Sentry MCP server

This MCP server for Sentry enables AI models to retrieve and analyze error reports from the Sentry error tracking service. It provides tools to fetch detailed issue information by ID or URL, making it easy to incorporate error tracking data into your AI-powered workflows.

Installation

Install and build the server with npm:

# Install dependencies
npm install

# Build the project
npm run build

Configuration

The server requires configuration through environment variables. Create a .env file in the project root with these settings:

# Required: Sentry authentication token
SENTRY_AUTH_TOKEN=your_sentry_auth_token

# Optional: Sentry organization name
SENTRY_ORGANIZATION_SLUG=your_organization_slug

# Optional: Sentry project name
SENTRY_PROJECT_SLUG=your_project_slug

# Optional: Sentry base url
SENTRY_BASE_URL=https://sentry.com/api/0

Environment Variables Explained

• SENTRY_AUTH_TOKEN (required): Your Sentry API access token
• SENTRY_PROJECT_SLUG (optional): Your Sentry project's slug identifier
• SENTRY_ORGANIZATION_SLUG (optional): Your Sentry organization's slug identifier

Note: Project and organization information can be omitted if they're included in the URL you provide when using the tools.

Running the Server

Standard Execution

Run the server via standard IO:

node dist/index.js

Debugging

Debug with MCP Inspector:

npx @modelcontextprotocol/inspector node dist/index.js

Available Tools

get_sentry_issue Tool

This tool retrieves and analyzes Sentry issues by their ID or URL.

Input:

• issue_id_or_url (string): The Sentry issue ID or URL to analyze

Returns: Complete issue details including:

• Title
• Issue ID
• Status
• Level
• First seen timestamp
• Last seen timestamp
• Event count
• Complete stack trace

sentry-issue Prompt Template

This template fetches issue details from Sentry and returns them formatted as conversation context.

Input:

• issue_id_or_url (string): The Sentry issue ID or URL

Returns: Formatted issue details ready for use in conversation context

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.