Query Raygun Crash Reports with Natural Language
A hosted MCP server connecting AI assistants to Raygun's crash reporting, RUM, and APM data, with no local server to install.
1.0.0Add to Favorites
Why it matters
Connect your AI assistant to Raygun crash reports and user monitoring data. Interact with your application's errors, deployments, and performance metrics using natural language conversations.
Outcomes
What it gets done
List and investigate error groups
Track application deployments and correlate with errors
Analyze performance trends and user monitoring data
Manage application API keys and error statuses
Source
Get it from source
Spark does not host a copy of it.
Open sourceReports
Agent outcome reports
No reports yet
Capabilities
Tools your agent gets
List all applications in your Raygun account
Search applications by name
Get detailed information about an application
Generate a new API key for an application
List error groups in an application
Get complete details about a specific error group
Change error group status (resolved, ignored, active)
Add investigation notes to an error group
Overview
Raygun MCP Server
Raygun MCP Server is a hosted, remote MCP server that connects AI assistants to Raygun's crash reporting, real user monitoring, and application performance monitoring data. It requires no local install and authenticates via OAuth or a Personal Access Token. Reach for it when investigating crashes, performance regressions, or customer sessions through an AI assistant instead of switching to the Raygun dashboard.
What it does
Raygun MCP Server is a hosted, remote MCP server that connects AI assistants to Raygun's Crash Reporting, Real User Monitoring, and Application Performance Monitoring, letting an AI investigate errors and performance through natural-language conversation. Raygun hosts and updates the service at https://api.raygun.com/v3/mcp - there is no package or local server to install.
When to use - and when NOT to
Use it to investigate errors and performance without leaving your AI assistant - ask it to find errors that first appeared after the latest deployment, investigate the most frequent production error with a representative stack trace, find the backend methods or database queries that consumed the most time in the last 24 hours, pull the last session for a specific customer, or compare p95 page performance over the last seven days for the largest regression.
Requires an active Raygun account and subscription. OAuth is the recommended auth path (no client ID/secret needed, Raygun supports automatic client registration); each OAuth connection grants access to one Raygun plan, so a different plan needs a separate configuration authorized separately. Some tools write to Raygun data - error statuses, deployments, invitations, comments, and ingestion API keys - and application tools can return or rotate ingestion API keys, which should be treated as credentials since rotating one immediately invalidates the previous key; review write actions before approving them. Tool results may be included in conversations processed by your AI client or model provider, so diagnostic and customer data sharing should follow your organization's policies.
Capabilities
Applications: list/search applications, get details, regenerate an API key. Error Management: list/search error groups by error/stack trace/URL/version/user/tags/custom data, investigate a group's full details, update status (resolve/ignore/activate), add/read investigation comments, list occurrences, get a full stack trace for an instance. Deployments: list, create, get the latest with error analysis, investigate comprehensively, update or delete. Customers & Sessions: search customers, investigate a profile with recent errors and sessions, list sessions, investigate a session's environment/errors/page views. APM: search recurring backend performance issues, investigate an issue's metrics and affected traces, search slow/failing traces, investigate a trace's profiler threads, rank slow methods/queries/external calls as hotspots. Performance & Metrics: list monitored pages, investigate a page, analyze website performance trends, performance distribution/variability, and error trend rates. Team Management: manage/send/revoke invitations.
How to install
OAuth (recommended): add the URL as a Streamable HTTP server with no Authorization header. Claude Code: claude mcp add --transport http raygun https://api.raygun.com/v3/mcp, then /mcp and follow the browser auth flow; Codex: codex mcp add raygun --url https://api.raygun.com/v3/mcp then codex mcp login raygun; Cursor and VS Code have one-click install badges and prompt for authentication on connect. For clients without MCP OAuth support or for automation, use a Personal Access Token from https://app.raygun.com/user/tokens as Authorization: Bearer YOUR_PAT_TOKEN in the server's HTTP headers - keep it secure and never commit it to version control.
