Enable NeuroDock-hosted storage: NeuroDock provisions a private database (isolated to your account) and the memory tools store data there. Records your explicit consent and returns a disclosure of what is stored and how to erase it. Requires a signed-in NeuroDock account. For maximum privacy use connect_byos_storage (your own database) instead.

Connect your own libSQL/Turso database so the NeuroDock memory tools store data in YOUR database, not on NeuroDock. Validates the URL and smoke-tests the connection before saving it. Requires a signed-in NeuroDock account.

Disable storage and erase it. Hosted: destroys the NeuroDock-managed database NeuroDock provisioned for you. BYOS: clears the stored connection (your own database is left untouched). Either way your stored preference and consent are cleared. Requires a signed-in account.

Disconnect your BYOS storage database. NeuroDock deletes the connection and retains nothing about your storage. Your data stays in your own database, untouched. (To erase NeuroDock-hosted storage instead, use disable_and_erase_storage.) Requires a signed-in NeuroDock account.

Report whether you are signed in and which storage mode is active (mode: hosted, byos, or none).

Look up everything your connected cognitive graph knows about a named person, project, decision, or concept. Alias-resolves the input. Requires a signed-in account with connected storage (connect_byos_storage).

Persist a typed-edge (subject, predicate, object) fact into your connected cognitive graph. Entities referenced by name are auto-created. Requires a signed-in account with connected storage (connect_byos_storage).

Return decisions recorded against a named project in your connected cognitive graph, newest first, optionally filtered by an ISO 8601 since-date. Requires a signed-in account with connected storage.

Return a server-generated activity summary of your connected cognitive graph for the trailing seven local days, optionally scoped to a project. Requires a signed-in account with connected storage.

Decode subtext, ambiguity, and the likely implicit ask in an incoming message. Returns a deterministic baseline analysis plus a structured prompt the caller's MCP client MAY execute to refine the baseline against its own LLM.

Score an outgoing message on directness / warmth / urgency axes (0..100), optionally relative to a baseline of the sender's prior messages, and flag phrases that deviate substantially from baseline or from a target register. Returns deterministic axes plus an LLM-refinement prompt.

Rewrite an outgoing message toward a target register while preserving caller-named technical terms. The deterministic baseline applies register-specific surface transforms; the LLM refinement prompt produces a stronger rewrite while keeping the same preservation contract.

Convert a meeting transcript into a four-section structured brief: my_asks, others_asks, decisions, ambiguous_items. Every ambiguous_item is anchored to a verbatim transcript span; the server rejects responses where the anchor cannot be located.

Detect whether the user's current prompt is a semantic repeat of recent prompts within a rolling window. Stateless; returns a structured advisory signal.

Classify hyperfocus escalation from a caller-supplied chronometric snapshot into one of (none, gentle, nudge, hard). Stateless; quotes prior_intent verbatim.

Detect over-validation in a candidate response or repeated reassurance-seeking in recent user messages. Returns a counter_prompt the caller MAY surface.

Break a vague goal into a small ordered list of atomic 5-90 minute tasks with explicit acceptance criteria and dependency edges. Stateless: returns tasks but does NOT persist them.