSON-RPC messages and break your server.
</Warning>

## Docstrings and tool decorators

MCP tools decorator parameters are especially important as this is the human-readable text that the LLM has context of. This will be treated as part of the prompt when fed to the LLM and this will decide when to use each tool.

## Troubleshooting

<AccordionGroup>
  <Accordion title="Edit the jira-cli config file">
    On macOS:

    ```text theme={null}
    /Users/<your-username>/.config/.jira/.config.yml
    ```
  </Accordion>

  <Accordion title="404 error when using jira init">
    If you get a 404 error when using `jira init`, you may need to edit the jira-cli config file to point to the correct Jira instance.

    There are only 3 possible values for the auth type, so try each one:

    * `basic`
    * `password`
    * `bearer`
  </Accordion>
</AccordionGroup>


# Feature Request
Source: https://jira.xaviercollantes.dev/feature-request

Suggest new features and improvements for Jira MCP

Have an idea for a new feature or improvement? We'd love to hear it! Feature requests help us understand what the community needs and prioritize our development efforts.

## Before suggesting

<Steps>
  <Step title="Check existing requests">
    Search [existing issues](https://github.com/xcollantes/jira-mcp/issues) with the "Enhancement" label to see if your idea has already been suggested. If it has, you can add your support and additional thoughts to the existing discussion.
  </Step>

  <Step title="Review the roadmap">
    Check if your suggestion aligns with our current development priorities or planned features.
  </Step>
</Steps>

## Submit a feature request

<Steps>
  <Step title="Open a new issue">
    [Create a new GitHub Issue](https://github.com/xcollantes/jira-mcp/issues/new) with the "Enhancement" label.
  </Step>

  <Step title="Use a descriptive title">
    Choose a clear, specific title that summarizes your suggestion, e.g., "Add
    support for bulk ticket updates" or "Implement dark mode for web interface".
  </Step>

  <Step title="Provide comprehensive details">
    ### Problem statement

    * **Current situation**: What's the problem or limitation you're facing?
    * **Impact**: How does this affect your workflow or productivity?
    * **Use case**: Provide a concrete example of when and how this feature would be used

    ### Proposed solution

    * **Description**: How should the new feature work?
    * **User experience**: What would the user interaction look like?
    * **Implementation approach**: If you have technical knowledge, suggest how this could be implemented

    ### Additional context

    * Screenshots, mockups, or diagrams if applicable
    * Any research or data supporting the need
  </Step>
</Steps>

## What makes a good feature request?

<Tip>
  **Pro tip**: Feature requests with detailed use cases, clear problem
  statements, and implementation ideas are more likely to be considered and
  implemented.
</Tip>


# Jira MCP - The Best MCP Server for Jira Integration
Source: https://jira.xaviercollantes.dev/index

The most powerful and feature-rich MCP server for Jira. Control Jira through AI-powered LLM clients like Cursor, Claude, and Windsurf using the Model Context Protocol.

<img alt="Claude Demo" />

<Note>
  **Safe for corporate environments.** This MCP server runs completely locally
  on your machine using the [jira-cli](https://github.com/ankitpokhrel/jira-cli)
  command line tool. No data is sent to third-party services. If your
  organization approves the use of jira-cli, on a technical level this MCP
  server is safe to use. *If in doubt, check with your IT department.*
</Note>

**Jira MCP is the best MCP server for Jira integration**, allowing AI assistants like Cursor, Claude Desktop, Windsurf, or ChatGPT to ask questions and perform actions with your Jira instance.

