Airbrake Connector for AI agents.
10 live capabilities
Manage error monitoring and release tracking directly from your code editor.
Waiting for input…
Why people use Airbrake
Airbrake Error Monitoring for Faster Debugging
This Connector changes that by bringing the dashboard to your AI agent. You can just ask your agent to pull the latest errors or show you the stack trace for a specific crash. It gives you the data you need exactly where you're already working.
What Vinkius changes
You get a hands-on way to manage your error monitoring without leaving your workspace.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Debugging a production crash
An engineer asks the agent to find the most frequent error in the API Gateway project and gets the stack trace immediately.
- Real-world use case 02
Tracking a new release
A DevOps lead tells the agent to record version 3.
- Real-world use case 03
Auditing error spikes
A QA lead asks the agent to list error groups for the mobile app to see which ones have the highest severity.
Complete set · 10capabilities
The complete Airbrake capability set.
These are the exact actions your AI can choose when you ask it to work with Airbrake.
01—04
4 capabilities in this set.
Part of 10 available through Airbrake.
- 01 Capability
Get project
Get specific details about a monitored project. This helps you understand the scope of a project's configuration.
- 02 Capability
List deploys
See a list of all tracked deployments. Use this to see how many times you've released a specific version.
- 03 Capability
List environments
View all your configured environments like production or staging. This helps you see where your code is currently running.
- 04 Capability
List error groups
See all error groups for a specific project. It shows you the frequency and severity of each group.
05—07
3 capabilities in this set.
Part of 10 available through Airbrake.
- 05 Capability
List notices
See individual error occurrences within a group. This is useful for looking at specific instances of a bug.
- 06 Capability
List projects
Get a list of every project you monitor in Airbrake. Use it to quickly see your entire portfolio of apps.
- 07 Capability
Report notice
Report a custom error notice for tracking. This lets you manually log specific issues that need attention.
08—10
3 capabilities in this set.
Part of 10 available through Airbrake.
- 08 Capability
Track deploy
Record a new deployment with its version and environment. This ensures your errors are tied to the right release.
- 09 Capability
Check airbrake status
Verify that your API connection is working. Use it to make sure the Connector is communicating correctly with Airbrake.
- 10 Capability
Get error group
Fetch the full details of a single error group. It provides the stack trace and the number of affected users.
Set up in minutes
One URL. Then ask Airbrake to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Airbrake from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_HHP9bR8t0n7QJxt74sVaPWkt2VOwkv5TiYKo0BfB/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Airbrake, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Airbrake for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_HHP9bR8t0n7QJxt74sVaPWkt2VOwkv5TiYKo0BfB/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Airbrake URL.
- Step 03
Save and start
Save the connection and enable Airbrake in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"airbrake": {
"url": "https://edge.vinkius.com/vk_preview_HHP9bR8t0n7QJxt74sVaPWkt2VOwkv5TiYKo0BfB/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Airbrake
Open Agent mode in chat and ask: "Using Airbrake, help me...". 10 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"airbrake": {
"url": "https://edge.vinkius.com/vk_preview_HHP9bR8t0n7QJxt74sVaPWkt2VOwkv5TiYKo0BfB/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Airbrake
Ask Copilot: "Using Airbrake, help me...". 10 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"airbrake": {
"url": "https://edge.vinkius.com/vk_preview_HHP9bR8t0n7QJxt74sVaPWkt2VOwkv5TiYKo0BfB/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Airbrake
Open Cascade and ask: "Using Airbrake, help me...". 10 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"airbrake": {
"url": "https://edge.vinkius.com/vk_preview_HHP9bR8t0n7QJxt74sVaPWkt2VOwkv5TiYKo0BfB/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Airbrake
Ask Cline: "Using Airbrake, help me...". 10 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add airbrake --transport http "https://edge.vinkius.com/vk_preview_HHP9bR8t0n7QJxt74sVaPWkt2VOwkv5TiYKo0BfB/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Airbrake
Ask Claude: "Using Airbrake, show me...". 10 tools are ready
Where the request belongs
Work Airbrake can move forward.
This is for the engineer who's tired of tab-switching between their code and an error dashboard. It's for the person who needs to know what broke in production the second it happens.
On-call Engineer
Investigates production spikes and pulls stack traces instantly during an incident.
DevOps Lead
Tracks deployment versions and monitors environment health across staging and production.
QA Engineer
Reports custom test failures and monitors error groups across different environments.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsSentry
Monitor errors and application health via Sentry. query issues, inspect events, audit releases and check alert rules directly from any AI agent.
BugSnag
Monitor application errors via BugSnag. track stability, inspect error groups, and retrieve event details directly from any AI agent.
Honeybadger (Error Tracking)
Monitor app exceptions and uptime via Honeybadger. list projects, resolve faults, and track deployments.
Rollbar
Connect your AI assistant to Rollbar to identify active bugs, review stack traces, trace code deployments, and manage error lifecycles without leaving the chat.
AppDynamics (Application Performance Monitor API)
Monitor application performance, business transactions, and infrastructure health rules directly from your AI agent.
New Relic
Monitor and query your entire stack via New Relic NerdGraph. track entities, NRQL, and alerts directly from your AI agent.
Bring your own AI
Change the model, client or framework. Keep Airbrake connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Airbrake.
The practical details behind the request, access and result.
What is the Airbrake MCP?
It is a connector that allows your AI agent to access your Airbrake dashboard. You can ask questions about errors, projects, and deployments without leaving your code editor.
How does it help with debugging?
It lets your AI agent pull specific stack traces and error group details instantly. You can identify which bugs are spiking and see the exact lines of code that failed.
Can it see my production errors?
Yes, it can view error groups across all your configured environments, including production, staging, and development.
Does it support multiple projects?
Yes, it can list all your monitored projects and fetch specific configuration details for each one.
How do I connect it to my account?
Once you subscribe on Vinkius, you just need to provide your Airbrake API key to your AI client to get started.
Can it track my deployments?
Yes, it can record new releases with version numbers and environment info, which helps link errors to specific code changes.
Is it safe for my data?
The Connector only accesses the data within your Airbrake account that you authorize through your API key.
Can my AI show me the most recent error groups for a project?
Yes. Use the list_error_groups capability 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 capability 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 capability sends a custom error with a type and message to any project. This is useful for tracking non-exception events or test failures.
One connection away
Give your agent a direct line to Airbrake.
Connect Airbrake once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available