Sentry MCP Server
Enable secure connectivity between Sentry issues and debugging data, and LLM clients, using a Model Context Protocol (MCP) server.
The Sentry MCP Server has been released for production, however MCP is a developing technology and changes should be expected. There will be bugs. Please reach out on GitHub if you have any feedback or concerns.
The Sentry MCP Server connects your LLM client to Sentry using the Model Context Protocol (MCP), giving your AI tools direct access to issues, errors, projects, and Seer analysis. Sentry hosts and manages a remote MCP server with OAuth authentication, so there's nothing to install.
Add the Sentry MCP server to your client with this configuration:
{
"mcpServers": {
"Sentry": {
"url": "https://mcp.sentry.dev/mcp"
}
}
}
Most clients support the OAuth configuration. When you first connect, you'll be prompted to:
- Log in with your Sentry organization
- Accept the OAuth authorization
- Grant access to the necessary permissions
Once authenticated, all 16+ tools become available in your client.
If you've joined a new Sentry organization, log out of your LLM's MCP integration and log back in to refresh access.
Select your client below for specific setup instructions. All clients use the remote OAuth server at https://mcp.sentry.dev/mcp unless noted otherwise.
The Sentry MCP page provides a web-based interface where you can authenticate with your Sentry organization and test the MCP server directly in your browser.
Once connected, try these prompts to start using Sentry context in your LLM:
- Tell me about the issues in my
project-name - Check Sentry for errors in
components/UserProfile.tsxand propose solutions - Diagnose issue
PROJECT-123and propose solutions - Create a new project in Sentry for
new-service-nameand set up local instrumentation - Use Sentry's Seer to analyze and propose a solution for issue
PROJECT-456 - Show me the most recent releases for my organization
- Find all unresolved crashes in my React Native app
The Sentry MCP Server provides 16+ tools for interacting with Sentry data:
Core Tools — Organizations, Projects, Teams, Issues, and DSN management
Analysis Tools — Error searching across files and projects, detailed issue investigation, and Seer integration for AI-powered root cause analysis
Advanced Features — Release management, performance monitoring, and custom queries
The Sentry MCP Server provides seamless integration with Seer, Sentry's AI agent. Through MCP, you can trigger Seer analysis, get AI-generated fix recommendations, and monitor fix status — all from within your LLM client.
MCP and Seer are complementary tools. MCP brings Sentry context into your LLM, while Seer is purpose-built for deep issue analysis and automated debugging. Use MCP to invoke Seer for complex debugging workflows.
OAuth Authentication Problems
- Ensure your client supports OAuth authentication
- Check that you have the necessary permissions in your Sentry organization
- Try logging out of the MCP integration and logging back in
Connection Issues
- Verify the MCP server URL is correct:
https://mcp.sentry.dev/mcp - Check your client's MCP configuration syntax
Missing Tools
- Ensure authentication completed successfully
- Verify your Sentry organization access
- Check for error messages in your client's console
For additional support, visit the GitHub repository or contact Sentry support.
Our documentation is open source and available on GitHub. Your contributions are welcome, whether fixing a typo (drat!) or suggesting an update ("yeah, this would be better").