MCP Observatory
32s ago Tracked 72,287 Last 32s ago 24h 2,665
Watchlist

Black-Swan-Causal-Labs/dag-studio-webmcp

github
github analyzed ed7aa63

Read and edit a live DAG Studio canvas through its predefined WebMCP tools.

maintainer
Black-Swan-Causal-Labs
licence
—
first seen
2026-09-08
last seen
2026-09-08
releases · 30d
0
github stars
0 reported
short id

Black-Swan-Causal-Labs/dag-studio-webmcp is an MCP server distributed on github, maintained by Black-Swan-Causal-Labs, tracked here since September 2026. It has shipped 0 releases and exposes 9 tools. Tools include add_edge, add_node, analyze_current_dag, check_adjustment_set, generate_analysis_code, get_current_dag, and 3 more. Its composite risk grade is A — an inferred review prompt computed from observed signals, not a verdict.

lifetime releases
0
releases · 30d
0
dependencies
0
dependents
0

what we found

Its 9 tools appear to reach network, inferred from tool names, descriptions and input schemas rather than from observed behaviour.

full security breakdown →

tools

9
  • add_edge Adds a directed causal claim; duplicate, self, and cyclic edges are rejected.
  • add_node Adds a researcher-reviewable variable to the visible canvas.
  • analyze_current_dag Returns open backdoor paths, minimal sufficient adjustment sets, identifiability, and diagnostics.
  • check_adjustment_set Checks a proposed set against the encoded backdoor paths.
  • generate_analysis_code Generates R/dagitty or Python/NetworkX code for the live graph.
  • get_current_dag Reads live nodes, roles, positions, directed edges, exposure, and outcome.
  • remove_edge Removes a directed causal claim.
  • remove_node Removes a node and its incident edges.
  • simulate_current_dag Runs the existing linear Gaussian SEM for the live graph, opens the visible simulation result, and returns bounded summaries, correlations,…

release cadence · 90d

0 releases

No releases yet.

recent releases

last 0

No releases yet.