Contact us
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 / Causal

get_graph()

Key

The causal graph by version or as-of, with statuses, evidence, and confidence on every edge — plus a Mermaid rendering for chat display.

get_graph(version, as_of, format)→ GRAPH

Callable over MCP as get_graph(version, as_of, format). REST mirror GET /v1/graph Planned — alpha is MCP-only

Why your agent calls it

Before reasoning causally, the agent loads the graph the humans actually approved — not its own intuition about how the business works. The Mermaid rendering drops straight into chat, so the human and the agent argue about the same picture.

What it returns
DISCOUNTWIN RATEMARGINREVENUEAPPROVEDAGENTS PROPOSE EDGES · HUMANS APPROVE · CONFIDENCE PER EDGE
get_graph() · The governed graph, by version or as-of.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_graph( version="v14", as_of="2026-06-11T17:00:00Z", format="mermaid", )
Parameters
ParamTypeDescription
versionstringA specific graph version. Default latest.
as_oftimestampThe graph as it stood at this moment.
formatenum"json" (default) or "mermaid".
Example response
get_graph()JSON · ILLUSTRATIVE
{ "version": "v14", "nodes": ["discount", "win_rate", "gross_margin", "revenue"], "edges": [ { "edge": "discount → win_rate", "status": "approved", "confidence": 0.7 }, { "edge": "discount → gross_margin", "status": "approved", "confidence": 0.8 }, { "edge": "win_rate → revenue", "status": "approved", "confidence": 0.9 } ], "mermaid": "graph LR; discount-->win_rate; …" }
Related — Causal
keypropose_nodes()Propose variables for the graph — status proposed.keypropose_edge()Propose a cause→effect edge, with evidence.keyvalidate_graph()Structural checks before anyone trusts an edge.keyidentify()Can this effect be estimated at all? The gate.keyestimate()A causal estimate that survives the skeptic checks.keysimulate_intervention()do(X=x) on the approved graph — the knock-on report.keyattribute_change()What caused this metric to move?