dagstudio-mcp

Black-Swan-Causal-Labs/dagstudio-mcp

★ 0 stars JavaScript AI/LLM Updated today

MCP server for the DAG Studio causal-inference engine: backdoor analysis, adjustment sets, bias simulation, effect-modification classification. Validated against dagitty.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "dagstudio-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "Black-Swan-Causal-Labs/dagstudio-mcp"
      ]
    }
  }
}

README Excerpt

Model Context Protocol (MCP) server for the [DAG Studio](https://github.com/Black-Swan-Causal-Labs/dag-studio) causal-inference engine. It lets AI agents construct, analyze, and validate causal directed acyclic graphs (DAGs) using the same engine that powers the [DAG Studio canvas](https://dagstudio.blackswancausallabs.com/).

Tools (9)

analyze_dagcheck_overadjustmentclassify_effect_modificationcompute_biasgenerate_codeget_canonical_exampleparse_dagittysimulate_datavalidate_engine

Topics

causal-inferencedagdagittyepidemiologymcpmodel-context-protocolreal-world-evidence

dagstudio-mcp

Quick Install

README Excerpt

Tools (9)

Topics

Related AI/LLM Servers