Ghostshell MCP Server

Run AI-powered conjoint experiments from Claude, Cursor, or any MCP-compatible client. Understand **why** people make decisions using causal

Remote serverstreamable-httpPython

What is the Ghostshell MCP server?

Run AI-powered conjoint experiments from Claude, Cursor, or any MCP-compatible client. Understand why people make decisions using causal inference and synthetic populations. The ghostshell mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 14 defined tools rather than through you.

Its toolset

Everything the assistant can do here goes through one of these:

  • check_causality — Validate that a research question is causal
  • generate_attributes_levels — Generate experiment attributes and levels using AI
  • validate_population — Validate target population demographics
  • get_population_stats — Get population statistics for a country
  • create_experiment — Create and run a conjoint experiment
  • get_experiment_status — Check experiment progress
  • list_experiments — List all your experiments
  • get_experiment_results — Get detailed experiment results
  • get_run_details — Get detailed run information
  • get_run_artifacts — Get run artifacts and files
  • update_run_config — Update run configuration
  • generate_personas — Generate AI personas for an experiment

Adding it to your client

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

Configuration

You will need 3 environment variables: AUTH0_JWT_TOKEN, API_BASE_URL, YOUR_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

When to reach for it

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Ghostshell's toolset — check_causality, generate_attributes_levels, validate_population and 11 more — is a fair guide to whether it matches your workflow. It is maintained by subconscious-ai; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Ghostshell.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the ghostshell mcp server does with a few real requests.

Available tools

ToolWhat it does
check_causalityValidate that a research question is causal
generate_attributes_levelsGenerate experiment attributes and levels using AI
validate_populationValidate target population demographics
get_population_statsGet population statistics for a country
create_experimentCreate and run a conjoint experiment
get_experiment_statusCheck experiment progress
list_experimentsList all your experiments
get_experiment_resultsGet detailed experiment results
get_run_detailsGet detailed run information
get_run_artifactsGet run artifacts and files
update_run_configUpdate run configuration
generate_personasGenerate AI personas for an experiment
get_experiment_personasGet personas for an experiment
get_amce_dataGet AMCE analytics data

How to install the Ghostshell MCP server

Add to your MCP config:
```json
{
  "mcpServers": {
    "subconscious-ai": {
      "command": "/absolute/path/to/venv/bin/python3",
      "args": ["/absolute/path/to/server/main.py"],
      "env": {
        "AUTH0_JWT_TOKEN": "your_token",
        "API_BASE_URL": "https://api.subconscious.ai"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
AUTH0_JWT_TOKENCredential the server authenticates with.Yes
API_BASE_URLEndpoint or connection string the server talks to.Yes
YOUR_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use Ghostshell to check causality.
  • Use Ghostshell to generate attributes levels.
  • Use Ghostshell to validate population.

Frequently asked questions

It connects Ghostshell to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (check_causality, generate_attributes_levels, validate_population, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Ghostshell directly.