Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Manage Jitsu data pipelines: destinations, streams, connections, functions, live events.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://use.jitsu.com/mcpRun this in your terminal
claude mcp add --transport http jitsu https://use.jitsu.com/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"jitsu": {
"url": "https://use.jitsu.com/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"jitsu": {
"type": "http",
"url": "https://use.jitsu.com/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://use.jitsu.com/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
We have not read this server’s tool list yet; we check endpoints in rotation.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
The registry name was verified against the domain jitsu.com (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.0.0) reached the registry 3 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, dotnet-mcp
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
MCP server for .NET symbols, XAML, source generators, and restricted workspace edit
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Open-source event data platform. An alternative to Segment.
Website · Docs · MCP Server · Jitsu Cloud · Self-hosting · Slack · MIT License
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:
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.The fastest way to run Jitsu is [Jitsu Cloud](https://use.jitsu.com) — we host and scale it for you.
See pricing for the full breakdown, or jump straight into the Quick Start guide.
Once you have a workspace:
| 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 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).
Claude Code
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.
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 : :
claude mcp add --transport http jitsu https://use.jitsu.com/mcp \
--header "Authorization: Bearer $JITSU_API_KEY"
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.
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.
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.
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+:
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.
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.
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.
Jitsu is licensed under the MIT License.