Who it's for
Developers and on-call engineers who want to investigate crashes, performance regressions, and customer sessions through an AI assistant instead of switching to the Raygun dashboard.
Source README
🔭 Raygun MCP Server
Investigate errors and performance in Raygun with AI assistants
A remote Model Context Protocol (MCP) server that connects AI assistants to Raygun Crash Reporting, Real User Monitoring, and Application Performance Monitoring.
✨ Key Features
- 🐛 Error Management - Investigate, resolve, and track application errors and crashes with full stack traces and context
- 🚀 Deployment Tracking - Monitor releases and correlate errors with deployments to identify problematic changes
- ⚡ Performance Insights - Analyze page load times, user metrics, and performance trends over time
- 🔬 APM Investigation - Find backend hotspots, recurring performance issues, and slow traces
- 👥 User Monitoring - Track customer sessions, behavior patterns, and identify affected users
- 🤝 Team Collaboration - Manage invitations and coordinate error resolution across your team
- 📊 Metrics & Analytics - Time-series analysis and distribution histograms for errors and performance
📋 Requirements
- A Raygun account with an active subscription
- An MCP client with OAuth support, or a Raygun Personal Access Token
🚀 Getting Started
The Raygun MCP server is hosted at:
https://api.raygun.com/v3/mcp
Raygun hosts and updates the service, so there is no package or local server to install.
OAuth (recommended)
Add the URL as a Streamable HTTP server without an Authorization header. On first connection, your MCP client will open Raygun in your browser so you can sign in, select a plan, review the requested permissions, and authorize access.
You do not need to supply an OAuth client ID or client secret. Raygun supports automatic client registration.
Codex and the ChatGPT desktop app
codex mcp add raygun --url https://api.raygun.com/v3/mcp
codex mcp login raygun
This configuration is shared by the Codex CLI, Codex IDE extension, and ChatGPT desktop app on the same Codex host.
In the ChatGPT desktop app, open Settings > MCP servers, select Add server, choose Streamable HTTP, and enter the Raygun endpoint. Save and restart the app, then select Authenticate for Raygun.
ChatGPT on the web uses remote MCP tools through Plugins and does not read your local Codex MCP configuration. A separately published Raygun Plugin would be installed from the Plugins catalog.
Claude Code
claude mcp add --transport http raygun https://api.raygun.com/v3/mcp
Run /mcp in Claude Code and follow the browser authentication flow.
Cursor
{
"mcpServers": {
"raygun": {
"url": "https://api.raygun.com/v3/mcp"
}
}
}
Cursor will prompt you to authenticate when it connects.
VS Code
{
"servers": {
"raygun": {
"type": "http",
"url": "https://api.raygun.com/v3/mcp"
}
}
}
VS Code will prompt you to authenticate when it connects.
Personal Access Token
PAT authentication remains supported for clients without MCP OAuth support and for automation. The following example uses Cursor's configuration format; other clients use the same Authorization header in their HTTP server configuration:
{
"mcpServers": {
"raygun": {
"url": "https://api.raygun.com/v3/mcp",
"headers": {
"Authorization": "Bearer YOUR_PAT_TOKEN"
}
}
}
}
💬 Your First Prompt
After configuration, try asking your AI assistant:
- “Find the errors that first appeared after the latest deployment of my checkout application.”
- “Investigate the most frequently occurring production error and show me a representative stack trace.”
- “Which backend methods or database queries consumed the most time in the last 24 hours?”
- “Show me the last session for customer
user@example.comand explain where their experience failed.” - “Compare p95 page performance over the last seven days and identify the largest regression.”
