Raindrop’s MCP server brings Raindrop Triage — our expert investigator for AI applications — into your coding assistant. Ask it what’s happening in your app, hand off its findings to your local agent, and go from “something looks off” to a code fix without leaving your editor. The server is hosted atDocumentation Index
Fetch the complete documentation index at: https://raindrop.ai/docs/llms.txt
Use this file to discover all available pages before exploring further.
https://mcp.raindrop.ai/mcp — there’s nothing to install. Add the configuration to your editor and start asking.
Investigate with Raindrop Triage
The Raindrop agent continuously analyzes your traces, signals, and user feedback to surface real issues — not just metrics, but full investigation reports with root-cause hypotheses and the events that demonstrate them. Through the MCP server, your local coding agent can pull those investigations in and collaborate on the fix:- Ask Raindrop what’s wrong. “Ask Raindrop agent what issues happened today” returns the active investigations — title, description, suspected cause, and the conversations that triggered them.
- Drill in. Your local agent pulls the full trace for any flagged event: prompts, tool calls, model outputs, timings, errors.
- Fix it in code. With the investigation and trace in context, your local agent can locate the relevant prompt or handler in your repo and propose a patch — you stay in your editor the whole time.
Other capabilities
Beyond agent-led investigations, the MCP server exposes the rest of your Raindrop data:- Pull an activity overview — event trends, recent issues, and top signals from your dashboard.
- Search events semantically — find conversations matching a description (e.g. “users frustrated by load times”).
- Inspect traces — full execution tree for any event, including timing, tool calls, and errors.
- Quantify signals — count and filter events matching a signal over a time range.
- Browse user history — list conversations for a specific user.
- “Show me an overview from Raindrop of what’s happening in my app”
- “Find Raindrop events where users are getting bad responses”
- “How many Raindrop events matched the ‘tool_failure’ signal this week?”
- “List Raindrop conversations for user [ID]“
Authentication
OAuth 2.1 is the default. Most MCP clients handle it automatically — on first connection, your editor opens a browser window to authenticate. No tokens to manage. API key is the alternative for clients that don’t support OAuth, or for non-interactive environments (CI, shared setups). At app.raindrop.ai, go to settings → API Keys → Query SDK → Manage API Keys → New API Key, then pass it as a Bearer token:Connect your editor
- Claude Code
- Cursor
- VS Code
- Windsurf
- Other
Run this command in your project directory:Claude Code supports OAuth natively — it will open a browser window to authenticate on first use.To use an API key instead:
Troubleshooting
Tools not showing up in my editor Verify your MCP configuration is correct and restart your editor. Check that the server URL is exactlyhttps://mcp.raindrop.ai/mcp. In Claude Code, run claude mcp list or /mcp to confirm the server is registered.
Authentication failed
If using OAuth, try disconnecting and re-authenticating — your editor will reopen the browser auth flow. If using an API key, check that the header format is exactly Authorization: Bearer <token> with no extra whitespace.