MCP server that transforms linear AI reasoning into structured, auditable thought graphs
Drift inferred · capture-to-capture
No drift recorded — single capability capture; advisories appear once its surface changes.
transport stdio counts 9 tools · 0 res
· 0 prompts
permission surface via README inference
tools
-
action
A plan to use a tool
-
assumption
A belief taken as true for this reasoning line
-
critique
Self-correction or flaw identification
-
evidence
Data from tools or prior knowledge
-
hypothesis
A proposed explanation or solution
-
objective
The overall goal of the reasoning task
-
question
A point of uncertainty to resolve
-
sub_problem
Decomposition of a larger problem
-
synthesis
A conclusion from previous thoughts
evidence-backed
findings quoted directly from the published source artifact — not inferred
This server hasn't been statically analyzed yet (npm/PyPI artifacts only).