Black-Swan-Causal-Labs/dagstudio-mcp
MCP server Claude CodeCodexCursor +2
Causal DAG analysis: backdoor paths, adjustment sets, bias simulation. Validated against dagitty. Remote server at dagstudio-mcp.blackswancausallabs.com.
Black-Swan-Causal-Labs/robins-i-mcp
MCP server Claude CodeCodexCursor +2
MCP server implementing ROBINS-I V2 (follow-up/cohort) as a deterministic, provenanced risk-of-bias engine for one result of a non-randomized study. Runs locally from the robins-i-mcp Python package.
Black-Swan-Causal-Labs/target-mcp
MCP server Claude CodeCodexCursor +2
MCP server operationalizing the TARGET reporting guideline (Cashin et al., JAMA/BMJ 2025) as a deterministic, provenanced scoring engine for target trial emulation studies. Runs locally from the target-mcp Python package.
Black-Swan-Causal-Labs/openfda-mcp
MCP server Claude CodeCodexCursor +2
MCP server for FDA drug and device regulatory metadata via openFDA (CDER, CBER, CDRH). Runs locally from the openfda-mcp Python package.