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
MCP & API

Build on the decision substrate.

Cascadian is one MCP server in front of one Postgres. Connect your agent in one line, then call the tools behind every Cascadian answer: memory that cannot lie about the past, a causal graph humans own, knock-on simulation, and a ledger that scores every call. Start with the quickstart, or jump to a tool.

Watch · 90 seconds

New here? Start with the overview.

What is Cascadian
Start here
01QuickstartPlug your agent in with one command. Claude Code, Desktop, Cursor, or any MCP runtime.02Authentication & approvalsScoped keys for agents — and an approval token that never crosses the MCP boundary.03The decision objectEvery recommendation carries its receipts — rationale, assumptions, invalidation criteria, a frozen expectation.
Try it — sandbox

Run a call right here.

Three canned calls, no key, no setup. Pick a scenario and run it — the response is the exact shape your agent gets back over MCP. Sample data, clearly labeled; the live server is gated behind the alpha.

Sandbox — canned, spec-true responses. No key, no server, no live data.

Sandbox — sample responseget_context_pack()
// Press RUN to call get_context_pack() in the sandbox.
Sample — canned from the spec, not a live server
Concepts

The substrate behind every call.

ConceptThe Four Memory NetworksTritemporal memory that physically cannot lie about the past.ConceptThe Governed Causal GraphHumans own truth; agents only propose. No estimate without identification.ConceptThe Knock-on Simulatordo(X=x) on the approved graph — every downstream effect, with its assumptions.ConceptThe Decision LedgerExpectations frozen before outcomes. Variance diagnosed, learning proposed.
Tools · ~27

~27 tools. Four surfaces.

Every tool is callable over MCP — JSON-schema validated, workspace-scoped, audited, with an honest capability_status where it matters. A REST mirror is planned; the alpha is MCP-only. Each tool gets its own page with a diagram and a worked call.

Memory — What is known — facts, sources, the four memory networks.
keybootstrap()The ~200-token session card your agent reads first.keyingest_source()Store a raw source — chunked, embedded, indexed.keyassert_fact()Write a temporal fact with an honest available_at.keypropose_memory()Propose a memory item — contradiction-checked on write.keylink_memories()A typed relationship edge, with rationale.keysupersede_memory()Revise without erasing — new row, old row closed.keysearch_memory()Hybrid retrieval with an honest empty result.keyget_facts()What was true, as of any moment.keyget_entity()The versioned dossier for one entity.keyget_memory()The full evidence card, by id.keyget_context_pack()Everything knowable for a decision, stamped and typed.keylist_contradictions()Open conflicts waiting on a human.
Causal — Why — the governed graph, identification, estimates, knock-ons.
keypropose_nodes()Propose variables for the graph — status proposed.keypropose_edge()Propose a cause→effect edge, with evidence.keyget_graph()The governed graph, by version or as-of.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?
Decisions — Decide and learn — the ledger that makes judgment compound.
keyopen_decision()Open a decision and pin what is knowable now.keyrecord_recommendation()The full recommendation — expectation frozen.scopedrecord_decision()The immutable commit. Approval enforced server-side.keyrecord_outcome()Measured actuals against the frozen expectation.keypropose_learning()Queue what the variance taught — humans approve.keyreview_calibration()How good are the calls, over time and by type.keyget_decision()The full decision card, by id.
Governance — Trust — approvals, audit, leakage detection, honesty.
scopedrequest_approval()Ask the human. The token never crosses this boundary.keyget_pending_approvals()What is waiting on a human.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.