mcp-server

Streamline AI with mission-control

Name: Streamline AI with mission-control
Author: builderz-labs

Dispatch tasks and govern AI operations from one dashboard, for founders using AI agents

intermediate⏱ 1-2 hours💵 Free self-hosted

6,250 stars84 forksTypeScriptUpdated 9/20/2026100% free · open source

What it is

Manage and govern your AI agents from a central dashboard.

Real use case example

"A founder like you can use this to automate data import from Amazon to Notion by setting up an AI agent in this mission control dashboard, then create a trigger for new products, and finally have the data synced within a few minutes."

Best insideClaude DesktopCursorCodex CLI

When to use it

•You have multiple AI models or agents that need to work together to accomplish a task
•You want to monitor and control the cost of running AI workflows and operations
•You need to manage complex AI workflows and want a centralized platform to do so

Ready-to-paste prompt

dispatch task 'sentiment-analysis' to agent ' transformer-model' with input '{"text": "This is a sample text"}'

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/mission-control && curl -fsSL https://workflowstacks.com/api/skills/mission-control/claude-skill -o ~/.claude/skills/mission-control/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Streamline AI with mission-control works

Codeflow

Free to inspect

Streamline AI with mission-control is a very large TypeScript project (~109k lines across 425 code files, plus 246 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, MIT license, has a test suite.

Size

Very large codebase

~109k lines · 425 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Node.js · Docker

Needs API keys (.env)

TypeScript 95%JavaScript 3%Shell 1%CSS 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
CLAUDE.md
The instructions the AI actually follows
3
src/index.ts
Where the program starts running
4
package.json
Dependencies and the commands it exposes
5
.env.example
The API keys and settings you must provide

What's in each folder

src/Core code — the actual logic569 files

skills/Prompts, skills & agent definitions4 files

docs/Documentation24 files

wiki/Documentation2 files

examples/Examples you can copy1 files

scripts/Helper scripts29 files

messages/Folder11 files

ops/Deployment / infrastructure3 files

READMEHas testsDocumentedCI checksDocker readyExamples includedMIT licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/mission-control && curl -fsSL https://workflowstacks.com/api/skills/mission-control/claude-skill -o ~/.claude/skills/mission-control/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

builderz-labs

Language

TypeScript