🛠️ Tools
The Raygun MCP server provides the following categories of tools:
📱 Applications
applications_list- List all applications in your Raygun accountapplications_search- Search for applications by nameapplication_get_details- Get detailed application informationapplication_regenerate_api_key- Generate a new API key for an application
🐛 Error Management
error_groups_list- List error groups within an applicationerror_groups_search- Search occurrences by error, stack trace, URL, version, user, tags, or custom dataerror_group_investigate- Get complete details about a specific error grouperror_group_update_status- Change error group status (resolve, ignore, activate)error_group_add_comment- Add investigation notes to an error grouperror_group_read_comments- Review existing investigation noteserror_group_instances_list- List occurrences in an error grouperror_instance_get- Get the full stack trace and context for an occurrence
🚀 Deployments
deployments_list- List deployments for an applicationdeployment_create- Create a new deployment recorddeployment_get_latest- Get the most recent deployment with error analysisdeployment_investigate- Get comprehensive deployment informationdeployment_manage- Update or delete a deployment
👥 Customers & Sessions
customers_search- Search customers by name, email, or identifiercustomer_investigate- Get customer profile, recent error groups, and sessionssessions_list- List user sessions with environment and device datasession_investigate- Inspect a session's environment, errors, and page views
🔬 Application Performance Monitoring
apm_issues_search- Find recurring backend performance issues and anti-patternsapm_issue_investigate- Inspect an issue's metrics and affected tracesapm_traces_search- Find slow or failing backend requestsapm_trace_investigate- Inspect profiler threads and significant calls in a traceapm_hotspots_search- Rank slow methods, database queries, and external calls
📊 Performance & Metrics
pages_list- List monitored pages in an applicationpage_investigate- Get page details for metrics queriesmetrics_website_performance_analyze- Track performance trends over timemetrics_performance_distribution_analyze- Understand performance variabilitymetrics_error_trends_analyze- Track error rates and patterns
🤝 Team Management
invitations_manage- List and review team invitationsinvitation_send- Send a new team invitationinvitation_revoke- Cancel a pending invitation
For detailed documentation on each tool, see the Tool Reference.
🔐 Authentication
OAuth
Raygun implements the MCP authorization flow for HTTP clients. The server advertises its authorization server through OAuth Protected Resource Metadata, and compatible clients register themselves automatically using Client ID Metadata Documents or Dynamic Client Registration.
Access is tied to the Raygun user, plan, and scopes approved on the consent screen. Compatible clients securely store and refresh their own tokens.
Each OAuth connection grants access to one Raygun plan. Add another Raygun MCP configuration and authorize it separately when you need to work with a different plan.
Security and access
- OAuth never gives the client more access than the signed-in Raygun user already has.
- Read and write access is controlled by the scopes approved during OAuth or assigned to the PAT.
- Some tools can change Raygun data, including error statuses, deployments, invitations, comments, and ingestion API keys. Review write actions before approving them in your MCP client.
- Application tools can return or rotate ingestion API keys. Treat returned keys as credentials; rotating a key immediately invalidates the previous one.
- Tool results may be included in conversations processed by your chosen AI client or model provider. Follow your organization's policies for sharing diagnostic and customer data.
Obtaining a Personal Access Token
PATs remain available when OAuth is not suitable:
- Navigate to Raygun Personal Access Tokens
- Click Create New Token
- Give your token a descriptive name (e.g., "MCP Server Access")
- Select the appropriate permissions for your use case
- Copy the generated token and send it as
Authorization: Bearer YOUR_PAT_TOKEN
Keep PATs secure and never commit them to version control.
For more details, see the Raygun API documentation.
📖 About
The Raygun MCP server enables AI assistants to investigate Crash Reporting, RUM, and APM data; track deployments; analyze performance; and manage application monitoring through natural-language conversations.
🔗 Resources
- 📚 Raygun Documentation
- 📘 Raygun MCP Setup Guide
- 🔌 Raygun API Reference
- 🤖 Model Context Protocol
- 🐛 Report Issues
Built with ❤️ by Raygun
FAQ
Common questions
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.