Summary
Bridges Claude, ChatGPT, Cursor, and other AI assistants directly to the ADAS multi-agent platform. Exposes twelve tools that let your AI read the ADAS spec, validate skill and solution definitions through a five-stage pipeline, deploy to production, and monitor health. The workflow is conversational: describe a customer support system with escalation, and the assistant builds the skill definitions, validates them, deploys, and confirms everything is running. No manual JSON authoring or dashboard hopping. Works over stdio for local setups or streamable HTTP at mcp.ateam-ai.com for remote access. Particularly useful if you're building production agent systems on ADAS and want to stay in your editor or chat interface instead of context switching to docs and deployment tools.
Keeps your Mac awake while Claude Code, Codex or Cursor works. Lets it sleep when they are done.
Try free for 7 days →
Block distracting apps from your iPhone permanently without a 3rd party app. Free and open source.
Block now (100% free) →
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Free an open-source skills that make AI coding agents easier to understand, verify, and control.
Download for free →
Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →Tools
Public tool metadata for what this MCP can expose to an agent.
12 tools
adas_get_specGet the ADAS specification — schemas, validation rules, system tools, agent guides, and templates. Use this to understand how to build skills and solutions.1 params
Get the ADAS specification — schemas, validation rules, system tools, agent guides, and templates. Use this to understand how to build skills and solutions.
Parameters* required
topicstringWhat to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum valuesone of
overview · skill · solution · enumsadas_get_examplesGet complete working examples that pass validation. Study these before building your own.1 params
Get complete working examples that pass validation. Study these before building your own.
Parameters* required
typestringExample type: 'skill' = Order Support Agent, 'connector' = stdio MCP connector, 'connector-ui' = UI-capable connector, 'solution' = full 3-skill e-commerce solution, 'index' = list all available ex...one of
skill · connector · connector-ui · solution · indexadas_validate_skillValidate a skill definition through the 5-stage ADAS validation pipeline. Returns errors and suggestions to fix.1 params
Validate a skill definition through the 5-stage ADAS validation pipeline. Returns errors and suggestions to fix.
Parameters* required
skillobjectThe full skill definition object to validate
adas_validate_solutionValidate a solution definition — cross-skill contracts, grant economy, handoffs, and LLM quality scoring.2 params
Validate a solution definition — cross-skill contracts, grant economy, handoffs, and LLM quality scoring.
Parameters* required
skillsarrayArray of skill definitions included in the solution
solutionobjectThe full solution definition object to validate
adas_deploy_solutionDeploy a complete solution to ADAS Core — identity, connectors, skills. The Skill Builder auto-generates MCP servers from tool definitions. This is the main deployment action.4 params
Deploy a complete solution to ADAS Core — identity, connectors, skills. The Skill Builder auto-generates MCP servers from tool definitions. This is the main deployment action.
Parameters* required
connectorsarrayArray of connector metadata (id, name, transport, command, args)
mcp_storeobjectOptional: connector source code files. Key = connector id, value = array of {path, content}
skillsarrayArray of full skill definitions
solutionobjectSolution architecture — identity, grants, handoffs, routing
adas_deploy_skillDeploy a single skill into an existing solution.2 params
Deploy a single skill into an existing solution.
Parameters* required
skillobjectFull skill definition
solution_idstringThe existing solution ID to add the skill to
adas_deploy_connectorDeploy a connector — registers in the Skill Builder catalog and connects in ADAS Core.1 params
Deploy a connector — registers in the Skill Builder catalog and connects in ADAS Core.
Parameters* required
connectorobjectConnector metadata (id, name, transport, command, args)
adas_list_solutionsList all solutions deployed in the Skill Builder.
List all solutions deployed in the Skill Builder.
No parameter schema in public metadata yet.
adas_get_solutionRead solution state — definition, skills, health, status, or export. Use this to inspect deployed solutions.3 params
Read solution state — definition, skills, health, status, or export. Use this to inspect deployed solutions.
Parameters* required
skill_idstringOptional: read a specific skill by ID (original or internal)
solution_idstringThe solution ID
viewstringWhat to read: 'definition' = full solution def, 'skills' = list skills, 'health' = live health check, 'status' = deploy status, 'export' = exportable bundle, 'validate' = re-validate from stored st...one of
definition · skills · health · status · export · validateadas_updateUpdate a deployed solution or skill incrementally using PATCH. Supports dot notation for scalar fields and _push/_delete/_update for arrays.4 params
Update a deployed solution or skill incrementally using PATCH. Supports dot notation for scalar fields and _push/_delete/_update for arrays.
Parameters* required
skill_idstringRequired when target is 'skill'
solution_idstringThe solution ID
targetstringWhat to update: 'solution' or 'skill'one of
solution · skillupdatesobjectThe update payload — use dot notation for scalars (e.g. 'problem.statement'), and tools_push/tools_delete/tools_update for array operations
adas_redeployRe-deploy after making updates. Regenerates MCP servers and pushes to ADAS Core.2 params
Re-deploy after making updates. Regenerates MCP servers and pushes to ADAS Core.
Parameters* required
skill_idstringOptional: redeploy a single skill. Omit to redeploy all skills.
solution_idstringThe solution ID
adas_solution_chatSend a message to the Solution Bot — an AI assistant that understands your deployed solution and can help with modifications.2 params
Send a message to the Solution Bot — an AI assistant that understands your deployed solution and can help with modifications.
Parameters* required
messagestringYour message to the Solution Bot
solution_idstringThe solution ID
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 — ChatGPT, Claude, Gemini, Copilot, Cursor, Windsurf, and any MCP-compatible environment — directly to the ADAS platform.
