check_causalityLABSCO SUMMARY
Conjoint analysis without recruiting respondents.
The pipeline is the real product: validate the question, generate attributes and personas, run, then read AMCE rather than raw preference counts. Synthetic populations are drawn from Census microdata, so the sample is defensible in a way a prompt asking a model to act as a consumer is not — and the personas an experiment used can be read back beside its findings.
What it is
The MCP front end for Subconscious AI, which runs conjoint experiments against synthetic personas built from US Census microdata (IPUMS) and returns causal estimates. It proxies to the Subconscious AI backend, so the experiment runs there and the tools carry your credential to it.
What you get
- check_causality tests whether a research question supports a causal claim at all, before a run is spent on it.
- generate_attributes_levels turns the question into conjoint attributes and their levels; update_run_config revises a run without rebuilding the design.
- validate_population and get_population_stats check who the sample represents, by country, before the result is treated as representative.
- generate_personas builds the respondents and get_experiment_personas returns the ones a given experiment actually used.
- create_experiment runs the conjoint; get_experiment_status polls it while it works and list_experiments covers everything you have run.
- get_experiment_results, get_run_details and get_run_artifacts return the outcome, the run's detail and its files.
- get_amce_data returns average marginal component effects — which attribute moved the choice and by how much — and get_causal_insights returns the written reading of them.
Requirements
A Subconscious AI account with an active subscription, and an access token. The supported setup runs locally over stdio on Python 3.11 or newer, with the token and the API base address supplied through the environment as AUTH0_JWT_TOKEN and API_BASE_URL — keep that config file private, because it holds a bearer credential. A hosted SSE endpoint exists but the vendor marks it experimental and accepts the credential only in the Authorization header.
Setup effort
Build from source — git clone https://github.com/Subconscious-ai/ghostshell.git
USE CASES
01
Working out which product attribute actually drives the choice
Design a conjoint over the attributes and levels, run it, and read the AMCE estimates instead of guessing from a survey's top line.
02
Checking a research question is answerable before you spend a run
Test whether the question supports a causal claim at all, which is cheaper to learn now than after the data comes back.
03
Making sure the sample looks like the market
Generate the personas, validate the target population and read its statistics before treating the result as representative.
04
Following a long-running experiment
Poll the status while it runs, then pull the results and artifacts when it finishes.
05
Re-running a study with one thing changed
Adjust the run configuration on an existing experiment rather than rebuilding the design around it.
06
Auditing a result you are about to present
Read the causal insights alongside the personas the experiment actually used, so the finding and the sample are seen together.
15 tools
Listed in project docs. Your client may show a different list.
generate_attributes_levelsvalidate_populationget_population_statscreate_experimentget_experiment_statuslist_experimentsget_experiment_resultsget_run_detailsget_run_artifactsupdate_run_configgenerate_personasget_experiment_personasget_amce_dataget_causal_insightsBEFORE YOU INSTALL
What to know first
Tools you get
15 tools named in the project's documentation.
Requires
- Python 3.11+
- AUTH0_JWT_TOKEN in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone this one yourself.
Server setup
TERMINAL
# Clone the repository
git clone https://github.com/Subconscious-ai/ghostshell.git
cd ghostshell
# Create virtual environment
python3 -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install dependencies
pip install -e ".[dev]"MCP Clients
Any MCP client — local stdio
ANY MCP CLIENT — LOCAL STDIO · JSON
{
"mcpServers": {
"subconscious-ai": {
"command": "<YOUR_PATH_TO_GHOSTSHELL>/venv/bin/python3",
"args": [
"<YOUR_PATH_TO_GHOSTSHELL>/server/main.py"
],
"env": {
"AUTH0_JWT_TOKEN": "<YOUR_AUTH0_JWT_TOKEN>",
"API_BASE_URL": "https://api.subconscious.ai"
}
}
}
}
