Alpha MCPAPI reference · v1

The MCP your agents call.

Tritemporal memory that cannot lie about the past, a governed causal graph, knock-on simulation, and a decision ledger — the engine behind every Cascadian answer, at machine speed.

MCPPOSTGRESGOVERNED
Tools / Memory

list_contradictions()

Key

Every open contradiction in memory that needs human adjudication. Agents surface conflicts; they never silently resolve them.

list_contradictions(status)CONFLICTS[]

Callable over MCP as list_contradictions(status). REST mirror GET /v1/contradictions Planned — alpha is MCP-only

Why your agent calls it

A standing agenda item for the human. The agent surfaces every unresolved conflict in memory; the human adjudicates. Workspaces that clear this list regularly make measurably cleaner decisions — the conflicts you ignore are the variance you eat later.

What it returns
MEMORY Amem_0871CONTRADICTSMEMORY Bmem_0912OPEN CONFLICTS WAIT FOR HUMAN ADJUDICATION — NEVER AUTO-RESOLVED
list_contradictions() · Open conflicts waiting on a human.ILLUSTRATIVE
Call it from an agent

Over MCP, your agent invokes it on its own when the moment calls for it — just describe the situation. A Python SDK for headless runtimes is planned; this is what the call will look like.

agent · python sdkSDK · PLANNED — ALPHA IS MCP-ONLY
from cascadian import Cascadian cx = Cascadian(api_key=os.environ["CASCADIAN_API_KEY"]) result = cx.list_contradictions( status="open", )
Parameters
ParamTypeDescription
statusenum"open" (default) or "resolved".
Example response
list_contradictions()JSON · ILLUSTRATIVE
{ "open": [ { "a": "mem_0871", "b": "mem_0912", "summary": "discount lift: unclear vs net-negative", "needs": "human adjudication" } ] }
Related — Memory