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

ingest_source()

Key

Stores a raw source, chunks it, embeds it, and FTS-indexes it. Returns the source_id and chunk summaries. Extraction is Claude's job afterward — the server stores honestly, it does not interpret.

ingest_source(content, title, source_type)SOURCE_ID + SUMMARIES

Callable over MCP as ingest_source(content, title, source_type). REST mirror POST /v1/sources Planned — alpha is MCP-only

Why your agent calls it

When something worth remembering arrives — a call transcript, a pricing review, a board memo — the agent stores it raw. The server chunks, embeds, and indexes; the agent then extracts the facts and beliefs worth proposing. Storage and interpretation stay separate on purpose.

What it returns
STEP 1STORE RAWSTEP 2CHUNK + EMBEDSTEP 3FTS INDEXRETURNS SOURCE_ID + CHUNK SUMMARIES · EXTRACTION IS CLAUDE'S JOB
ingest_source() · Store a raw source — chunked, embedded, indexed.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.ingest_source( content="Discount pulls deals forward; net win-rate lift unclear.", title="Q2 pricing review notes", source_type="note", )
Parameters
ParamTypeDescription
contentREQUIREDstringThe raw source text to store.
titlestringHuman-readable source title.
source_typestringe.g. "note", "document", "transcript".
Example response
ingest_source()JSON · ILLUSTRATIVE
{ "source_id": "src_0307", "chunks": 14, "chunk_summaries": [ { "id": "chk_2210", "summary": "Q2 pricing review — discount tier margin impact" } ] }
Related — Memory