
Connect Raygun to ChatGPT, Claude and Gemini
Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Debug crashes and track user sessions using natural language.
Developed, maintained, and hosted by Vinkius.
MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
Your AI does the work. We keep it safe and sound.
No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.
Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

Each Connector runs inside its own sealed environment.
Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.
One switch stops every agent. Instantly.
One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.
Spending limits that pause instead of surprise.
Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.
Three controls, built into the layer your AI connects through.
Curated set · 7 capabilities
We ship only the actions that matter.
01-04
4 capabilities in this set.
Part of 7 available through Raygun.
- 01
Create legacy deployment
This capability creates a new deployment record using the legacy API. Use it to log release events in Raygun.
- 02
Send crash report
This capability sends a manual crash report and error payload to the Raygun API. It's useful for logging errors during manual testing.
- 03
List applications
This capability retrieves a list of all Raygun applications you have access to. It helps your agent identify which app to target for queries.
- 04
List deployments
This capability pulls a list of recent deployments for a specific application. Use it to correlate code changes with performance shifts.
05-07
3 capabilities in this set.
Part of 7 available through Raygun.
- 05
Rum authenticate
This capability handles authentication with the legacy RUM API. It's a required step before searching for user sessions.
- 06
Rum get session
This capability fetches detailed metadata for a specific RUM session. It provides the granular data needed to debug individual user issues.
- 07
Rum search sessions
This capability searches through RUM sessions based on your criteria. Use it to find specific user journeys or performance patterns.
Real work
What teams actually run
Post-Deployment Verification
After a new release, ask your agent to check if error rates have changed for that specific application.
Bug Reproduction
Find a specific user session via RUM search to see exactly what happened during a reported failure.
Testing Error Handling
Trigger a manual crash report through the agent to verify that your monitoring is working as expected.
Environment Auditing
Quickly list all environments and applications to ensure your monitoring coverage is complete.
Automate a task
Put Raygun to work on one thing.
Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.
One connector, every AI
Raygun works with the most popular AI clients.
These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.
Claude
ChatGPT
Gemini
Perplexity
Grok
Microsoft Copilot
Cursor
VS Code
Windsurf
JetBrains
Cline
LangChain
Vercel AI SDK
Lovable
Z.ai
Raycast
Qwen Code
Kimi Code
Le ChatBuilding your own app? The connector is yours to use.
You don't need a client to put Raygun to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.
Observed, not estimated
979ms average. Fast in production.
Raygun is checked daily against the live service.
- Fastest day
- 803ms
- Slowest day
- 1216ms
- 14-day trend
- Slowing+18%
Connect your client
One URL. Every client.
Activate the Connector, copy your link, and paste it into the client you already use. 7 capabilities arrive ready to run.
Preview access · not provider authentication
The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Raygun, so you can see the experience inside your AI.
It does not authenticate your account with Raygun. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
Raygun Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_QpfOtHUiSame8oggeIDGUEXJk4SI9HG2gUoF0CTJ/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Raygun capabilities are ready to use.
{
"mcpServers": {
"raygun-mcp": {
"url": "https://edge.vinkius.com/vk_preview_QpfOtHUiSame8oggeIDGUEXJk4SI9HG2gUoF0CTJ/mcp"
}
}
}
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Step-by-step instructions for each client are in the guide. How to connect
Guided setup for Claude? Set up Raygun in Claude and other AIs
Who it's for
Built for the work Raygun owners hand off.
This MCP is built for technical teams who need to bridge the gap between their code and their observability data.
- 01
DevOps & SREs
They use the agent to quickly check application health and deployment status without switching tabs.
- 02
Software Engineers
They use the agent to send manual crash reports or inspect RUM sessions to reproduce bugs.
- 03
Product Owners
They use the agent to query user session data to see how features perform in real-world scenarios.
FAQ
Questions Raygun owners ask.
- 01
How do I connect Raygun to my AI client?
You subscribe to the MCP on Vinkius and provide your Raygun Personal Access Token. Once connected, you can use it immediately in any compatible client like Claude or Cursor.
- 02
What credentials does this MCP need?
You will need to provide either a Raygun Personal Access Token (PAT) or an API Key to authenticate your requests.
- 03
Can I use this to debug specific user issues?
Yes. You can use the RUM capabilities to search for sessions and retrieve detailed metadata for specific user journeys.
- 04
Does this work with my existing Raygun dashboard?
This MCP acts as a bridge to your existing Raygun account, allowing you to interact with your data through your AI agent instead of the web dashboard.
- 05
Which AI clients are compatible?
This MCP works with any client that supports the Model Context Protocol, including Claude, Cursor, and Windsurf.
- 06
How can I see a list of all my Raygun applications?
Use the list_applications capability. It will retrieve all applications associated with your Personal Access Token, including their IDs and names.
- 07
Can I manually report an error that happened on a specific machine?
Yes, use the send_crash_report capability. You can specify the machine name, error message, stack trace, and even custom data to be sent to Raygun.
- 08
How do I search for user sessions from a specific country?
First, authenticate using rum_authenticate to get a session key. Then, use rum_search_sessions and provide the country code in the parameters.
Explore
More in Developer Tools
Honeybadger (Error Tracking) AI Connector
Monitor app exceptions and uptime via Honeybadger — list projects, resolve faults, and track deployments.
ViewBugSnag AI Connector
Monitor application errors via BugSnag — track stability, inspect error groups, and retrieve event details dir
ViewAirbrake AI Connector
Catch application errors in real time, track performance bottlenecks, and keep your codebase healthy with proa
ViewRollbar AI Connector
Connect your AI assistant to Rollbar to identify active bugs, review stack traces, trace code deployments, and
View
Suggestions
Sentry AI Connector
Monitor errors and application health via Sentry — query issues, inspect events, audit releases and check aler
ViewTrack-POD AI Connector
Optimize delivery routes, capture electronic proof of delivery, and track driver performance for logistics ope
ViewAgent Error Propagation Tracker AI Connector
Trace error chains and calculate system impact in multi-agent environments.
ViewAfterShip Tracking AI Connector
Shipment tracking and logistics — track packages, manage couriers, and monitor deliveries via AI.
View
Connect Raygun to Claude, Cursor, ChatGPT & more
