Black-Swan-Causal-Labs/dagstudio-mcp
MCP server Claude CodeCodexCursor
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
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
Skill Claude CodeCodex
Assess a manuscript against the TARGET reporting checklist FAST by fanning the 39 leaves out across parallel scoring subagents, then merging and submitting through the target-checklist MCP server. Use when a user asks to review, score, or assess an observational target-trial-emulation study against TARGET and the…
Black-Swan-Causal-Labs/target-mcp
MCP server Claude CodeCodexCursor
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.