Spark
Sign In
MCP Connector

Query Raygun Crash Reports with Natural Language

A remote MCP server for Raygun - investigate crashes, track deployments, and analyze performance conversationally.

Connect
Works with raygun
Raygun
Own this? Claim it
91
Spark score
out of 100
Updated 5 months ago
Version 1.0.0
Models
universal
Add 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

01

List and investigate error groups

02

Track application deployments and correlate with errors

03

Analyze performance trends and user monitoring data

04

Manage application API keys and error statuses

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-raygun | bash

Capabilities

Tools your agent gets

applications_list

List all applications in your Raygun account

applications_search

Search applications by name

application_get_details

Get detailed information about an application

application_regenerate_api_key

Generate a new API key for an application

error_groups_list

List error groups in an application

error_group_investigate

Get complete details about a specific error group

error_group_update_status

Change error group status (resolved, ignored, active)

error_group_add_comment

Add investigation notes to an error group

+7 tools

Overview

Raygun MCP Server

This remote MCP server connects AI assistants to Raygun crash reporting and RUM data: error investigation and lifecycle management, deployment tracking, performance insights, and user monitoring. Use it when an AI assistant needs to investigate Raygun errors, track deployments, or analyze performance and user data. Requires a Raygun subscription and PAT.

What it does

A remote MCP server connecting AI assistants to Raygun's crash reporting and real user monitoring data, hosted at https://api.raygun.com/v3/mcp with no local install required. It covers six feature areas: error management (investigate, resolve, and track application errors with full stack traces and context), deployment tracking (monitor releases and correlate errors with deployments to spot problematic changes), performance insights (page load times, user metrics, and trends over time), user monitoring (customer sessions, behavior patterns, and affected users), team collaboration (managing invitations and coordinating error resolution), and metrics/analytics (time-series analysis and distribution histograms). Documented tools include applications_list, applications_search, application_get_details, and application_regenerate_api_key for application management, plus error_groups_list, error_group_investigate, error_group_update_status (resolve/ignore/activate), error_group_add_comment, error_instances_browse, and error_instance_get_details for error management - part of a larger documented tool set covering deployments, performance, users, and analytics as well.

When to use - and when NOT to

Use it when an AI assistant needs to investigate crashes, track deployments against error trends, analyze performance metrics, or look into affected users in Raygun - for example "show me the most recent error groups in my Raygun applications" or "what were the latest deployments and did they introduce any new errors." It requires an active Raygun subscription and a Raygun Personal Access Token (PAT).

Capabilities

Application management (list, search, get details, regenerate API key), error-group investigation and lifecycle management (list, investigate, update status, comment), individual error-instance browsing with full stack traces, plus documented tool categories for deployment tracking, performance insights, user monitoring, and metrics/analytics - the complete tool reference lives in the project's TOOLS.md.

How to install

As a hosted remote server, it's added directly to an MCP client with a URL and bearer-token header rather than installed locally. For Claude Code: claude mcp add --transport http raygun https://api.raygun.com/v3/mcp --header "Authorization: Bearer YOUR_PAT_TOKEN". Cursor, JetBrains AI Assistant, and VS Code use a similar JSON block with a "url" and "headers" Authorization Bearer entry; Codex, Gemini CLI, Amp, Cline, and Zed have their own equivalent one-line or config-block setup, all documented in the README. The PAT token comes from app.raygun.com/user/tokens.

Who it's for

Development and support teams using Raygun for crash reporting and real user monitoring who want to investigate errors, track deployments, and analyze performance conversationally through an AI assistant instead of the Raygun dashboard - useful for both incident triage right after a bad deploy and routine performance review across a set of applications.

Source README

🔭 Raygun MCP Server

Access your crash reporting data in Raygun with AI assistants

MCP
API
Status
Docs

A remote Model Context Protocol (MCP) server that connects AI assistants to your crash reporting and real user monitoring data in Raygun through natural language conversations.

📚 Tool Reference • 🚀 Quick Start • 🔑 Get API Token

✨ 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
  • 👥 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

🚀 Getting Started

The Raygun MCP server is hosted remotely at https://api.raygun.com/v3/mcp.

💡 Tip: Choose your AI assistant below and follow the configuration instructions. Don't forget to replace YOUR_PAT_TOKEN with your actual Raygun Personal Access Token!

