io.github.ariekogan/ateam-mcp
Build, validate, and deploy multi-agent AI solutions from any AI environment.
Ask AI about io.github.ariekogan/ateam-mcp
Powered by Claude Β· Grounded in docs
I know everything about io.github.ariekogan/ateam-mcp. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
ateam-mcp
Give any AI the ability to build, validate, and deploy production multi-agent systems.
This is an MCP server that connects AI assistants β ChatGPT, Claude, Gemini, Copilot, Cursor, Windsurf, and any MCP-compatible environment β directly to the ADAS platform.
An AI developer says "Build me a customer support system with order tracking and escalation" β and their AI assistant handles the entire lifecycle: reads the spec, builds skill definitions, validates them, deploys to production, and verifies health. No manual JSON authoring, no docs reading, no copy-paste workflows.
Why this matters
Today, building multi-agent systems requires deep platform knowledge, manual configuration, and switching between docs, editors, and dashboards. ateam-mcp eliminates all of that by making the ADAS platform a native capability of the AI tools developers already use.
The AI assistant becomes the developer interface:
Developer: "Create an identity verification agent that checks documents,
validates faces, and escalates fraud cases"
AI Assistant:
β reads ADAS spec (adas_get_spec)
β studies working examples (adas_get_examples)
β builds skill + solution definitions
β validates iteratively (adas_validate_skill, adas_validate_solution)
β deploys to production (adas_deploy_solution)
β verifies everything is running (adas_get_solution β health)
Developer: "Add a new skill that handles address verification"
AI Assistant:
β deploys into the existing solution (adas_deploy_skill)
β redeploys (adas_redeploy)
β confirms health
No context switching. No manual steps. The full ADAS platform β specs, validation, deployment, monitoring β is available as natural language.
How it reaches the AI community
ChatGPT users
ChatGPT supports MCP connectors in Developer Mode. Users connect by pasting a single URL:
Settings β Connectors β Developer Mode β paste https://mcp.ateam-ai.com
That's it. All 12 ADAS tools appear in ChatGPT. Any ChatGPT Pro, Plus, Business, or Enterprise user can build and deploy multi-agent solutions through conversation.
Claude users
Claude Desktop β install as an extension (one-click) or add to config:
{
"mcpServers": {
"ateam": {
"command": "npx",
"args": ["-y", "@ateam-ai/mcp"],
"env": {
"ADAS_TENANT": "your-tenant",
"ADAS_API_KEY": "your-api-key"
}
}
}
}
Claude Code β one command:
claude mcp add ateam -- npx -y @ateam-ai/mcp
Cursor / Windsurf / VS Code (Copilot)
Add to .cursor/mcp.json, mcp_config.json, or .vscode/mcp.json:
{
"mcpServers": {
"ateam": {
"command": "npx",
"args": ["-y", "@ateam-ai/mcp"],
"env": {
"ADAS_TENANT": "your-tenant",
"ADAS_API_KEY": "your-api-key"
}
}
}
}
Gemini and other platforms
As MCP adoption grows (it's now governed by the Agentic AI Foundation under the Linux Foundation, co-founded by Anthropic, OpenAI, and Block), every AI platform that implements MCP gets access to ateam-mcp automatically. The remote HTTP endpoint (https://mcp.ateam-ai.com) works with any client that supports Streamable HTTP transport.
Discovery
Developers find ateam-mcp through:
- npm β
npm search mcp ai-agentsβ@ateam-ai/mcp - Official MCP Registry β registry.modelcontextprotocol.io
- Claude Desktop Extensions β built-in extension browser
- Claude Code Plugin Marketplace β
/pluginβ Discover tab - Windsurf MCP Marketplace β built-in marketplace
- VS Code MCP Gallery β Extensions view
- Community directories β Smithery, mcp.so, PulseMCP (30,000+ combined listings)
Available tools
| Tool | What it does |
|---|---|
adas_get_spec | Read the ADAS specification β skill schema, solution architecture, enums, agent guides |
adas_get_examples | Get complete working examples β skills, connectors, solutions |
adas_validate_skill | Validate a skill definition through the 5-stage pipeline |
adas_validate_solution | Validate a solution β cross-skill contracts + quality scoring |
adas_deploy_solution | Deploy a complete solution to production |
adas_deploy_skill | Add a skill to an existing solution |
adas_deploy_connector | Deploy a connector to ADAS Core |
adas_list_solutions | List all deployed solutions |
adas_get_solution | Inspect a solution β definition, skills, health, status, export |
adas_update | Update a solution or skill incrementally (PATCH) |
adas_redeploy | Push changes live β regenerates MCP servers, deploys to ADAS Core |
adas_solution_chat | Talk to the Solution Bot for guided modifications |
Setup
# Clone
git clone https://github.com/ariekogan/ateam-mcp.git
cd ateam-mcp
# Install
npm install
# Configure
cp .env.example .env
# Edit .env with your ADAS tenant and API key
# Run
npm start
Architecture
βββββββββββββββββββββββββββββββββββββββββββββββ
β AI Environment β
β (ChatGPT / Claude / Cursor / Windsurf) β
β β
β Developer: "build me a support system" β
ββββββββββββββββββββ¬βββββββββββββββββββββββββββ
β MCP protocol
β (stdio or HTTP)
ββββββββββββββββββββΌβββββββββββββββββββββββββββ
β ateam-mcp β
β 12 tools β spec, validate, deploy, manage β
ββββββββββββββββββββ¬βββββββββββββββββββββββββββ
β HTTPS
β X-ADAS-TENANT / X-API-KEY
ββββββββββββββββββββΌβββββββββββββββββββββββββββ
β ADAS External Agent API β
β api.ateam-ai.com β
ββββββββββββββββββββ¬βββββββββββββββββββββββββββ
β
ββββββββββββββββββββΌβββββββββββββββββββββββββββ
β ADAS Core β
β Multi-agent runtime β
βββββββββββββββββββββββββββββββββββββββββββββββ
License
MIT
