jitsu

MCP数据服务

提供方 Jitsu

数据服务 未标注 OAuth 授权 社区 / 第三方 ClaudeCursorVS CodeCodex

由 Jitsu 提供的 MCP 服务器,未标注。

一句话选型结论

按资料字段整理

jitsu 属于数据服务类 MCP 服务器,传输方式未标注,OAuth 授权,可直接接入 Claude、Cursor、VS Code 等,没有现成安装命令,需按官方文档接入。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类数据服务 传输方式未标注 鉴权OAuth 授权 部署方式未标注
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

数据服务
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

cdp analytics etl data warehouse clickhouse open source

支持客户端

适用场景

cdpanalyticsetl

安装与配置

未标注 OAuth 授权
上游未给出传输方式
  1. 1
    准备运行环境

    按官方文档确认运行环境(常见为 Node.js 或 Python),装好后再执行安装命令。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
数据库查询

用自然语言查库、取数,不用手写 SQL。

数据同步与清洗

把多来源数据拉到一处做整理。

报表取数

按口径快速拉出统计结果。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 已适配 Claude、Cursor、VS Code,换客户端不用重新研究配置。

先想清楚的地方

  • 没有现成安装命令,需要按官方文档自己填启动命令和参数。
  • 使用前要准备好OAuth 授权对应的凭据,并按最小权限配置。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在数据服务场景里让模型直接调用外部能力的人。
  • 已经在用 Claude、Cursor 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
jitsu当前 未标注 未标注 未标注 无 未标注
Memory 9d25f64e 9 未标注 未标注 无 2026-05-17
Getzep MCP 9 stdio · 本地进程 本地部署 有 2026-05-17
anything-llm 未标注 stdio · 本地进程 本地部署 有 2026-04-11
Prisma MCP Server 未标注 stdio · 本地进程 本地部署 有 2026-05-17
Astr Bot 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

数据服务
字段来自项目仓库与公开索引,中文说明由本站标注
提供方Jitsu上游标注的维护方 Jitsu
分类数据服务本站按上游分类展示
连接方式未标注上游未给出传输方式
鉴权方式OAuth 授权远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型未标注上游给出的部署形态
最近核验未标注上游最后核验时间

详细介绍

8.1 KB
来自项目仓库与上游目录的原文,未做删改

Open-source event data platform. An alternative to Segment.

Website ·
Docs ·
MCP Server ·
Jitsu Cloud ·
Self-hosting ·
Slack ·
MIT License


What is Jitsu?

Jitsu collects event data from your websites, apps and servers, and delivers it to your data
warehouse and to whatever other tools you use. It covers the same ground as Segment, but it's
MIT-licensed and self-hostable, so the whole pipeline can run inside your own infrastructure —
or on Jitsu Cloud, same software, hosted.

Data lands in minutes, not hours: Segment loads warehouses once or twice a day (hourly at best),
while Jitsu delivers per destination in batches as frequent as a minute, or row-by-row where that
suits the destination. And where Segment bills by Monthly Tracked User, Jitsu Cloud bills by event
volume, so the bill tracks data rather than audience size — while self-hosting has no usage billing
at all.

A typical Jitsu setup gives you:

  • Event collection from the browser, mobile, or the server, via
    SDKs, an HTTP API, or a drop-in Segment proxy.
  • Delivery to destinations — ClickHouse, BigQuery, Snowflake, Redshift, Postgres, S3, GCS, and
    dozens of SaaS tools, streamed or micro-batched depending on what the destination prefers. See the
    destination catalog.
  • Functions — JavaScript that runs on every event to filter,
    transform, and enrich it before delivery.
  • Write them in the browser, or build and deploy them from your own repo with the
    Jitsu CLI — jitsu-cli init scaffolds a TypeScript project
    with tests, and jitsu-cli deploy ships it to your workspace. Use whatever tooling you like:
    TypeScript, npm libraries, your own test suite, and your normal CI.
  • Connector syncs — pull data into your warehouse from third-party sources (Airbyte-compatible
    connectors).
  • A user identity graph and profile builder, built automatically from the event stream.
  • Live Events — see every event, function log and
    destination write as it happens, which makes debugging a pipeline a matter of seconds rather than
    days.
  • An MCP server, so an AI agent can configure and operate all of
    the above.

Get started with Jitsu Cloud

The fastest way to run Jitsu is Jitsu Cloud — we host and scale it for
you.

  • Free tier: 200k events/month, no credit card required.
  • Unlimited destinations and unlimited captured events on every plan.
  • A free ClickHouse instance is included, so you can go from zero to queryable event data
    without provisioning a warehouse first.
  • Custom domains, events debugger, and the Configuration API on the free tier too.

See pricing for the full breakdown, or jump straight into the
Quick Start guide.

Once you have a workspace:

  1. Create a site (a stream) and grab your write key.
  2. Add a destination — ClickHouse, BigQuery, Snowflake, Postgres, S3, or anything from the
    catalog.
  3. Start sending events using one of the methods below.

