Subconscious Ai MCP Server

@subconscious-ai

代码仓库

基本信息

分类

其他

传输方式

stdio

认证方式

oauth

作者

subconscious-ai

提交者

Nihar Shah

关于 Subconscious Ai MCP Server

Run conjoint experiments and causal research through AI-powered behavioral simulations

#subconscious-ai#behavioral-simulation#causal-research

Subconscious Ai MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "subconscious-ai": {
      "url": "https://ghostshell-runi.vercel.app/api/sse?token=YOUR_TOKEN"
    }
  }
}

Subconscious Ai MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

此服务需要认证，获取工具列表可能需要登录或使用服务提供方的凭据。

点击上方按钮,直接连接服务器端点实时获取工具列表。

概览

What is Subconscious Ai Mcp?

Subconscious Ai Mcp is an MCP (Model Context Protocol) server that lets you run AI-powered conjoint experiments from Claude Desktop, Cursor, or any MCP-compatible client. It uses causal inference and synthetic populations based on US Census microdata to help understand why people make decisions.

How to use Subconscious Ai Mcp?

You can use the hosted server by adding a URL with a token to your MCP client configuration (Claude Desktop or Cursor), or run it locally by cloning the repo, installing dependencies with Python 3.11+, and setting environment variables AUTH0_JWT_TOKEN and API_BASE_URL. Tokens are obtained from app.subconscious.ai.

Key features of Subconscious Ai Mcp

Causal research: validate research questions and generate statistically valid experiments
Synthetic populations: AI personas based on US Census microdata (IPUMS)
Conjoint analysis: AMCE for measuring attribute importance
Works with Claude Desktop, Cursor, and any MCP-compatible client
REST API with direct HTTP access for integrations (n8n, Zapier)
Real-time updates via Server-Sent Events for live experiment progress

Use cases of Subconscious Ai Mcp

Validate whether a research question is causal before running an experiment
Generate experiment attributes and levels (e.g., for an EV preference study)
Run a conjoint experiment with synthetic respondents and get AMCE analytics
Get AI-generated causal insights and key findings from completed experiments
Integrate experiment creation into no-code automation tools like n8n

常见问题

What runtime and dependencies are required?

Python 3.11+ is required for local execution. Dependencies are listed in `requirements.txt` and installed via pip.

How does authentication work?

You need an active Subconscious AI subscription. For the hosted server, include your token as a query parameter in the SSE URL. For local setup, set the `AUTH0_JWT_TOKEN` environment variable.

Where does experiment data live?

The server proxies requests to the Subconscious AI backend (`https://api.subconscious.ai`). Self-hosted deployments also route through this backend; user data is not stored on the MCP server itself.

What transports and protocols are supported?

The server supports MCP via SSE (Server-Sent Events) and also provides a REST API at `/api/call/{tool}` endpoints. Both require authentication.

Is there a limit to the number of experiments or respondents?

The README mentions experiments can be created with a specified confidence level (e.g., "Reasonable"), but does not state explicit quantitative limits. The platform surveys synthetic respondents (e.g., 500 per experiment).

其他分类下的更多 MCP 服务器

Klarix Intelligence Engine

Klarix

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

Volley.sh

Volley

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi