mcp-probe-kit

data-ai MCP Server

Spec-driven dev workflow MCP for Cursor & AI agents — start_feature/bugfix orchestration, auto Skill+AGENTS bootstrap, memory, GitNexus. npx -y mcp-probe-kit@latest

VerifiedInstall Ready
data-aidata-ai
3 views33 stars3 forksv3.6.3MIT

Why This Matters

Discovered via smithery and last synced 3mo ago.

VerifiedInstall Ready
Source
smithery
Stars
33
Last synced
3mo ago
Install
Instructions detected

Install

1. Install the package

npx -y mcp-probe-kit@latest

2. Add to claude_desktop_config.json

{
  "mcpServers": {
    "mcp-probe-kit": {
      "command": "npx",
      "args": [
        "mcp-probe-kit"
      ]
    }
  }
}

Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)

12
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (12)

ui_design_system

Directly generate design specs

fix_bug

TBP 8-step RCA only, without full orchestration

init_project

Generate complete project spec docs

Scenario

Recommended Tool

init_project_context

Generate tech stack/architecture/conventions

start_feature

Auto-complete: spec→estimation

start_bugfix

Root-cause-first flow: TBP RCA → fix → test

start_product

One-click: PRD→prototype→HTML

start_ui

Complete flow: design→components→code

add_feature

More lightweight, only generates docs

agents

context

State

Meaning