Obscura MCP Server
@madeinphantom
About Obscura MCP Server
About
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"obscura": {
"command": "npx",
"args": [
"-y",
"@obscuraai/mcp-server"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Obscura MCP Server?
This MCP server connects your AI assistant or coding agent to Obscura AI's Workflow Builder. When you describe a business process, it generates an interactive visual workflow and returns a shareable link to edit, export, and share the flow. No API key or signup is required.
How to use Obscura MCP Server?
Configure the server in your MCP-compatible client (Claude Desktop, Claude Code, Cursor, Windsurf, Cline, or any stdio client) by adding the command npx -y @obscuraai/mcp-server. For HTTP use, send POST requests to https://obscuraai.xyz/api/mcp with no auth. Then ask your agent to map out any business automation.
Key features of Obscura MCP Server
- Generates visual workflows from simple text descriptions
- Returns a shareable link to an interactive, editable canvas
- No signup, no API key, and no cost
- Supports 14 pre‑built industry‑aware workflow templates
- Works with Claude Desktop, Claude Code, Cursor, Windsurf, and more
- Compatible with both stdio (JSON‑RPC) and HTTP transports
Use cases of Obscura MCP Server
- Map out a guest check‑in automation for a hotel
- Design a lead qualification pipeline for a creative agency
- Build a document processing flow for a law firm
- Create a tenant maintenance request workflow for property management
FAQ from Obscura MCP Server
Do I need an API key or to sign up?
No. The server works immediately without any authentication or registration. It is free to use.
Which clients are supported?
Claude Desktop, Claude Code (CLI), Cursor, Windsurf, Cline, Continue.dev, Zed, and any MCP stdio client. It can also be called directly via HTTP from LangChain, CrewAI, or custom LLMs.
How do I install it?
The server runs via npx. Add it to your client's MCP configuration with the command npx -y @obscuraai/mcp-server. Specific config file locations are provided for each client in the setup instructions.
Is there a cost?
No, the server is provided at no cost. No payment or account is required.
What transport does it use?
It supports stdio (JSON‑RPC over stdin/stdout) for local agents and HTTP (POST to https://obscuraai.xyz/api/mcp) for remote or framework‑based agents. No authentication is needed for either transport.
Frequently asked questions
Do I need an API key or to sign up?
No. The server works immediately without any authentication or registration. It is free to use.
Which clients are supported?
Claude Desktop, Claude Code (CLI), Cursor, Windsurf, Cline, Continue.dev, Zed, and any MCP stdio client. It can also be called directly via HTTP from LangChain, CrewAI, or custom LLMs.
How do I install it?
The server runs via npx. Add it to your client's MCP configuration with the command `npx -y @obscuraai/mcp-server`. Specific config file locations are provided for each client in the setup instructions.
Is there a cost?
No, the server is provided at no cost. No payment or account is required.
What transport does it use?
It supports stdio (JSON‑RPC over stdin/stdout) for local agents and HTTP (POST to `https://obscuraai.xyz/api/mcp`) for remote or framework‑based agents. No authentication is needed for either transport.
Basic information
More Other MCP servers
Inbox Zero AI
elie222The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.
XcodeBuildMCP
cameroncookeA Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
Activepieces
activepiecesAI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
FastMCP v2 🚀
jlowin🚀 The fast, Pythonic way to build MCP servers and clients.
Nginx UI
0xJackyYet another WebUI for Nginx
Comments