obscuraai-mcp

obscuraai-mcp

MCP server for Claude, ChatGPT, coding agents (cursor, claude code etc), windsurf, etc— generate visual AI automation workflows. Describe a business process, get an interactive flow map you can edit and share.

Category
访问服务器

README

Obscura AI — AI Workflow Generator for Any LLM or Coding Agent

Describe any business process. Get a visual AI automation workflow you can edit, export, and share — inside Claude, Cursor, Windsurf, your terminal, or any MCP-compatible client.

Try the Builder free | Website


What this does

This MCP server connects your AI assistant or coding agent to Obscura AI's Workflow Builder. When you ask it to map out a business automation, it generates an interactive visual workflow and gives you a link to open, edit, and share it.

No API key. No signup. No cost.

Example

You: "Map out an automation for guest check-in at my hotel"

Claude / Cursor / your agent: Here's your workflow — 6 steps covering booking confirmation through post-stay review.

Open your workflow: https://obscuraai.xyz/builder?d=eJxVjk...

The link opens a visual canvas where you can drag nodes, edit labels, and export or share the flow.


Compatible clients

Client Type
Claude Desktop Desktop app
Claude Code CLI / terminal
Cursor IDE
Windsurf IDE
Cline VS Code extension
Continue.dev VS Code / JetBrains
Zed Editor
Any MCP stdio client CLI / custom agents
HTTP direct LangChain, CrewAI, custom LLMs

Supported industries

Industry Example workflows
Hospitality Guest comms, table reservations, supplier coordination, event planning
Real Estate Property pipeline, tenant management, document processing
Agencies Client onboarding, content pipeline, lead qualification
Legal Document intelligence, case intake, compliance
Finance KYC checks, reporting pipelines, invoice automation

14 pre-built workflow templates with industry-aware label customization.


Setup

Claude Desktop

Add to your config file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "obscura": {
      "command": "npx",
      "args": ["-y", "@obscuraai/mcp-server"]
    }
  }
}

Restart Claude Desktop. You'll see "obscura" in your connected tools.

Claude Code (CLI)

claude mcp add obscura -- npx -y @obscuraai/mcp-server

Cursor / Windsurf / Cline

Add to your MCP settings (usually mcp.json or equivalent):

{
  "mcpServers": {
    "obscura": {
      "command": "npx",
      "args": ["-y", "@obscuraai/mcp-server"]
    }
  }
}

Terminal / custom agent (stdio)

npx -y @obscuraai/mcp-server

The server speaks JSON-RPC over stdin/stdout — pipe messages directly from any agent.

HTTP endpoint (LangChain, CrewAI, custom LLMs)

POST https://obscuraai.xyz/api/mcp
Content-Type: application/json

No auth required. Call it from any HTTP-capable agent or LLM framework.


Tool reference

generate_obscura_workflow

Generates a visual workflow and returns a shareable link to the interactive canvas.

Parameter Type Required Description
description string Yes The business process to automate
industry string No hospitality, real-estate, agencies, professional-services, finance, legal, events, other

Try asking your agent:

  • "Map out an automation for lead qualification at my agency"
  • "Design a guest communications workflow for a Dubai hotel"
  • "Build a document processing pipeline for a law firm"
  • "Create a tenant maintenance request flow for property management"

About Obscura AI

Obscura AI builds custom AI workflows, agents, and automations for modern businesses. We deploy systems in days, not months.

Founder: Prince Adza

Markets served: Dubai, Monte Carlo, South Africa, Singapore, London, and expanding across North America and Europe.


License

MIT

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