jitsu

Jitsu MCP Server

Jitsu's MCP integration lets AI assistants configure and debug customer data pipelines. Teams managing Jitsu workspaces can control syncs, inspect event logs, and test transformations.

Server facts

jitsu MCP Server

Project

Author
Jitsu
Website
jitsu.com
License
Not specified

Tech

Runtime / language
Not specified
Transports
Not specified
Remote available
Yes
Authentication
oauth

Activity

GitHub stars
5,108
Last commit
Data as of

Tags

  • analytics
  • cdp
  • clickhouse
  • data pipeline
  • data warehouse
  • etl
  • event streaming
  • open source
  • segment alternative

Overview

Within a Jitsu workspace, the MCP tools let an assistant inspect configuration schemas before creating or updating streams, destinations, services, and their connections. Connector specifications describe credential fields, while stream discovery provides the catalog used to configure syncs. Source credential checks run asynchronously and can be polled for results; destination connection tests return synchronously and support stored or unsaved configurations. Sync controls cover starting and cancelling jobs, checking task status, retrieving logs, and inspecting saved incremental cursors. Resetting a cursor makes the next run start from scratch, with resets blocked while a sync is running.

For troubleshooting, event queries expose records covering incoming data, function executions, bulker writes, and the dead-letter queue. Transformation functions and profile builders can run against sample events, returning results, logs, and store mutations without saving changes. Statistics show event counts by pipeline resource and outcome, source-to-destination pairs with successful syncs, and profile-building progress. Configuration changes and deletions prompt for approval. Access uses OAuth 2.1 with dynamic client registration for workspaces available to the authenticated account. The integration supports Jitsu Cloud and self-hosted deployments.

jitsu setup notes

  • jitsu has no recorded license; confirm reuse terms in its repository.

Related MCP servers