Black-Swan-Causal-Labs/dagstudio-mcp
github JavaScript analyzed · update queued
MCP server for the DAG Studio causal-inference engine: backdoor analysis, adjustment sets, bias simulation, effect-modification classification. Validated against dagitty.
No releases · last push 3d ago
No releases or dependencies recorded yet.
A minimal
what we found
tools
-
analyze_Backdoor paths, minimal sufficient adjustment sets, identifiabilitydag -
check_Detect adjustment for mediators, colliders, and descendants of exposureoveradjustment -
classify_Classify effect-modifier structure (direct, indirect, proxy, common-cause, pure interaction)effect_ modification -
compute_Empirical bias of an adjustment strategy against the simulated truthbias -
generate_R / Python analysis code for a DAG, plus a one-click DAG Studio URLcode -
get_Canonical teaching DAGs (confounding, M-bias, frontdoor, and others)canonical_ example -
parse_Parse dagitty DSL (raw or R-wrapped) into the structured DAG modeldagitty -
simulate_Simulate data from a DAG under user-specified structural coefficientsdata -
validate_Run the full canonical validation suite and report engine versionengine
Black-Swan-Causal-Labs/dagstudio-mcp is an MCP server distributed on github, maintained by Black-Swan-Causal-Labs, tracked here since July 2026. It has shipped 0 releases and exposes 9 tools. Tools include analyze_dag, check_overadjustment, classify_effect_modification, compute_bias, generate_code, get_canonical_example, and 3 more. Its composite risk grade is A — an inferred review prompt computed from observed signals, not a verdict.