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

link_memories()

Key

Creates a typed relationship edge between two memory items — supports, contradicts, refines — with the rationale recorded on the edge.

link_memories(from_id, to_id, relation, rationale)EDGE

Callable over MCP as link_memories(from_id, to_id, relation, rationale). REST mirror POST /v1/memories/link Planned — alpha is MCP-only

Why your agent calls it

When the agent notices structure — this lesson supports that belief, this fact contradicts that assumption — it records the relationship explicitly, with the reasoning on the edge. Retrieval gets smarter every time.

What it returns
DISCOUNTWIN RATEMARGINREVENUEAPPROVEDAGENTS PROPOSE EDGES · HUMANS APPROVE · CONFIDENCE PER EDGE
link_memories() · A typed relationship edge, with rationale.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.link_memories( from_id="mem_0912", to_id="mem_0871", relation="contradicts", rationale="Margin data shows the tier is net-negative.", )
Parameters
ParamTypeDescription
from_idREQUIREDstringSource memory id.
to_idREQUIREDstringTarget memory id.
relationREQUIREDstringThe typed relation, e.g. "contradicts".
rationaleREQUIREDstringWhy this edge exists.
Example response
link_memories()JSON · ILLUSTRATIVE
{ "edge_id": "lnk_0118", "relation": "contradicts", "status": "proposed" }
Related — Memory