Sending events

Method Use it for
HTML snippet Any website, no build step
@jitsu/js Isomorphic — works in the browser and in Node.js
@jitsu/jitsu-react React and Next.js apps
HTTP API Any language, backend services
Segment proxy Migrating off Segment without touching client code

Everything the UI does is also available through the
Management API and the
Jitsu CLI.

Jitsu MCP Server

Jitsu ships a Model Context Protocol server, so coding agents and
AI assistants can build and operate your data pipelines directly — no clicking through the UI.

An agent connected to Jitsu can set up a destination, wire a connection, send a test event, read the
resulting Live Events, notice that a function threw, fix the function, and re-run it — the full
loop, without a human in the middle.

Endpoint: https://use.jitsu.com/mcp (or /mcp when self-hosting).

Connect your client

Claude Code```bash
claude mcp add --transport http jitsu https://use.jitsu.com/mcp


Other clients (Claude Desktop, Cursor, VS Code) take the same URL — see
jitsu.com/docs/mcp for their setup.

### Authentication

Interactive clients use **OAuth 2.1** — no API key to manage. The first tool call opens a browser
tab asking you to approve the connection; tokens are scoped, listed, and revocable from your account
settings page.

Headless environments (CI, cron, servers) use a personal API key instead — generate one on the user
settings page and pass it as `Authorization: Bearer :`:```bash
claude mcp add --transport http jitsu https://use.jitsu.com/mcp \
  --header "Authorization: Bearer $JITSU_API_KEY"

What the agent can do

25 tools, covering everything the console does: read and write workspace configuration
(destinations, streams, connections, functions), query Live Events and function logs, run and cancel
connector syncs, discover source streams and inspect sync state, execute functions and profile
builders against test data, and pull event and sync statistics. Full reference:
jitsu.com/docs/mcp.

Architecture

Jitsu is a handful of independently scalable services:

Service Stack What it does
ingest Go HTTP endpoint that accepts events and writes them to Kafka
rotor TypeScript Routes events, runs Functions, applies destination-specific transforms
bulker Go High-throughput warehouse ingestion — batching, schema management, retries
sync-controller Go Orchestrates connector syncs (pulling data from third-party sources)
console Next.js Admin UI, Management API, and the MCP server

Backed by Postgres (configuration), Kafka/Redpanda (event bus), ClickHouse (live events and
metrics), and MongoDB (profiles).

Bulker is also usable standalone if you just want a warehouse
ingestion engine and are comfortable with low-level APIs.

Self-hosting

Jitsu is MIT-licensed and fully self-hostable, with no usage limits and no feature gating. Cloud is
the path of least resistance; self-hosting is for when you need the data to stay inside your own
infrastructure.

Quick start (Kubernetes / Minikube)

The development Helm chart is the recommended way to get a complete stack running locally. You'll
need Minikube (a single-node Kubernetes cluster on your
machine) and Helm v3+:```bash
git clone -b newjitsu --single-branch https://github.com/jitsucom/jitsu
cd jitsu/helm

minikube start # give the VM at least 8GB RAM
./dev-deploy.sh deploy
./dev-deploy.sh tunnel # in a second terminal
```

./dev-deploy.sh tunnel runs minikube tunnel, which routes the cluster's LoadBalancer services to
localhost so you can reach them from your browser — console on :3000, ingest on :3049, bulker
on :3042, rotor on :3401, plus Postgres, ClickHouse, MongoDB and Kafka. It asks for sudo (it
binds privileged ports) and has to keep running in its own terminal for the whole session.

The console will be at http://localhost:3000. Full instructions:
Self-hosting Quick Start.

Production

For real deployments, read the
Production Deployment guide and the
Configuration Reference. It covers scaling each service,
Kafka sizing, and the environment variables every component reads.

Contributing

Contributions are welcome. CONTRIBUTING.md covers the repository layout, how to
set up a development environment and run the test suites, and the branch, commit and pull request
conventions.

Community & support

  • Slack — the fastest way to reach the team and other users
  • GitHub Issues — bugs and feature requests
  • Docs — guides and reference

License

Jitsu is licensed under the MIT License.

常见问题

6 问
答案由本站依据条目字段整理,不引用上游原文
jitsu 怎么安装?

资料没有给出安装命令,请到官方仓库或文档按说明接入;这类条目多数是生态应用,或尚未发布可安装包。

jitsu 怎么在 Claude、Cursor、VS Code 里配置?

它的传输方式未标注,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

jitsu 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

jitsu 需要 API Key 吗?

资料标注需要OAuth 授权认证,使用前准备好对应凭据,并按最小权限配置。

jitsu 支持哪些客户端?

资料标注支持 Claude、Cursor、VS Code、Codex、Zed;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

jitsu 能提供哪些能力?

资料显示能力标签包括 cdp、analytics、etl、data warehouse、clickhouse、open source。具体工具清单以官方文档为准。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 未标注。