## Why Jira MCP?

<CardGroup>
  <Card title="Enterprise Ready" icon="building">
    Runs locally with no third-party data sharing. Safe for corporate environments.
  </Card>

  <Card title="Full-Featured" icon="sparkles">
    Complete Jira control: create, update, search, and manage tickets with natural language.
  </Card>

  <Card title="Easy Setup" icon="bolt">
    Pre-built binaries for all platforms. Get started in minutes, not hours.
  </Card>

  <Card title="Open Source" icon="code">
    MIT licensed and actively maintained. Contribute or customize as needed.
  </Card>
</CardGroup>

## Example prompts

<CardGroup>
  <Card title="Show tickets assigned to me with links and a summary of progress." icon="list-check" />

  <Card title="What's the link and status of that ticket with the new button feature?" icon="circle-question" />

  <Card title="Add a comment to PROJ-456 explaining the fix in my current branch." icon="comment" />

  <Card title="Add this spreadsheet of user stories as story issues to PROJ. Make the stories medium priority with a due date of 2 weeks from now." icon="file-import" />
</CardGroup>

## Get started

<Card title="Quickstart" icon="rocket" href="/quickstart">
  Install and configure Jira MCP in minutes.
</Card>

## Configure your AI tool

Set up Jira MCP with your preferred AI assistant.

<CardGroup>
  <Card title="Cursor" icon="arrow-pointer" href="/ai-tools/cursor">
    Configure Cursor IDE with Jira MCP.
  </Card>

  <Card title="Claude Code" icon="asterisk" href="/ai-tools/claude-code">
    Set up Claude Code CLI with Jira MCP.
  </Card>

  <Card title="Windsurf" icon="water" href="/ai-tools/windsurf">
    Configure Windsurf with Jira MCP.
  </Card>
</CardGroup>

## How it works

<Steps>
  <Step title="Prompt your AI assistant">
    You enter questions or commands to an LLM client such as Claude Desktop, Cursor, Windsurf, or ChatGPT.
  </Step>

  <Step title="LLM analyzes available tools">
    The LLM analyzes the available MCP tools and decides which one(s) to use. The
    LLM has context of each tool and what it is meant for in human language.
  </Step>

  <Step title="MCP server executes commands">
    The client executes the chosen tool(s) through the MCP server. The MCP server
    runs locally on your machine or remotely via an endpoint.
  </Step>

  <Step title="Results returned to LLM">
    The results are sent back to the LLM, which formulates a natural language response and displays data or performs actions using the MCP server.
  </Step>
</Steps>

## Architecture

MCP follows a client-server architecture where an **MCP host** (an AI application like Cursor or Claude Desktop) establishes connections to one or more **MCP servers**. The **MCP host** accomplishes this by creating one **MCP client** for each **MCP server**. Each MCP client maintains a dedicated connection with its corresponding MCP server.

<Card title="Learn more about MCP architecture" icon="diagram-project" href="https://modelcontextprotocol.io/docs/learn/architecture">
  Read the official MCP documentation for details on architecture.
</Card>


# Quickstart - Install Jira MCP
Source: https://jira.xaviercollantes.dev/quickstart

Get started with Jira MCP, the best MCP server for Jira integration. Install and configure in minutes on Linux, macOS, or Windows.

Get the best Jira MCP server up and running in just a few minutes. Jira MCP provides seamless AI-powered Jira integration for Cursor, Claude, Windsurf, and other LLM clients.

## Prerequisites

Before installing Jira MCP, you need to set up the Jira CLI that the MCP server uses to execute commands.

<Steps>
  <Step title="Install jira-cli">
    Follow the installation instructions for your operating system from the [jira-cli repository](https://github.com/ankitpokhrel/jira-cli?tab=readme-ov-file#installation).
  </Step>

  <Step title="Get Jira API credentials">
    Depending on your Jira implementation (Cloud or Self-Hosted), you will need to use a different authentication type.

    Add these to your `.bashrc`, `.zshrc`, or other shell configuration file:

    ```bash theme={null}
    # https://id.atlassian.com/manage-profile/security/api-tokens
    export JIRA_API_TOKEN=""

    # `bearer` for token,
    # `basic` for Jira account API token
    # `password` for Jira account password
    export JIRA_AUTH_TYPE="basic"
    ```

    Make sure to source the file after adding the credentials:

    ```bash theme={null}
    source ~/.bashrc
    ```

    <Note>
      See [alternative credential
      methods](https://github.com/ankitpokhrel/jira-cli/discussions/356) for other
      ways to configure authentication.
    </Note>

