# Raygun MCP server

> Investigate errors, track deployments, analyze performance and manage application monitoring in Raygun

- Listing: https://mcp.tc/i/raygun
- Connect: use the server's own URL `https://api.raygun.com/v3/mcp` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: OAuth sign-in
- Category: [Observability & Incidents](https://mcp.tc/c/observability)
- Vendor: Raygun (MindscapeHQ)
- Homepage: <https://raygun.com/>
- Repository: <https://github.com/MindscapeHQ/mcp-server-raygun>

## About

Connects AI assistants to Raygun Crash Reporting, Real User Monitoring and Application Performance Monitoring. You can list and investigate error groups, read stack traces, update error status, track deployments, look up customers and sessions, and find slow backend traces and hotspots.

Runs as a hosted Streamable HTTP endpoint at https://api.raygun.com/v3/mcp, so nothing is installed locally. Clients with OAuth support sign in to Raygun in the browser and approve the requested permissions. A Raygun Personal Access Token sent as a Bearer header also works. A Raygun account with an active subscription is required.

## What it can do

- List and search applications and error groups
- Investigate errors with full stack traces and context
- Resolve, ignore or comment on error groups
- List, create and investigate deployments
- Search customers and inspect user sessions
- Find slow backend traces, APM issues and hotspots
- Analyze page performance and error trends over time

## Example prompts

- "Find the errors that first appeared after the latest deployment of my checkout application."
- "Investigate the most frequent production error and show a representative stack trace."
- "Which backend methods or database queries consumed the most time in the last 24 hours?"
- "Compare p95 page performance over the last seven days and find the largest regression."

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http raygun https://api.raygun.com/v3/mcp
```

2. Start Claude Code, type `/mcp`, pick **raygun** and choose **Authenticate**. A browser window opens for the Raygun (MindscapeHQ) sign-in.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.

2. Name it **Raygun** and paste this URL:

```url
https://api.raygun.com/v3/mcp
```

3. Click **Add**, then **Connect**, and sign in when Raygun (MindscapeHQ) asks.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=Raygun&connectorUrl=https%3A%2F%2Fapi.raygun.com%2Fv3%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://api.raygun.com/v3/mcp` and click **Add**.

3. Click **Connect** and sign in when Raygun (MindscapeHQ) asks.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, go to **Plugins**, select **+**, then **Add custom MCP server**.

2. Enter a name for the server.

3. Under **Connection**, paste `https://api.raygun.com/v3/mcp` as the server URL, then for authentication choose **OAuth**. ChatGPT sends you to Raygun (MindscapeHQ) to sign in.

4. Check **I understand and want to continue**, then select **Create as a plugin**.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=raygun&config=eyJ1cmwiOiJodHRwczovL2FwaS5yYXlndW4uY29tL3YzL21jcCJ9>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "raygun": {
      "url": "https://api.raygun.com/v3/mcp"
    }
  }
}
```

Cursor shows **Needs authentication** next to the server. Click the button beside it to sign in.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=raygun&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fapi.raygun.com%2Fv3%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"raygun","type":"http","url":"https://api.raygun.com/v3/mcp"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "raygun": {
      "type": "http",
      "url": "https://api.raygun.com/v3/mcp"
    }
  }
}
```

VS Code asks you to sign in the first time the server starts.

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "raygun": {
      "serverUrl": "https://api.raygun.com/v3/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade and sign in when asked.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add raygun --url https://api.raygun.com/v3/mcp
codex mcp login raygun
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.raygun]
url = "https://api.raygun.com/v3/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http raygun https://api.raygun.com/v3/mcp
```

Then, inside Gemini CLI, run `/mcp auth raygun` to sign in.

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "raygun": {
      "type": "http",
      "url": "https://api.raygun.com/v3/mcp"
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://api.raygun.com/v3/mcp`.

## Details

- Server version: 1.1.0
- Last checked: 2026-11-18 (reachable, asks for credentials)
- Listed: 2026-11-01
- Updated: 2026-11-01

---
Source: https://mcp.tc/i/raygun (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report
