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

propose_nodes()

Key

Claude (or an algorithm adapter) proposes variables for the causal graph, with rationale and evidence links. Everything lands at status=proposed — humans approve graph structure.

propose_nodes(nodes, rationale, evidence_ids)PROPOSED NODES

Callable over MCP as propose_nodes(nodes, rationale, evidence_ids). REST mirror POST /v1/graph/nodes Planned — alpha is MCP-only

Why your agent calls it

When the agent's reading suggests a variable the graph doesn't model yet — onboarding spend, rep tenure — it proposes the node with its reasoning. The graph only grows through proposals a human has seen.

What it returns
DISCOUNTWIN RATEMARGINREVENUEAPPROVEDAGENTS PROPOSE EDGES · HUMANS APPROVE · CONFIDENCE PER EDGE
propose_nodes() · Propose variables for the graph — status proposed.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.propose_nodes( nodes=[{"name": "onboarding_spend"}], rationale="Margin data shows the tier is net-negative.", evidence_ids=["mem_0871"], )
Parameters
ParamTypeDescription
nodesREQUIREDobject[]Proposed variables — name + description each.
rationaleREQUIREDstringWhy these variables belong in the graph.
evidence_idsstring[]Memory or sources supporting the proposal.
Example response
propose_nodes()JSON · ILLUSTRATIVE
{ "proposed": [ { "node": "onboarding_spend", "status": "proposed" } ] }
Related — Causal