Airbroke
🔥 Lightweight, Airbrake/Sentry-compatible, PostgreSQL-based Open Source Error Catcher
What is Airbroke?
Airbroke is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🔥 lightweight, airbrake/sentry-compatible, postgresql-based open source error catcher
🔥 Lightweight, Airbrake/Sentry-compatible, PostgreSQL-based Open Source Error Catcher
This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 🔥 Lightweight, Airbrake/Sentry-compatible, PostgreSQL-based
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx airbrokeConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Airbroke
Airbroke is a lightweight, open-source error monitoring platform compatible with both Airbrake and Sentry SDKs, backed by PostgreSQL for persistence, and deployable via Docker or one-click cloud providers. Its built-in MCP server exposes eight tools that let AI assistants list projects, browse error notices and occurrences (with full backtraces), run cross-project searches, and retrieve SDK integration snippets — turning Claude into an interactive error-triage partner. Engineering teams who want to own their crash-reporting infrastructure and also query errors conversationally through an AI assistant deploy Airbroke.
Prerequisites
- PostgreSQL 15+ database with at least 8 available connection slots
- Node.js 22 or 24+ for building from source (or Docker for containerised deployment)
- A value for AIRBROKE_MCP_API_KEY to authenticate MCP requests
- BETTER_AUTH_SECRET for session authentication
- An MCP client such as Claude Desktop that supports HTTP-based MCP servers
Configure environment variables
Copy the .env.dist template and fill in at minimum DATABASE_URL, DIRECT_URL, BETTER_AUTH_SECRET, and AIRBROKE_MCP_API_KEY. The MCP API key is a static bearer token you generate yourself.
cp .env.dist .env
# Required fields to set:
# DATABASE_URL=postgresql://user:pass@host:5432/airbroke
# DIRECT_URL=postgresql://user:pass@host:5432/airbroke
# BETTER_AUTH_SECRET=<random-secret>
# AIRBROKE_MCP_API_KEY=<your-static-bearer-token>
# AIRBROKE_CORS_ORIGINS=https://myapp.example.comDeploy with Docker Compose
Build and start the Airbroke stack using the included Makefile targets. The app listens on port 3000 by default.
make build
make runIntegrate your application's error reporting
Point your existing Airbrake or Sentry SDK at your Airbroke instance. Airbrake notices go to /api/v3/notices and Sentry envelopes to /api/sentry/*/envelope.
# Example Airbrake SDK config (Node.js)
const airbrake = new Airbrake.Notifier({
projectId: 1,
projectKey: 'your-project-key',
host: 'https://myairbroke.example.com'
});Connect the MCP server to your AI client
The MCP endpoint is at POST /api/mcp. Configure your MCP client (Claude Desktop or similar) to call this HTTP endpoint with your API key in the header.
# Claude Desktop / TOML-style MCP config
[mcp_servers.airbroke]
url = "https://myairbroke.example.com/api/mcp"
[mcp_servers.airbroke.http_headers]
X-Airbroke-Mcp-Key = "your-static-bearer-token"Verify MCP tools are available
Ask your AI assistant to list Airbroke projects. The eight available tools are: airbroke_list_projects, airbroke_get_project, airbroke_list_notices, airbroke_list_occurrences, airbroke_get_notice, airbroke_get_occurrence, airbroke_search, and airbroke_get_setup_guide.
Airbroke Examples
Client configuration
HTTP-based MCP config for connecting Claude Desktop to a deployed Airbroke instance.
{
"mcpServers": {
"airbroke": {
"type": "http",
"url": "https://myairbroke.example.com/api/mcp",
"headers": {
"X-Airbroke-Mcp-Key": "your-static-bearer-token"
}
}
}
}Prompts to try
Example prompts for querying your Airbroke error data through an AI assistant.
- "List all projects tracked in Airbroke."
- "Show me the 10 most recent error notices for the payments service."
- "Get the full backtrace for the latest NullPointerException in the API project."
- "Search across all projects for errors mentioning 'database connection timeout'."
- "Give me the SDK setup guide for integrating Sentry into a Node.js app."Troubleshooting Airbroke
MCP requests return 401 Unauthorized
Make sure AIRBROKE_MCP_API_KEY is set in your .env and that you are sending it as either 'Authorization: Bearer <key>' or 'X-Airbroke-Mcp-Key: <key>' in the request header.
Database connection errors during startup
Verify DATABASE_URL points to a running PostgreSQL 15+ instance with at least 8 free connection slots. If you are using PgBouncer, also set DIRECT_URL to a direct (non-pooled) connection string for migrations.
Airbrake/Sentry notices are not appearing in the dashboard
Check AIRBROKE_CORS_ORIGINS includes the origin of the app sending notices. The error collection endpoints are /api/v3/notices (Airbrake) and /api/sentry/*/envelope (Sentry).
Frequently Asked Questions about Airbroke
What is Airbroke?
Airbroke is a Model Context Protocol (MCP) server that 🔥 lightweight, airbrake/sentry-compatible, postgresql-based open source error catcher It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Airbroke?
Follow the installation instructions on the Airbroke GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Airbroke?
Airbroke works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Airbroke free to use?
Yes, Airbroke is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Airbroke Alternatives — Similar Monitoring & Observability Servers
Looking for alternatives to Airbroke? 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 Airbroke 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 Airbroke?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.