AutobotX MCP Server

AutobotX MCP Server

Provides access to 141 operational workflows across 17 departments, an intelligent guide bot, real-time communities, document processing, and organizational state management through MCP tools.

Category
访问服务器

README

AutobotX

The all in one enabled system for CFAO Mobility Nigeria.

AutobotX puts 141 operational workflows, an intelligent guide bot named AutoX, live department communities, direct messaging, document processing, and a full Model Context Protocol hub in front of every team in the organization.

Live application: https://autobotx-hnctut.v2.appdeploy.ai/

AutobotX MCP endpoint: https://api-v2.appdeploy.ai/app/autobotx-hnctut/api/mcp

What is inside

  • 17 department bays covering Sales and Distribution, Marketing and Communications, Finance and Accounting, Human Resources, Legal and Compliance, Operations and Logistics, Customer Support and Aftersales, Engineering and IT, Data and Analytics, Design and Experience, Product Management, Enterprise Knowledge, Productivity and Planning, Business Operations, Research and Innovation, Plugin Studio, and the Document Center.
  • 141 workflow skills sourced from the knowledge work plugins catalog. Every skill runs as a structured form: an objective field, a context field, and a drag and drop document zone.
  • AutoX, a guide bot that knows the full catalog and routes any request to the right workflow with one click buttons.
  • Individual user accounts with a personal history of every workflow run, AutoX exchange, and external tool call.
  • A departments dropdown where anyone can join a department community. Each community is a live, synchronized channel, and colleagues who share a department can message each other directly in real time.
  • Document upload in PDF, DOCX, PPTX, XLSX, CSV, TXT and image formats. Every deliverable downloads as DOCX, PPTX, XLSX, CSV or TXT.
  • A dedicated MCP server handling core organizational state, plus the ability to accept, connect and route requests to any external MCP server.
  • A strict plain text output contract: model prompts and a server side sanitizer keep markdown artifacts out of every input and output.

Architecture

The app targets the AppDeploy platform (frontend plus backend).

  • frontend: React 19, Vite, Tailwind CSS, HashRouter. Pages live in src/pages, shared UI in src/components, state and helpers in src/lib.
  • backend/index.ts: API routes for profiles, departments, community channels, direct messages, workflow runs, history, document extraction, the MCP registry and organizational state.
  • backend/brain.ts: the AI engine. Builds the per skill system prompts, runs AutoX, and scrubs every output.
  • backend/mcp.ts: the AutobotX MCP server (JSON-RPC 2.0 over streamable HTTP) and the proxy that connects external MCP servers.
  • backend/catalog.ts: the generated catalog of 17 departments and 141 skills.
  • Realtime updates flow over WebSockets through the entity subscription pattern in backend/realtime-subscribers.ts.

Note: the platform injects the AppDeploy SDK packages at deploy time, so this repository intentionally does not list them in package.json and will not build standalone without the AppDeploy toolchain.

Design

A workshop and showroom identity: asphalt ink surfaces, concrete grey work areas, CFAO signal red, Saira Semi Condensed display type with IBM Plex Sans and IBM Plex Mono, departments presented as numbered service bays, and a hazard tape signature stripe.

MCP tools

The AutobotX MCP server exposes six tools to any connected client: list_departments, list_skills, run_skill, autox_guide, org_state_get and org_state_set.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选