Ateam Mcp

io.github.ariekoganPublished by GitHub account ariekoganv0.1.2Updated Oct 24, 2026

Build, validate, and deploy multi-agent AI solutions from any AI environment.

VerifiedStreamable HTTPWeb executableCloud & InfrastructureDeveloper ToolsAI & ML

Overview

AI-generated overview

Connects an AI assistant to the ADAS platform so it can read specs, build, validate and deploy multi-agent solutions and skills.

What you can do
  • Read the ADAS specification and complete working examples for skills, connectors and solutions
  • Validate skill definitions and whole solutions, including cross-skill contracts and quality scoring
  • Deploy solutions, add skills to existing solutions, deploy connectors, and redeploy changes live
  • List and inspect deployed solutions, including definition, skills, health, status and export
  • Update solutions or skills incrementally and chat with a Solution Bot for guided modifications
  • Open a private workspace, run commands in it, check status, save work and close it
When to use it
Useful when you want an assistant to author and ship multi-agent systems on the ADAS platform without hand-writing JSON or switching between docs, editors and dashboards. Also fits iterative work where an assistant validates, deploys and checks the health of skills and solutions.
Requirements
A remote Streamable HTTP endpoint or the local npm package run with npx; OAuth sign-in or an A-Team workspace API key sent as an Authorization Bearer header on every request. A workspace key from an owner or admin is needed, and the local process signs in only through its auth tool. Network access to the ADAS API.
Before you install
Deploy, redeploy, update and workspace save actions change live production systems. The workspace key grants access to a whole workspace, so keep it out of chats and pass it through sign-in or client config. Workspace exec runs arbitrary commands in a hosted workspace, and requests are forwarded to the ADAS platform and API.

Installation

In SourceWeft

  1. Open Ateam Mcp in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.ariekogan%2Fateam-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "ateam": {
      "type": "http",
      "url": "https://mcp.ateam-ai.com/mcp"
    }
  }
}

README

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:

bash
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:

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

ToolWhat it does
adas_get_specRead the ADAS specification — skill schema, solution architecture, enums, agent guides
adas_get_examplesGet complete working examples — skills, connectors, solutions
adas_validate_skillValidate a skill definition through the 5-stage pipeline
adas_validate_solutionValidate a solution — cross-skill contracts + quality scoring
adas_deploy_solutionDeploy a complete solution to production
adas_deploy_skillAdd a skill to an existing solution
adas_deploy_connectorDeploy a connector to ADAS Core
adas_list_solutionsList all deployed solutions
adas_get_solutionInspect a solution — definition, skills, health, status, export
adas_updateUpdate a solution or skill incrementally (PATCH)
adas_redeployPush changes live — regenerates MCP servers, deploys to ADAS Core
adas_solution_chatTalk to the Solution Bot for guided modifications
ateam_workspace_openFor a chat agent with no shell: open one private workspace (files in /workspace) for the conversation
ateam_workspace_execRun one command in the workspace (100 s foreground; run_in_background for long builds)
ateam_workspace_statusCheck the workspace: unsaved changes, a long save or background command
ateam_workspace_saveMake the workspace's work live (the only way the other tools see it)
ateam_workspace_closeFinish; 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

bash
# Clonegit clone https://github.com/ariekogan/ateam-mcp.gitcd ateam-mcp
# Installnpm 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

Source: README.md at commit 03c419d

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v0.1.2LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.