Jitsu MCP server
{
"mcpServers": {
"jitsu": {
"type": "http",
"url": "https://use.jitsu.com/mcp"
}
}
}{
"mcpServers": {
"jitsu": {
"type": "http",
"url": "https://use.jitsu.com/mcp"
}
}
}{
"mcpServers": {
"jitsu": {
"type": "http",
"url": "https://use.jitsu.com/mcp"
}
}
}{
"servers": {
"jitsu": {
"type": "http",
"url": "https://use.jitsu.com/mcp"
}
}
}{
"mcpServers": {
"jitsu": {
"type": "http",
"url": "https://use.jitsu.com/mcp"
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsonversion 1.0.0
What it does
Jitsu is an open-source event data platform that collects data from websites, apps, and servers, then delivers it to data warehouses and other tools. This MCP server lets you configure and operate Jitsu pipelines—destinations, streams, connections, functions, and live events—programmatically through an AI agent or LLM.
- Configure data pipeline destinations like ClickHouse, BigQuery, or Snowflake and route event streams to them.
- Create and deploy JavaScript functions that filter, transform, and enrich events before they reach destinations.
- Monitor live events, function logs, and destination writes in real-time to debug pipeline issues.
Tools this server exposes
| Tool | Does |
|---|---|
| manage_destinations | Create, read, update, and delete event delivery destinations. |
| manage_streams | Create and configure event streams (sites) that collect events. |
| manage_connections | Set up and manage connections to data sources and destinations. |
| manage_functions | Deploy and configure JavaScript functions that process events. |
| view_live_events | Access real-time event data, function logs, and destination writes. |
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.