About DAG Studio WebMCP
DAG Studio WebMCP is an MCP server published by Black-Swan-Causal-Labs in the Blockchain category: read and edit a live DAG Studio canvas through its predefined WebMCP tools.
Install
git clone https://github.com/Black-Swan-Causal-Labs/dag-studio-webmcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (9)
add_edgeAdds a directed causal claim; duplicate, self, and cyclic edges are rejected.
Parameters not published.
add_nodeAdds a researcher-reviewable variable to the visible canvas.
Parameters not published.
analyze_current_dagReturns open backdoor paths, minimal sufficient adjustment sets, identifiability, and diagnostics.
Parameters not published.
check_adjustment_setChecks a proposed set against the encoded backdoor paths.
Parameters not published.
generate_analysis_codeGenerates R/dagitty or Python/NetworkX code for the live graph.
Parameters not published.
get_current_dagReads live nodes, roles, positions, directed edges, exposure, and outcome.
Parameters not published.
remove_edgeRemoves a directed causal claim.
Parameters not published.
remove_nodeRemoves a node and its incident edges.
Parameters not published.
simulate_current_dagRuns the existing linear Gaussian SEM for the live graph, opens the visible simulation result, and returns bounded summaries, correlations, effect estimates, and a 10-row preview.
Parameters not published.
Ask AI
Ask AI about DAG Studio WebMCP
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.