An AI developer says "Build me a customer support system with order tracking and escalation" — 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:
→ reads ADAS spec (adas_get_spec)
→ studies working examples (adas_get_examples)
→ builds skill + solution definitions
→ validates iteratively (adas_validate_skill, adas_validate_solution)
→ deploys to production (adas_deploy_solution)
→ verifies everything is running (adas_get_solution → health)
Developer: "Add a new skill that handles address verification"
AI Assistant:
→ deploys into the existing solution (adas_deploy_skill)
→ redeploys (adas_redeploy)
→ confirms health
No context switching. No manual steps. The full ADAS platform — specs, validation, deployment, monitoring — 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 → Connectors → Developer Mode → 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.ai and Claude Desktop — add the hosted connector: open Customize > Connectors (Claude Desktop: Customize in the sidebar, then Connectors), click Add custom connector, enter https://mcp.ateam-ai.com, and click Connect. The A-Team sign-in page opens in the browser and asks for your workspace's key: copy it from app.ateam-ai.com/connect (a workspace owner or admin) and paste it there. The key decides the workspace; to switch, Disconnect and Connect again with the other workspace's key.
Claude Code — the hosted connector, signed in the same way:
claude mcp add --transport http ateam https://mcp.ateam-ai.com
then /mcp and authenticate in the browser.
Never paste a key into a chat. ateam_bootstrap's session field says which workspace a session is on and how to switch.
Cursor / Windsurf / VS Code (Copilot)
Add the hosted server to .cursor/mcp.json, mcp_config.json, or .vscode/mcp.json:
{
"mcpServers": {
"ateam": { "url": "https://mcp.ateam-ai.com/mcp" }
}
}
A client with OAuth opens the A-Team sign-in page; one without sends the key as Authorization: Bearer <key> from its own config (see below). A local process (npx -y @ateam-ai/mcp) signs in only through ateam_auth: an ADAS_API_KEY in its environment does not sign it in.
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, also at /mcp) works with any client that supports Streamable HTTP transport.
The HTTP endpoint needs a credential on every request: OAuth (clients that support it follow the 401 challenge on their own), or your A-Team API key sent as Authorization: Bearer <key>. An anonymous request is refused with 401; since 0.4.93 there is no anonymous session to call ateam_auth from. See CHANGELOG.md.
Discovery
Developers find ateam-mcp through:
- npm —
npm search mcp ai-agents→@ateam-ai/mcp - Official MCP Registry — registry.modelcontextprotocol.io
- Claude Desktop Extensions — built-in extension browser
- Claude Code Plugin Marketplace —
/plugin→ Discover tab - Windsurf MCP Marketplace — built-in marketplace
- VS Code MCP Gallery — Extensions view
- Community directories — Smithery, mcp.so, PulseMCP (30,000+ combined listings)
Available tools
| Tool | What it does |
|---|---|
adas_get_spec | Read the ADAS specification — skill schema, solution architecture, enums, agent guides |
adas_get_examples | Get complete working examples — skills, connectors, solutions |
adas_validate_skill | Validate a skill definition through the 5-stage pipeline |
adas_validate_solution | Validate a solution — 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 — definition, skills, health, status, export |
adas_update | Update a solution or skill incrementally (PATCH) |
adas_redeploy | Push changes live — regenerates MCP servers, deploys to ADAS Core |
adas_solution_chat | Talk to the Solution Bot for guided modifications |
ateam_workspace_open | For a chat agent with no shell: open one private workspace (files in /workspace) for the conversation |
ateam_workspace_exec | Run one command in the workspace (100 s foreground; run_in_background for long builds) |
ateam_workspace_status | Check the workspace: unsaved changes, a long save or background command |
ateam_workspace_save | Make the workspace's work live (the only way the other tools see it) |
ateam_workspace_close | Finish; optionally save first. Brings back the single-file write tools withheld while it was open |
The ateam_workspace_* tools are listed whenever you are signed in. A workspace the platform cannot give (a trial workspace, a key tied to no person) is refused by the call itself, with the single-file tools to use instead.
Setup
# Clone
git clone https://github.com/ariekogan/ateam-mcp.git
cd ateam-mcp
# Install
npm install
# Run (a local stdio process)
npm start
A local process signs in with ateam_auth, given a workspace key the agent reads from a file outside the chat; an ADAS_API_KEY in the environment does not sign it in and is never sent. ADAS_API_URL in its environment points it at a self-hosted API. Most people use the hosted connector instead (above).
Architecture
┌─────────────────────────────────────────────┐
│ AI Environment │
│ (ChatGPT / Claude / Cursor / Windsurf) │
│ │
│ Developer: "build me a support system" │
└──────────────────┬──────────────────────────┘
│ MCP protocol
│ (stdio or HTTP)
┌──────────────────▼──────────────────────────┐
│ ateam-mcp │
│ 12 tools — spec, validate, deploy, manage │
└──────────────────┬──────────────────────────┘
│ HTTPS
│ X-ADAS-TENANT / X-API-KEY
┌──────────────────▼──────────────────────────┐
│ ADAS External Agent API │
│ api.ateam-ai.com │
└──────────────────┬──────────────────────────┘
│
┌──────────────────▼──────────────────────────┐
│ ADAS Core │
│ Multi-agent runtime │
└─────────────────────────────────────────────┘
License
MIT
Featured
Keeps your Mac awake while Claude Code, Codex or Cursor works. Lets it sleep when they are done.
Try free for 7 days →Block distracting apps from your iPhone permanently without a 3rd party app. Free and open source.
Block now (100% free) →Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Free an open-source skills that make AI coding agents easier to understand, verify, and control.
Download for free →Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →Categories
Registryactive
Package@ateam-ai/mcp
TransportSTDIO, HTTP
UpdatedFeb 17, 2026
