View on ApifyForge | Use on Apify Store
Knowledge Graph & Causal Discovery is an MCP project maintained in the apifyforge/knowledge-graph-causal-discovery-mcp repository. The maintainer describes its purpose as “View on ApifyForge | Use on Apify Store”. Read the project documentation for the complete scope.
The maintainer’s configuration uses https://ryanclinton--knowledge-graph-causal-discovery-mcp.apify.actor/mcp. Check the project’s account and authentication instructions when adding the endpoint to your client.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| Back | door criterion — adjustment for observed confounders |
| Front | door criterion — adjustment via mediating variables when confounders are unobserved |
| Balke | Pearl LP bounds — linear programming bounds for effects not identifiable by do-calculus, constraining via observable distributions |
| Self | adversarial negative sampling — samples negative triples with probability proportional to their current score, weighted by softmax temperature |
| Margin | based loss with margin gamma separating positive and negative triple scores |
| discover_causal_structure | |
| compute_interventional_effects | |
| simulate_counterfactuals | |
| extract_causal_claims_literature | |
| embed_causal_knowledge_graph | |
| estimate_causal_effect_tmle | |
| check_graph_consistency | |
| attribute_source_contribution |
{
"mcpServers": {
"knowledge-graph-causal-discovery-mcp": {
"url": "https://ryanclinton--knowledge-graph-causal-discovery-mcp.apify.actor/mcp"
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Persistent memory + context layer for AI dev teams. 17 tools via MCP.
Plan a knowledge-base placement path.
Generate beautiful Excalidraw architecture diagrams with auto-layout and component styling
Beefy MCP server — 10 tools for AI agent integration. Hosted by Junct.