Sentry

Retrieving and analyzing issues from Sentry.io

Catalog onlyCatalog onlySTDIO

Overview

Sentry is a Model Context Protocol server designed for retrieving and analyzing issues from Sentry.io. It enables developers to inspect error reports, stack traces, and debugging information efficiently.

To use Sentry, install it via pip or the recommended uv tool, set your Sentry authentication token, and invoke it through command line or integration in development environments like Claude Desktop or Zed.

Retrieve and analyze Sentry issues by ID or URL. - Detailed insights into issue including title, status, timestamps, and stack traces. - Support for debugging with the MCP inspector.

Analyzing application errors in real-time.
Retrieving historical error reports for diagnostics.
Debugging and improving application reliability by inspecting stack traces.

Tools

get_sentry_issue

issue_id_or_url

Retrieve and analyze a Sentry issue by ID or URL. Use this tool when you need to: - Investigate production errors and crashes - Access detailed stacktraces from Sentry - Analyze error patterns and frequencies - Get information about when issues first/last occurred - Review error counts and status

Last seen Apr 5, 2026

Add to your AI client

Use these steps to connect Sentry in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "sentry-modelcontextprotocol": {
      "command": "uvx",
      "args": [
        "mcp-server-sentry",
        "--auth-token",
        "YOUR_SENTRY_TOKEN"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "sentry-modelcontextprotocol": {
      "command": "uvx",
      "args": [
        "mcp-server-sentry",
        "--auth-token",
        "YOUR_SENTRY_TOKEN"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "sentry-modelcontextprotocol": {
      "command": "uvx",
      "args": [
        "mcp-server-sentry",
        "--auth-token",
        "YOUR_SENTRY_TOKEN"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "sentry-modelcontextprotocol": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-server-sentry",
        "--auth-token",
        "YOUR_SENTRY_TOKEN"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "sentry-modelcontextprotocol": {
      "command": "uvx",
      "args": [
        "mcp-server-sentry",
        "--auth-token",
        "YOUR_SENTRY_TOKEN"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "sentry-modelcontextprotocol": {
      "command": "uvx",
      "args": [
        "mcp-server-sentry",
        "--auth-token",
        "YOUR_SENTRY_TOKEN"
      ]
    }
  }
}

FAQ

How do I install Sentry?

You can install Sentry via pip using the command 'pip install mcp-server-sentry' or by using the uv tool.

What programming languages does Sentry support?

Sentry can be used with any programming language that can communicate with Sentry.io, as it primarily retrieves data from the Sentry API.

Is there support for multiple Sentry projects?

Yes, Sentry can handle multiple projects as long as you provide the corresponding authentication token for each project.

Research and data