mcp -raygun
Give your AI coding assistants access to Raygun so they can investigate, explain, and help resolve errors for you.
claude mcp add --transport stdio mindscapehq-mcp-server-raygun npx mcp-remote https://api.raygun.com/v3/mcp --header Authorization: Bearer YOUR_PAT_TOKEN
How to use
The Raygun MCP Server exposes Raygun crash reporting, deployments, performance, and user analytics to AI assistants via the MCP interface. It enables you to query and manipulate your Raygun data through natural language prompts and a suite of tools for applications, error management, deployments, customers & sessions, performance metrics, and team management. After configuring your PAT token and connecting to the remote MCP endpoint, you can invoke tools like error_groups_list to inspect error groups, deployments_list to review releases, customers_search to find affected users, or metrics_performance_distribution_analyze to understand performance variability. The available tools are organized by category, so you can ask your AI assistant to fetch a specific set of data (e.g., “Show me the latest error groups for App X” or “Analyze page load time trends for the top pages”). Each integration point returns structured data from Raygun, enabling precise follow-up questions and informed debugging.
How to install
Prerequisites:
- Node.js (with npm or npx) installed on your machine or deployment environment.
- Access to a Raygun account and a valid Personal Access Token (PAT).
- Internet access to reach https://api.raygun.com/v3/mcp.
Installation steps:
- Ensure Node.js and npm are installed:
- macOS/Linux: curl -fsSL https://nodejs.org/dist/index.html | bash
- Windows: download and install from https://nodejs.org/
- Verify npx is available:
- npm -v && node -v
- Run the MCP command to connect to Raygun (replace YOUR_PAT_TOKEN with your actual PAT):
- npx mcp-remote https://api.raygun.com/v3/mcp --header "Authorization: Bearer YOUR_PAT_TOKEN"
- Persist configuration (optional): add the configuration to your preferred MCP client setup following the provided example in your Tools/Documentation.
- If you prefer a script-based approach, create a small wrapper script that executes:
- npx mcp-remote https://api.raygun.com/v3/mcp --header "Authorization: Bearer YOUR_PAT_TOKEN"
Additional notes
Tips and common issues:
- Ensure your PAT has the correct permissions for the parts of Raygun you intend to access (applications, errors, deployments, etc.).
- When testing, keep YOUR_PAT_TOKEN in a secure location and avoid embedding it in code repositories.
- If you encounter 401/403 errors, double-check token validity and header formatting (case-sensitive: Authorization: Bearer ...).
- Some MCP clients may require explicit CORS or transport settings; adjust the --header value to match your environment, e.g., --header "Authorization: Bearer YOUR_PAT_TOKEN".
- Environment variables are not strictly required for token-based authentication in the provided setup, but you can customize the header payload if your deployment enforces different header conventions.
- For long-running queries, consider batching or paginating responses if the tool supports it, to avoid timeouts.
Related MCP Servers
ai
One-stop shop for building AI-powered products and businesses with Stripe.
llm-functions
Easily create LLM tools and agents using plain Bash/JavaScript/Python functions.
langchainjs -adapters
** THIS REPO HAS MOVED TO https://github.com/langchain-ai/langchainjs/tree/main/libs/langchain-mcp-adapters ** Adapters for integrating Model Context Protocol (MCP) tools with LangChain.js applications, supporting both stdio and SSE transports.
wanaku
Wanaku MCP Router
bitbucket
Bitbucket MCP - A Model Context Protocol (MCP) server for integrating with Bitbucket Cloud and Server APIs
filesystem
A Model Context Protocol (MCP) server for platform-agnostic file capabilities, including advanced search/replace and directory tree traversal