{"id":49029551,"url":"https://github.com/ariekogan/ateam-mcp","last_synced_at":"2026-06-03T16:00:45.497Z","repository":{"id":339073748,"uuid":"1160231149","full_name":"ariekogan/ateam-mcp","owner":"ariekogan","description":"ADAS MCP Server — build, validate, and deploy multi-agent solutions from any AI environment","archived":false,"fork":false,"pushed_at":"2026-05-12T10:27:22.000Z","size":507,"stargazers_count":0,"open_issues_count":1,"forks_count":3,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-12T11:09:38.180Z","etag":null,"topics":["adas","ai-agents","mcp","mcp-server","model-context-protocol","multi-agent"],"latest_commit_sha":null,"homepage":null,"language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ariekogan.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-02-17T17:38:11.000Z","updated_at":"2026-05-12T09:56:33.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/ariekogan/ateam-mcp","commit_stats":null,"previous_names":["ariekogan/ateam-mcp"],"tags_count":40,"template":false,"template_full_name":null,"purl":"pkg:github/ariekogan/ateam-mcp","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ariekogan%2Fateam-mcp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ariekogan%2Fateam-mcp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ariekogan%2Fateam-mcp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ariekogan%2Fateam-mcp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ariekogan","download_url":"https://codeload.github.com/ariekogan/ateam-mcp/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ariekogan%2Fateam-mcp/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33872298,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-03T02:00:06.370Z","response_time":59,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["adas","ai-agents","mcp","mcp-server","model-context-protocol","multi-agent"],"created_at":"2026-04-19T09:00:40.492Z","updated_at":"2026-06-03T16:00:45.487Z","avatar_url":"https://github.com/ariekogan.png","language":"JavaScript","funding_links":[],"categories":["AI Integration MCP Servers","📦 Other"],"sub_categories":[],"readme":"# ateam-mcp\n\n**Give any AI the ability to build, validate, and deploy production multi-agent systems.**\n\nThis is an MCP server that connects AI assistants — ChatGPT, Claude, Gemini, Copilot, Cursor, Windsurf, and any MCP-compatible environment — directly to the [ADAS](https://ateam-ai.com) platform.\n\nAn 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.\n\n## Why this matters\n\nToday, 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.\n\nThe AI assistant becomes the developer interface:\n\n```\nDeveloper: \"Create an identity verification agent that checks documents,\n            validates faces, and escalates fraud cases\"\n\nAI Assistant:\n  → reads ADAS spec (adas_get_spec)\n  → studies working examples (adas_get_examples)\n  → builds skill + solution definitions\n  → validates iteratively (adas_validate_skill, adas_validate_solution)\n  → deploys to production (adas_deploy_solution)\n  → verifies everything is running (adas_get_solution → health)\n\nDeveloper: \"Add a new skill that handles address verification\"\n\nAI Assistant:\n  → deploys into the existing solution (adas_deploy_skill)\n  → redeploys (adas_redeploy)\n  → confirms health\n```\n\nNo context switching. No manual steps. The full ADAS platform — specs, validation, deployment, monitoring — is available as natural language.\n\n## How it reaches the AI community\n\n### ChatGPT users\n\nChatGPT supports MCP connectors in Developer Mode. Users connect by pasting a single URL:\n\n**Settings → Connectors → Developer Mode → paste `https://mcp.ateam-ai.com`**\n\nThat'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.\n\n### Claude users\n\n**Claude Desktop** — install as an extension (one-click) or add to config:\n\n```json\n{\n  \"mcpServers\": {\n    \"ateam\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@ateam-ai/mcp\"],\n      \"env\": {\n        \"ADAS_TENANT\": \"your-tenant\",\n        \"ADAS_API_KEY\": \"your-api-key\"\n      }\n    }\n  }\n}\n```\n\n**Claude Code** — one command:\n\n```bash\nclaude mcp add ateam -- npx -y @ateam-ai/mcp\n```\n\n### Cursor / Windsurf / VS Code (Copilot)\n\nAdd to `.cursor/mcp.json`, `mcp_config.json`, or `.vscode/mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"ateam\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@ateam-ai/mcp\"],\n      \"env\": {\n        \"ADAS_TENANT\": \"your-tenant\",\n        \"ADAS_API_KEY\": \"your-api-key\"\n      }\n    }\n  }\n}\n```\n\n### Gemini and other platforms\n\nAs 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.\n\n### Discovery\n\nDevelopers find ateam-mcp through:\n\n- **npm** — `npm search mcp ai-agents` → `@ateam-ai/mcp`\n- **Official MCP Registry** — registry.modelcontextprotocol.io\n- **Claude Desktop Extensions** — built-in extension browser\n- **Claude Code Plugin Marketplace** — `/plugin` → Discover tab\n- **Windsurf MCP Marketplace** — built-in marketplace\n- **VS Code MCP Gallery** — Extensions view\n- **Community directories** — Smithery, mcp.so, PulseMCP (30,000+ combined listings)\n\n## Available tools\n\n| Tool | What it does |\n|---|---|\n| `adas_get_spec` | Read the ADAS specification — skill schema, solution architecture, enums, agent guides |\n| `adas_get_examples` | Get complete working examples — skills, connectors, solutions |\n| `adas_validate_skill` | Validate a skill definition through the 5-stage pipeline |\n| `adas_validate_solution` | Validate a solution — cross-skill contracts + quality scoring |\n| `adas_deploy_solution` | Deploy a complete solution to production |\n| `adas_deploy_skill` | Add a skill to an existing solution |\n| `adas_deploy_connector` | Deploy a connector to ADAS Core |\n| `adas_list_solutions` | List all deployed solutions |\n| `adas_get_solution` | Inspect a solution — definition, skills, health, status, export |\n| `adas_update` | Update a solution or skill incrementally (PATCH) |\n| `adas_redeploy` | Push changes live — regenerates MCP servers, deploys to ADAS Core |\n| `adas_solution_chat` | Talk to the Solution Bot for guided modifications |\n\n## Setup\n\n```bash\n# Clone\ngit clone https://github.com/ariekogan/ateam-mcp.git\ncd ateam-mcp\n\n# Install\nnpm install\n\n# Configure\ncp .env.example .env\n# Edit .env with your ADAS tenant and API key\n\n# Run\nnpm start\n```\n\n## Architecture\n\n```\n┌─────────────────────────────────────────────┐\n│  AI Environment                             │\n│  (ChatGPT / Claude / Cursor / Windsurf)     │\n│                                             │\n│  Developer: \"build me a support system\"     │\n└──────────────────┬──────────────────────────┘\n                   │ MCP protocol\n                   │ (stdio or HTTP)\n┌──────────────────▼──────────────────────────┐\n│  ateam-mcp                                  │\n│  12 tools — spec, validate, deploy, manage  │\n└──────────────────┬──────────────────────────┘\n                   │ HTTPS\n                   │ X-ADAS-TENANT / X-API-KEY\n┌──────────────────▼──────────────────────────┐\n│  ADAS External Agent API                    │\n│  api.ateam-ai.com                           │\n└──────────────────┬──────────────────────────┘\n                   │\n┌──────────────────▼──────────────────────────┐\n│  ADAS Core                                  │\n│  Multi-agent runtime                        │\n└─────────────────────────────────────────────┘\n```\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fariekogan%2Fateam-mcp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fariekogan%2Fateam-mcp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fariekogan%2Fateam-mcp/lists"}