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 / Governance

get_pending_approvals()

Key

Everything currently waiting on human sign-off, with the decision and risk level behind each item.

get_pending_approvals()→ PENDING[]

Callable over MCP as get_pending_approvals(). REST mirror GET /v1/approvals Planned — alpha is MCP-only

Why your agent calls it

The agent's polite nudge: what's still waiting on a human, with the risk level attached. Useful at session start and before an agent parks a workstream that's blocked on sign-off.

What it returns
AGENT · MCPrequest_approval()OUT OF BANDHUMAN · OWN TERMINALcascadian approveTHE APPROVAL TOKEN NEVER CROSSES THE MCP BOUNDARY
get_pending_approvals() · What is waiting on a human.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_pending_approvals()
Parameters

None. The call is workspace-scoped by the key that makes it.

Example response
get_pending_approvals()JSON · ILLUSTRATIVE
{ "pending": [ { "approval_id": "apr_0027", "decision": "dec_0142", "risk": "medium" } ] }
Related — Governance
scopedrequest_approval()Ask the human. The token never crosses this boundary.keyreconstruct_decision()Re-run the pinned reads. The diff is the audit.keydetect_leakage()Catch any future fact that leaked into the past.publiccapabilities()The honesty endpoint — what is real vs planned.