Sentry
A remote Model Context Protocol server acting as middleware to the Sentry API, allowing AI assistants like Claude to access Sentry data and functionality through natural language interfaces.
What is Sentry?
Sentry is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to remote model context protocol server acting as middleware to the sentry api, allowing ai assistants like claude to access sentry data and functionality through natural language interfaces.
A remote Model Context Protocol server acting as middleware to the Sentry API, allowing AI assistants like Claude to access Sentry data and functionality through natural language interfaces.
This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A remote Model Context Protocol server acting as middleware
Use Cases
Maintainer
Works with
Installation
NPM
npx -y @sentry/mcp-serverManual Installation
npx -y @sentry/mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Sentry
The Sentry MCP server is the official MCP integration maintained by Sentry, acting as middleware between AI assistants and the Sentry error-monitoring platform. It allows Claude and other AI agents to search issues, inspect error events and stack traces, analyze performance data, and query Sentry's AI-powered Seer feature through natural language. Teams use it to accelerate debugging by letting AI assistants pull live production error data directly into the conversation.
Prerequisites
- A Sentry account with at least one project (sentry.io or self-hosted)
- A Sentry user authentication token with appropriate scopes (generated at sentry.io/settings/account/api/auth-tokens/)
- Node.js 18+ installed (for the npx transport option)
- An MCP client such as Claude Desktop, Claude Code, or Cursor
- Optional: OpenAI or Anthropic API key if you want Sentry's AI-powered search (Seer) features
Generate a Sentry authentication token
Navigate to sentry.io → Settings → Account → API → Auth Tokens and create a new token. The token needs read access to issues, events, and projects.
Install via Claude Code plugin marketplace (easiest)
If you use Claude Code, install the Sentry MCP plugin directly from the marketplace.
claude plugin marketplace add getsentry/sentry-mcp
claude plugin install sentry-mcp@sentry-mcpOr run as a stdio server with npx
For Claude Desktop or other MCP clients, run the server using npx and pass your access token. For self-hosted Sentry, add the --host flag.
# Sentry.io (cloud)
npx @sentry/mcp-server@latest --access-token=YOUR_SENTRY_TOKEN
# Self-hosted Sentry
npx @sentry/mcp-server@latest --access-token=YOUR_SENTRY_TOKEN --host=sentry.example.com
# Self-hosted with HTTP only
npx @sentry/mcp-server@latest --access-token=YOUR_SENTRY_TOKEN --host=sentry.internal:9000 --insecure-httpConfigure Claude Desktop
Add the Sentry MCP server to your Claude Desktop configuration file.
{
"mcpServers": {
"sentry": {
"command": "npx",
"args": ["@sentry/mcp-server@latest"],
"env": {
"SENTRY_ACCESS_TOKEN": "your-sentry-token"
}
}
}
}Enable AI-powered Seer search (optional)
To use Sentry's Seer AI search features, provide an LLM API key. Set EMBEDDED_AGENT_PROVIDER to 'openai' or 'anthropic' and the corresponding key.
{
"mcpServers": {
"sentry": {
"command": "npx",
"args": ["@sentry/mcp-server@latest"],
"env": {
"SENTRY_ACCESS_TOKEN": "your-sentry-token",
"EMBEDDED_AGENT_PROVIDER": "anthropic",
"ANTHROPIC_API_KEY": "your-anthropic-key"
}
}
}
}Restart your MCP client and verify
Restart Claude Desktop or your MCP client. Ask a question about a Sentry project to confirm the integration is working.
Sentry Examples
Client configuration
Minimal Claude Desktop configuration for the Sentry MCP server using the stdio transport.
{
"mcpServers": {
"sentry": {
"command": "npx",
"args": ["@sentry/mcp-server@latest"],
"env": {
"SENTRY_ACCESS_TOKEN": "your-sentry-token"
}
}
}
}Prompts to try
Use these prompts to interact with Sentry data through Claude:
- "Show me the top 5 unresolved errors in my production environment from the last 24 hours"
- "Search Sentry for issues related to 'database connection timeout' in the backend project"
- "What is the full stack trace for Sentry issue PROJ-1234?"
- "Are there any performance regressions in the checkout flow this week?"
- "Summarize the recurring errors in my iOS app and suggest likely root causes"Troubleshooting Sentry
Authentication errors: 'Invalid token' or 403 Forbidden
Verify the SENTRY_ACCESS_TOKEN value is correct and has the necessary API scopes. Re-generate the token at sentry.io/settings/account/api/auth-tokens/ and ensure it is not expired.
AI-powered search tools (Seer) are not available
Seer requires setting EMBEDDED_AGENT_PROVIDER to 'openai' or 'anthropic' along with the corresponding API key in the MCP server environment. Without these, the standard search_events and search_issues tools still work.
Cannot connect to self-hosted Sentry instance
Pass --host=your-sentry-hostname to the npx command. If your instance uses HTTP only (no TLS), also add --insecure-http. Ensure the host is reachable from the machine running the MCP server.
Frequently Asked Questions about Sentry
What is Sentry?
Sentry is a Model Context Protocol (MCP) server that remote model context protocol server acting as middleware to the sentry api, allowing ai assistants like claude to access sentry data and functionality through natural language interfaces. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Sentry?
Install via npm with the command: npx -y @sentry/mcp-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Sentry?
Sentry works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Sentry free to use?
Yes, Sentry is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Sentry Alternatives — Similar Monitoring & Observability Servers
Looking for alternatives to Sentry? Here are other popular monitoring & observability servers you can use with Claude, Cursor, and VS Code.
Netdata
★ 78.9kReal-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Kubeshark
★ 11.9keBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.
Mission Control
★ 4.9kSelf-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.
Grafana
★ 3.0kThis MCP server enables natural-language querying of Grafana logs by automatically detecting log sources and service labels. It provides read-only access to log data with intelligent caching for efficient repeat queries.
Sentrux
★ 2.4kReal-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.
OpenInference
★ 986OpenTelemetry Instrumentation for AI Observability
Browse More Monitoring & Observability MCP Servers
Explore all monitoring & observability servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Sentry in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Sentry?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.