Amp

Guide: Amp MCP Documentation

amp mcp add raygun --header "Authorization=Bearer YOUR_PAT_TOKEN" https://api.raygun.com/v3/mcp
Claude Code

Guide: Claude Code MCP Documentation

claude mcp add --transport http raygun https://api.raygun.com/v3/mcp --header "Authorization: Bearer YOUR_PAT_TOKEN"
Cline

Guide: Cline MCP Documentation

Use https://api.raygun.com/v3/mcp and your PAT token

Codex

Guide: Codex MCP Documentation

[mcp_servers.raygun]
command = "npx"
args = ["mcp-remote", "https://api.raygun.com/v3/mcp", "--header", "Authorization: Bearer YOUR_PAT_TOKEN"]
Cursor

Go to Cursor Settings → MCP → New MCP Server

{
  "mcpServers": {
    "Raygun": {
      "url": "https://api.raygun.com/v3/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_PAT_TOKEN"
      }
    }
  }
}
Gemini CLI 
gemini mcp add --transport http raygun https://api.raygun.com/v3/mcp --header "Authorization: Bearer YOUR_PAT_TOKEN"
JetBrains AI Assistant

Guide: JetBrains AI Assistant MCP Documentation

{
  "mcpServers": {
    "Raygun": {
      "url": "https://api.raygun.com/v3/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_PAT_TOKEN"
      }
    }
  }
}
VS Code

Guide: VS Code MCP Servers

{
  "servers": {
    "raygun": {
      "url": "https://api.raygun.com/v3/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_PAT_TOKEN"
      }
    }
  }
}
Zed

Guide: Zed MCP Documentation

{
  "context_servers": {
    "raygun": {
      "source": "custom",
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://api.raygun.com/v3/mcp",
        "--header",
        "Authorization: Bearer YOUR_PAT_TOKEN"
      ],
      "env": {}
    }
  }
}

💬 Your First Prompt

After configuration, try asking your AI assistant:

🔍 "Show me the most recent error groups in my Raygun applications"

🚀 "What were the latest deployments and did they introduce any new errors?"

📊 "Analyze the performance trends for my top pages over the last 7 days"

🛠️ Tools

The Raygun MCP server provides the following categories of tools:

📱 Applications
  • applications_list - List all applications in your Raygun account
  • applications_search - Search for applications by name
  • application_get_details - Get detailed application information
  • application_regenerate_api_key - Generate a new API key for an application
🐛 Error Management
  • error_groups_list - List error groups within an application
  • error_group_investigate - Get complete details about a specific error group
  • error_group_update_status - Change error group status (resolve, ignore, activate)
  • error_group_add_comment - Add investigation notes to an error group
  • error_instances_browse - Browse individual error occurrences
  • error_instance_get_details - Get full stack trace and context for an error instance
🚀 Deployments
  • deployments_list - List deployments for an application
  • deployment_create - Create a new deployment record
  • deployment_get_latest - Get the most recent deployment with error analysis
  • deployment_investigate - Get comprehensive deployment information
  • deployment_manage - Update or delete a deployment
👥 Customers & Sessions
  • customers_search - Search customers by name, email, or identifier
  • customer_investigate - Get customer profile, recent error groups, and sessions
  • sessions_list - List user sessions with environment and device data
📊 Performance & Metrics
  • pages_list - List monitored pages in an application
  • page_investigate - Get page details for metrics queries
  • metrics_website_performance_analyze - Track performance trends over time
  • metrics_performance_distribution_analyze - Understand performance variability
  • metrics_error_trends_analyze - Track error rates and patterns
🤝 Team Management
  • invitations_manage - List and review team invitations
  • invitation_send - Send a new team invitation
  • invitation_revoke - Cancel a pending invitation

For detailed documentation on each tool, see the Tool Reference.

🔑 Configuration

Obtaining a Personal Access Token

To use the Raygun MCP server, you need a Raygun Personal Access Token (PAT):

  1. Navigate to Raygun Personal Access Tokens
  2. Click Create New Token
  3. Give your token a descriptive name (e.g., "MCP Server Access")
  4. Select the appropriate permissions for your use case
  5. Copy the generated token and use it in your MCP configuration

⚠️ Important: Replace YOUR_PAT_TOKEN in the configuration examples above with your actual token. Keep your token secure and never commit it to version control!

For more details, see the Raygun API documentation.

📖 About

The Raygun MCP server enables AI coding assistants to access and analyze your crash reporting and real user monitoring data in Raygun, helping you investigate errors, track deployments, analyze performance, and manage your application monitoring workflow-all through natural language conversations.

🔗 Resources

Built with ❤️ by Raygun

Raygun

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.