aacworkflow-mcp
Enables Claude and Claude Code to manage AACWorkflow tasks, agents, projects, squads, autopilots, and analytics through natural language.
README
aacworkflow-mcp
MCP server that lets Claude and Claude Code drive AACWorkflow: tasks (issues), agents, projects, squads, autopilots and analytics.
Bring your own token. Every user runs their own copy with their own AACWorkflow token — there is no shared server and no central credential store. Your token scopes you to the workspaces (companies) you belong to, and you can drive several from one install.
Quick start (any AACWorkflow user)
-
Create a token: aacworkflow.com → your workspace → Settings → Tokens → create. Copy the
mul_…value. -
Connect it to Claude Code (no clone needed — runs straight from GitHub):
claude mcp add aacworkflow --scope user \ -e AACWORKFLOW_TOKEN=mul_your_token \ -- npx -y github:AAChibilyaev/aacworkflow-mcp -
Start a new Claude Code session and ask: "list my aacworkflow agents", "create a task and assign it to the Маркетолог agent", "show this week's usage".
Multiple companies / workspaces
If your token belongs to one workspace it is used automatically. If you belong to several, either:
- set a default: add
-e AACWORKFLOW_WORKSPACE_ID=<id>, or - pass
workspace_idper call — runlist_workspacesfirst to see the ids.
Remote / hosted — work from anywhere (Claude Code, claude.ai, ChatGPT)
The same code also runs as a hosted, multi-tenant HTTP endpoint. Host it once; any registered AACWorkflow user connects with their own token in the Authorization header and drives their own workspaces (companies). No shared credentials.
Run the server
# from source
npm install && npm run build && PORT=8787 npm run start:http
# or Docker
docker build -t aacworkflow-mcp . && docker run -p 8787:8787 aacworkflow-mcp
Put it behind HTTPS (any reverse proxy / Coolify / Cloudflare) → e.g. https://mcp.example.com/mcp.
Endpoints: POST/GET/DELETE /mcp (MCP Streamable HTTP) and GET /health.
Connect from Claude Code (remote)
claude mcp add aacworkflow --transport http https://mcp.example.com/mcp \
--header "Authorization: Bearer mul_your_token"
Connect from ChatGPT (custom connector / developer mode)
Settings → Connectors → Add custom connector → MCP server URL https://mcp.example.com/mcp, auth header Authorization: Bearer mul_your_token.
Marketplace / directory listing
Personal use needs only the hosted URL above. To publish in the directories (Anthropic Connectors directory / OpenAI Apps), the platforms require OAuth 2.1 and a vendor review submitted from your own org account — the bearer-token endpoint here is ready for private/team use today; OAuth can be layered on for public listing.
Claude Desktop
~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"aacworkflow": {
"command": "npx",
"args": ["-y", "github:AAChibilyaev/aacworkflow-mcp"],
"env": { "AACWORKFLOW_TOKEN": "mul_your_token" }
}
}
}
Restart Claude Desktop.
Local install (development)
git clone https://github.com/AAChibilyaev/aacworkflow-mcp
cd aacworkflow-mcp && npm install && npm run build
claude mcp add aacworkflow -e AACWORKFLOW_TOKEN=mul_xxx -- node "$PWD/dist/index.js"
Tools (34)
- Account/workspace:
whoami,list_workspaces,list_members,list_runtimes - Agents:
list_agents,get_agent,create_agent,update_agent,list_agent_templates,create_agent_from_template,list_agent_tasks - Tasks (issues):
list_issues,get_issue,create_issue,update_issue,assign_issue_to_agent,rerun_issue,comment_issue,list_comments,search_issues - Projects / labels:
list_projects,create_project,list_labels,create_label - Squads:
list_squads,get_squad,create_squad - Autopilots:
list_autopilots,get_autopilot,trigger_autopilot,list_autopilot_runs - Analytics:
dashboard_usage_daily,dashboard_usage_by_agent,dashboard_agent_runtime
Dispatch work to an agent:
create_issuewithassignee_type:"agent"+assignee_id, orassign_issue_to_agenton an existing issue — the agent's runtime daemon picks it up and runs it.
Config
| Env | Default | |
|---|---|---|
AACWORKFLOW_TOKEN |
— | required (mul_…) |
AACWORKFLOW_SERVER_URL |
https://aacworkflow.com |
self-hosted? point here |
AACWORKFLOW_WORKSPACE_ID |
— | optional default workspace |
Security
Your token is read only from the environment you pass at install time and sent
only to your AACWORKFLOW_SERVER_URL over HTTPS. It is never written to the
repo, logged, or shared. Revoke it anytime in Settings → Tokens.
MIT licensed.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。