# Airbrake MCP

> Airbrake provides proactive monitoring for your codebase health and application performance. This MCP lets your AI client automatically track error spikes in real time, analyze specific failure groups, and correlate current errors against deployment versions. Check API connectivity, review all environments, or report a custom bug notice—all through natural conversation.

## Overview
- **Category:** productivity
- **Price:** Free
- **Tags:** airbrake, error-monitoring-api, exception-tracking, application-health, installment-automation, bug-manage, devops-tools, stability-metrics, mcp

## Description

You don't want to switch context just to check if the latest release broke something. This connector lets your agent manage your entire error monitoring workflow without you leaving your code editor. Need to know which environment is failing? You can list all configured environments and pull up detailed project configs instantly. Want to see what happened after the last deployment? The MCP tracks those installs, allowing you to correlate new errors with specific versions. If a developer finds an issue while testing, they can report it directly through your agent. Because Vinkius manages this entire catalog of tools, you get one connection point for all your system health needs—from project oversight to deep error inspection.

## Tools

### check_airbrake_status
Verifies that the MCP has active and functional API connectivity to Airbrake.

### get_error_group
Retrieves detailed information about a specific group of error types, including full stack traces.

### get_project
Fetches all configuration details for one specific monitored project.

### list_deploys
Generates a list of all past and current application deployments (Installments).

### list_environments
Shows every configured environment, like 'staging' or 'production', for the monitored apps.

### list_error_groups
Lists available error groups for a project, providing occurrence counts and severity levels.

### list_notices
Retrieves a list of individual reported error notices that occurred over time.

### list_projects
Returns a comprehensive list of every application or service monitored by Airbrake.

### report_notice
Allows the user to submit a new, custom-defined error notice for tracking purposes.

### track_deploy
Records a new deployment version and environment name against a specific project ID.

## Prompt Examples

**Prompt:** 
```
List all my Airbrake projects.
```

**Response:** 
```
You have 4 projects: 'API Gateway' (ID: 120394, 23 active error groups), 'Frontend App' (ID: 120395, 8 groups), 'Worker Service' (ID: 120396, 15 groups), and 'Mobile SDK' (ID: 120397, 3 groups). Which project would you like to investigate?
```

**Prompt:** 
```
Show me the error groups for project 120394.
```

**Response:** 
```
Project 'API Gateway' has 23 error groups. Top 3 by occurrence: 'TimeoutError' (1,847 occurrences, last seen 2 min ago), 'ConnectionRefused' (523 occurrences, last seen 15 min ago), 'ValidationError' (189 occurrences, last seen 1 hour ago). Would you like to inspect the stack trace of the TimeoutError?
```

**Prompt:** 
```
Record a Installment for project 120394: version 3.2.1, production.
```

**Response:** 
```
Installment recorded! Version 3.2.1 has been tracked in production for project 'API Gateway'. Airbrake will now correlate new errors with this release. Would you like to check the error rate after this Install?
```

## Capabilities

### List and configure projects
Get a list of all monitored applications and pull detailed configuration data for any specific project ID.

### Analyze current and historical errors
View groups of similar errors, see which ones are most frequent, check their severity, or inspect the full stack trace for a single instance.

### Monitor deployment history
Track all past releases (Installments) and record new version deployments, linking them to specific environments like production or staging.

### Check system status and connectivity
Verify that the API connection is active and your Airbrake account is operational. This confirms you can actually send data.

### Report new error notices
Submit a custom, immediate report of an error when automated tracking isn't possible or necessary.

## Use Cases

### Post-release failure investigation
A DevOps engineer notices an increase in errors. They ask the agent to list_deploys for the service and then use get_error_group on the top error type, immediately correlating the spike with version 3.2.1 which was deployed last night.

### Validating a new environment
A QA analyst needs to check staging before launch. They ask the agent to list_environments and then use list_error_groups against the 'staging' profile, ensuring all expected error groups are below threshold.

### Capturing ad-hoc bugs
A developer finds a bug during local testing that isn't tracked yet. They call report_notice directly through their agent, providing immediate context and allowing the team to monitor it as if it were an automated failure.

### Project health overview
A manager needs a quick status update on three microservices. The agent runs list_projects, giving them the IDs of all services, followed by running list_error_groups for each one to assess overall risk.

## Benefits

- Pinpoint the source of failures: Instead of guessing, you can use list_error_groups to see which specific error type is most frequent for a project. This cuts investigation time from hours to minutes.
- Maintain an audit trail: Use track_deploy whenever a release happens. This MCP links every reported failure back to the exact version and environment it occurred in.
- Skip dashboard clicks: Need to know if your API gateway is healthy? You can run check_airbrake_status directly through your agent, confirming connectivity before you even start coding.
- Deep dive into failures: Don't just see an error count. With get_error_group, you pull the full stack trace and affected users right into your chat window for immediate analysis.
- Manage complexity: When you list_projects, you get a centralized view of every service monitored, helping you know exactly which application to focus on next.

## How It Works

The bottom line is you tell your agent what data you need—error counts, deployment IDs, etc.—and it fetches the result directly from Airbrake without you touching a dashboard.

1. Subscribe to this MCP and enter your API Key from Airbrake account settings.
2. Connect the MCP to any compatible client (like Cursor or VS Code).
3. Ask your AI agent to perform a task, such as listing error groups for a specific project.

## Frequently Asked Questions

**How do I list all projects using list_projects?**
The tool gives you a clean roster of every monitored service in your account. This is useful for getting an initial scope of work and figuring out which project IDs you need to investigate next.

**What's the difference between list_error_groups and get_error_group?**
list_error_groups gives you a summary count, showing all unique error types for a project. get_error_group lets you dive into one specific type to see detailed information like stack traces.

**Can I track deployments manually with track_deploy?**
Yes, you can use track_deploy whenever an install happens, specifying the version and environment. This ensures your error tracking is always correlated against a known release date.

**Do I need to call check_airbrake_status first?**
It's good practice. Calling check_airbrake_status confirms that the MCP connection isn't stale or broken before you start asking for complex data like list_notices.

**When should I use the `report_notice` tool if I find a bug manually?**
You use `report_notice` when you need to track an error that Airbrake hasn't automatically captured. This lets you report custom errors right away, giving it full context for monitoring purposes.

**What specific data points does the `get_error_group` tool provide?**
The `get_error_group` tool gives deep details on an error group. You get full stack traces, frequency counts, and a list of users who were affected by that particular type of error.

**How do I check all the operational stages or environments using `list_environments`?**
Running `list_environments` shows you every configured stage for your project, like production, staging, and development. This is key for understanding where an error might be limited to.

**Does the `list_deploys` tool help me correlate errors with specific versions?**
Yes, `list_deploys` provides a history of all recorded releases. You can see which version was deployed and when, letting you trace error spikes back to a faulty build.

**Can my AI show me the most recent error groups for a project?**
Yes. Use the `list_error_groups` tool with the project ID. The agent returns all error groups with occurrence counts, severity levels, and the last time each error was seen.

**How do I track a Installment through the AI?**
Use the `track_Install` tool with the project ID, version string, and environment name. The agent records the Installment in Airbrake so you can correlate it with error rate changes.

**Can I report a custom error to Airbrake via my AI agent?**
Yes. The `report_notice` tool sends a custom error with a type and message to any project. This is useful for tracking non-exception events or test failures.