    <Warning>
      GUI applications like Cursor and Windsurf do not inherit shell environment
      variables from `.bashrc` or `.zshrc`. It is recommended to pass these
      variables explicitly in the MCP configuration using the `env` field (shown in
      the examples below).
    </Warning>
  </Step>

  <Step title="Initialize jira-cli">
    ```bash theme={null}
    jira init
    ```

    This will prompt you for your Jira URL and credentials.
  </Step>

  <Step title="Test jira-cli">
    ```bash theme={null}
    jira issue list
    ```

    This should return a list of issues in Jira.
  </Step>
</Steps>

## Install the MCP server

Choose your preferred installation method:

<Tabs>
  <Tab title="Download binary (Recommended)">
    Download the latest release for your operating system from the [Releases page](https://github.com/xcollantes/jira-mcp/releases).

    | Operating System      | Binary                               |
    | --------------------- | ------------------------------------ |
    | Linux                 | `jira-mcp-linux`                     |
    | Windows               | `jira-mcp-windows.exe`               |
    | macOS (Apple Silicon) | `jira-mcp-macos-apple-silicon-arm64` |
    | macOS (Intel)         | `jira-mcp-macos-x64`                 |

    <AccordionGroup>
      <Accordion title="Linux">
        ```bash theme={null}
        # Download the binary
        curl -L -o jira-mcp https://github.com/xcollantes/jira-mcp/releases/latest/download/jira-mcp-linux

        # Make it executable
        chmod +x jira-mcp

        # Move to a directory in your PATH (optional)
        sudo mv jira-mcp /usr/local/bin/
        ```

        Add to your LLM client configuration:

        ```json theme={null}
        {
          "mcpServers": {
            "jira": {
              "command": "/usr/local/bin/jira-mcp",
              "env": {
                "JIRA_API_TOKEN": "your-api-token",
                "JIRA_AUTH_TYPE": "basic"
              }
            }
          }
        }
        ```

        <Note>
          Replace `/usr/local/bin/jira-mcp` with the path to the binary on your machine
          if you moved it to a different location.
        </Note>
      </Accordion>

      <Accordion title="macOS">
        ```bash theme={null}
        # For Apple Silicon (M1/M2/M3)
        curl -L -o jira-mcp https://github.com/xcollantes/jira-mcp/releases/latest/download/jira-mcp-macos-apple-silicon-arm64

        # For Intel Macs
        curl -L -o jira-mcp https://github.com/xcollantes/jira-mcp/releases/latest/download/jira-mcp-macos-x64

        # Make it executable
        chmod +x jira-mcp

        # Move to a directory in your PATH (optional)
        sudo mv jira-mcp /usr/local/bin/
        ```

        <Warning>
          macOS may block the binary on first run. If you see a security warning, go to **System Settings > Privacy & Security** and click **Allow Anyway**, or run:

          ```bash theme={null}
          xattr -d com.apple.quarantine /usr/local/bin/jira-mcp
          ```
        </Warning>

        Add to your LLM client configuration:

        ```json theme={null}
        {
          "mcpServers": {
            "jira": {
              "command": "/usr/local/bin/jira-mcp",
              "env": {
                "JIRA_API_TOKEN": "your-api-token",
                "JIRA_AUTH_TYPE": "basic"
              }
            }
          }
        }
        ```

        <Note>
          Replace `/usr/local/bin/jira-mcp` with the path to the binary on your machine
          if you moved it to a different location.
        </Note>
      </Accordion>

      <Accordion title="Windows">
        1. Download `jira-mcp-windows.exe` from the [Releases page](https://github.com/xcollantes/jira-mcp/releases).
        2. Move the executable to a convenient location (e.g., `C:\Program Files\jira-mcp\`).

