RaygunFor AI Agents

Sign up → Instrumentation → MCP → prompt

Connect AI agents to your software telemetry

Follow this path once and your coding agent can start answering production debugging questions with Raygun evidence.

Step 1 · Account

Create a Raygun account

Start a free trial or sign in to an existing Raygun account. Make sure it can access the applications whose errors, sessions, and performance data your agent should inspect.

Sign up free

Step 2 · Instrumentation

Instrument your software with Raygun

Add a Raygun SDK to capture the production errors, user impact, and performance context your coding agent needs to investigate with confidence.

Explore all Raygun SDKs

Step 3 · MCP snippets

Choose your coding agent

Connect your preferred coding agent to the remote Raygun MCP endpoint, then it can use your production telemetry as evidence while it investigates and fixes issues. 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.

Configuration targetCursor Settings → Tools & MCP
{
  "mcpServers": {
    "Raygun": {
      "url": "https://api.raygun.com/v3/mcp"
    }
  }
}
  1. Open Cursor Settings → Tools & MCP → New MCP Server (or Add Custom MCP).
  2. Paste the JSON configuration.
  3. Cursor will prompt you to authenticate when it connects.

Step 4 · Prompt AI

Ask a question Raygun can answer

Good AI agent prompts name a release, error URL, user, time window, or route. That gives Raygun MCP a focused job and gives your team a fix plan that can be reviewed.

Explore more prompts
Fix a known exception
Use the Raygun MCP to investigate error group [error group URL].

1. Summarize the stack trace, last seen, frequency, and affected users.
2. Correlate the group with relevant deployments and inspect a representative error instance.
3. Keep in mind that the cause of the error might not be where the error was thrown. Look back through the code to see if it's a case of a faulty value being passed through, or data being put into a bad state somewhere else entirely.
4. Before making a fix, write a test that reproduces the cause of the issue and confirm that it fails.
5. Propose the smallest code change that fixes the bug and passes the test.

See it work

Watch an AI agent use Raygun MCP

See how a coding agent combines Raygun telemetry with code context to move from a production signal to a reviewable fix plan.

MCP deep dive

Production eyes for coding agents

Set it up once. Automate your software improvements.

Connect the remote MCP server, then make Raygun context part of every coding agent debugging workflow.

Prompts