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

get_facts()

Key

As-of fact and entity-state queries. Ask what was true — and what was knowable — at any point in time, on both temporal axes.

get_facts(entity, as_of)FACTS

Callable over MCP as get_facts(entity, as_of). REST mirror GET /v1/facts Planned — alpha is MCP-only

Why your agent calls it

The as-of question: what was true about this entity at that moment — and separately, what could we have known? An agent checking a past decision's premises uses this instead of trusting its own reconstruction.

What it returns
valid_from2025-09-01WHEN IT BECAME TRUEavailable_at2025-09-14WHEN WE COULD KNOWAS_OFEVERY READ ACCEPTS AS_OF · NO FUTURE LEAKS INTO THE PAST
get_facts() · What was true, as of any moment.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.get_facts( entity="discount_tier", as_of="2026-06-11T17:00:00Z", )
Parameters
ParamTypeDescription
entityREQUIREDstringThe entity to query.
as_oftimestampThe moment to reconstruct. Default now.
Example response
get_facts()JSON · ILLUSTRATIVE
{ "entity": "discount_tier", "as_of": "2026-01-01T00:00:00Z", "facts": [ { "attribute": "status", "value": "live", "valid_from": "2025-09-01" } ] }
Related — Memory