        Add to your LLM client configuration:

        ```json theme={null}
        {
          "mcpServers": {
            "jira": {
              "command": "C:\\Program Files\\jira-mcp\\jira-mcp-windows.exe",
              "env": {
                "JIRA_API_TOKEN": "your-api-token",
                "JIRA_AUTH_TYPE": "basic"
              }
            }
          }
        }
        ```

        <Note>
          Replace `C:\\Program Files\\jira-mcp\\jira-mcp-windows.exe` with the path to
          the binary on your machine if you moved it to a different location.
        </Note>
      </Accordion>
    </AccordionGroup>
  </Tab>

  <Tab title="Development setup with uv">
    Clone the repository:

    ```bash theme={null}
    git clone https://github.com/xcollantes/jira-mcp.git
    cd jira-mcp
    ```

    Add MCP server to your LLM client configuration:

    ```json theme={null}
    {
      "mcpServers": {
        "jira": {
          "command": "uv",
          "args": [
            "--directory",
            "/ABSOLUTE/PATH/TO/REPO/ROOT",
            "run",
            "python",
            "-m",
            "src.main"
          ],
          "env": {
            "JIRA_API_TOKEN": "your-api-token",
            "JIRA_AUTH_TYPE": "basic"
          }
        }
      }
    }
    ```

    This tells your LLM client that there is a tool that can be called by running `uv --directory /ABSOLUTE/PATH/TO/REPO run python -m src.main`.

    <Note>
      Install UV if you haven't already: [UV installation
      guide](https://docs.astral.sh/uv/getting-started/installation/)
    </Note>
  </Tab>

  <Tab title="Install globally with pipx">
    ```bash theme={null}
    # Install pipx if you haven't already
    brew install pipx
    pipx ensurepath

    # Clone and install the MCP server
    git clone https://github.com/xcollantes/jira-mcp.git
    cd jira-mcp
    pipx install -e .
    ```
  </Tab>
</Tabs>

## Next steps

<CardGroup>
  <Card title="Configure Cursor" icon="arrow-pointer" href="/ai-tools/cursor">
    Set up Jira MCP in Cursor IDE.
  </Card>

  <Card title="Configure Claude Code" icon="asterisk" href="/ai-tools/claude-code">
    Set up Jira MCP with Claude Code CLI.
  </Card>

  <Card title="Configure Windsurf" icon="water" href="/ai-tools/windsurf">
    Set up Jira MCP in Windsurf.
  </Card>

  <Card title="Development" icon="code" href="/development">
    Contribute to Jira MCP development.
  </Card>
</CardGroup>


# Report a Bug
Source: https://jira.xaviercollantes.dev/report-bug

Help us fix issues by reporting bugs with detailed information

Found a bug in Jira MCP? Help us improve by providing detailed information about the issue.

## Before reporting

<Steps>
  <Step title="Check for existing reports">
    Search [existing issues](https://github.com/xcollantes/jira-mcp/issues) to see if the bug has already been reported. If it has, you can add your experience to the existing discussion.
  </Step>

  <Step title="Update to latest version">
    Make sure you're using the latest version of Jira MCP. Bugs in older versions may already be fixed.
  </Step>
</Steps>

## Create a bug report

<Steps>
  <Step title="Open a new issue">
    [Create a new GitHub Issue](https://github.com/xcollantes/jira-mcp/issues/new) with the "Bug" label.
  </Step>

  <Step title="Use a clear title">
    Choose a descriptive title that summarizes the problem.
  </Step>

  <Step title="Provide detailed information">
    ### Description

    * **What happened**: Clear description of the bug
    * **When it happens**: Under what circumstances does this occur?
    * **Impact**: How does this affect your workflow?

    ### Steps to reproduce

    Provide step-by-step instructions to reproduce the issue:

    1. Step one
    2. Step two

    ### Expected behavior

    What should have happened instead?

    ### Environment

    * **OS**: (e.g., macOS 14.0, Windows 11, Ubuntu 22.04)
    * **Python version**: (e.g., Python 3.11.5)
    * **Jira MCP version**: (e.g., v1.2.0)
    * **AI tool**: (e.g., Cursor, Claude Desktop, Windsurf)
    * **Jira instance**: (e.g., Jira Cloud, Jira Server/Data Center)

    ### Logs and error messages

    Include any relevant error messages, logs, or stack traces. Remember to redact any sensitive information like API keys or personal data.

    ### Screenshots

    If applicable, include screenshots that demonstrate the issue.
  </Step>
</Steps>