mcp-server-sentry logo

mcp-server-sentry

by modelcontextprotocol

A Model Context Protocol server for retrieving and analyzing issues from Sentry.io. This server provides tools to inspect error reports, stacktraces, and other debugging information from your Sentry account.

View on GitHub

Last updated: N/A

What is mcp-server-sentry?

The mcp-server-sentry is a Model Context Protocol server designed to integrate with Sentry.io. It allows you to retrieve issue details, including stacktraces and other debugging information, directly from Sentry.

How to use mcp-server-sentry?

Install the server using either uv or pip as described in the installation instructions. Configure your Claude Desktop or Zed settings to use the server, providing your Sentry authentication token. Then, you can use the provided tools and prompts to retrieve and analyze Sentry issues.

Key features of mcp-server-sentry

  • Retrieves Sentry issue details by ID or URL

  • Provides full stacktrace information

  • Formats issue details for conversation context

  • Supports uv and pip installation methods

  • Integrates with Claude Desktop and Zed editors

Use cases of mcp-server-sentry

  • Quickly diagnose errors reported in Sentry

  • Provide error context in AI conversations

  • Integrate Sentry data into development workflows

  • Analyze error trends and patterns

FAQ from mcp-server-sentry

How do I install the mcp-server-sentry?

You can install it using either uv (recommended) or pip, as described in the 'Installation' section of the README.

How do I configure it to work with Claude Desktop?

Add the server configuration to your claude_desktop_config.json file, specifying the command and arguments (including your Sentry auth token).

How do I configure it to work with Zed?

Add the server configuration to your Zed settings.json file, specifying path to command and arguments (including your Sentry auth token).

What information does the server provide about Sentry issues?

The server returns details such as the issue title, ID, status, level, timestamps, event count, and the full stacktrace.

How do I debug the server?

Use the MCP inspector as described in the 'Debugging' section of the README, providing your Sentry auth token.