"Information on memory" matching MCP tools:

• forget

  memxus

  Permanently delete one memory by UUID. When to use: user asks to remove outdated or incorrect context, or to free plan storage. When NOT: fix content → update (mode=replace); find the ID first → list_memories or recall. Requires delete OAuth scope. Non-idempotent: deleting the same memory_id twice fails. Errors: Memory not found, Not authorized to delete this memory. Side effects: removes the memory row and vector embedding with no recovery; invalidates plan cache. The target workspace is always the one the memory itself belongs to (echoed in resolved_workspace); optionally pass workspace: <name> as a safety confirmation — the call fails if the memory is not actually in that workspace.

  Connector

• memory_index

  Recao

  List this account's company memory, one line per entry (name + description), newest first. Traverse index-first: scan this, then memory_recall(name) for full bodies. Memory accrues automatically from your competitor scans (exhaust) and from your own memory_note writes.

  Connector

• tax_rate

  Qiniso

  USE THIS before calculating VAT or sales tax on an invoice/quote — never recall the rate from memory, it is DATE-SENSITIVE. GB returns the UK standard VAT rate that applied on the given date (handles historical/temporary changes). US has no national VAT (returns 0); pass a state code for the state base sales-tax rate. Always pass the invoice date for GB.

  Connector

• append_memory

  space0

  Persist one event to this agent's memory stream. For kind=chat, ALWAYS pass `speaker` (the in-world player name behind the line) - flattening "grassguy: i am here" into event_text causes the agent to parrot the speaker as itself on the next tick. Server-side will embed `text` via Workers AI so the memory is reachable by `search_memories` semantic retrieval. Observation/action memories auto-anchor to your current space and last-looked subject by default once you have entered a space; pass space + subjectPosition only to override the anchor precisely. Reflection/chat stay unanchored.

  Connector

• get_security_profile

  mcp

  Comprehensive security and compliance information for Everstake: certifications, audits, infrastructure security, and compliance standards. Use when users need security details, compliance verification, or trust/safety information about Everstake's operations.

  Connector

• cortex_recall

  mitosis

  Semantic-only vector search over the memory, returning source excerpts. Prefer cortex_ask, which also uses full-text and graph expansion; reach for this when you specifically want nearest-neighbour matches on meaning.

  Connector

• remember

  memxus

  Save important information to long-term memory. Always set collection when the topic is clear: project work → project:<slug>, personal tastes → personal:preferences. Use append_to to extend an existing memory instead of creating duplicates. Vector search indexing completes asynchronously within a few seconds after save. To save to a team workspace instead of personal memory, pass workspace: <name>.

  Connector

• update

  memxus

  Update an existing memory by ID. Use mode replace (default) to patch fields, or append to extend content. Re-embeds only when content changes. The target workspace is always the one the memory itself belongs to (echoed in resolved_workspace); optionally pass workspace: <name> as a safety confirmation — the call fails if the memory is not actually in that workspace.

  Connector

• search_memory_facts

  WingmanProtocol Agent Gateway

  Search YOUR extracted memory facts by topic or entity name. No LLM needed — pure SQL lookup against pre-extracted facts. Scoped to facts from memory you own — registered handle + secret required. Returns entries with topics, entities, action_items, and summary.

  Connector

• zambo_remember

  Zambo AI Tools

  Store any information in your private Zambo memory — permanently, across every session, device, and AI client. Claude loses all context between sessions. zambo_remember fixes that forever. Store facts, goals, project state, preferences, research notes, API configs, anything. Your memory lives in 3 connected layers: (1) zambo_remember = private vault (only yours, keyed by email), (2) hive_write via Axis = public agent commons (all agents can read), (3) axis_memory_handoff = cross-platform session bundle. Free: 20 memories per email. Zambo Pass: unlimited.

  Connector

• memory_note

  Recao

  Write (or update) a memory entry on this account: decisions, campaign outcomes, learnings. Use a short kebab-case name and a one-line description (that's the index line); details go in body. Your future sessions and Recao's weekly reports read this.

  Connector

• memory_get

  x402-services

  Agent Memory: read a stored value by key, or omit key to list all keys in your namespace. Send { ns, token, key? }. [x402 paid tool — price $0.003; POST /api/memory/get]

  Connector

• crest_verify

  counterparty-intelligence

  Before you trust or pay another agent, look up its Crest passport: standing (new vs returning), days active, memory depth, and on-chain role if a wallet is bound. Pass a Crest agent_id, a 0x wallet, or an ERC-8004 agent id (we resolve its on-chain identity from the ERC-8004 Identity Registry on Base and overlay our behavioral read). Read-only, not financial advice.

  Connector

• test_deployment

  Nervous System

  Run 5-step test pipeline on a file before deployment: preflight, syntax, dependencies, ports, memory.

  Connector

• get_now_playing

  LONG Events

  Get what's currently playing at festival/party events. Returns live stage information with current artists. Use this to answer 'What's on now?' or 'Who's playing right now at AYA?'

  Connector

• check_llm_fit

  FitLLM

  Check whether a specific local LLM fits in the memory of a specific GPU or Apple Silicon Mac. Returns fits/tight/won't-fit verdict with the full memory breakdown (weights, KV cache, overhead), max context, and a concrete fix if it doesn't fit. Use this whenever a user asks anything like "can I run <model> on my <GPU/Mac>?", "will <model> fit in <N>GB?", or "what do I need to run <model>?". Architecture-aware math (MLA, sliding-window, hybrid attention, MoE) — more accurate than rule-of-thumb estimates.

  Connector

• call_instance_proxy

  runcomfy-mcp

  Call a ComfyUI backend endpoint on a live instance. Backs ``POST /prod/v2/deployments/{deployment_id}/instances/{instance_id}/proxy/{path}``. Get the instance_id from ``get_request_status`` once the status is ``in_progress``. Common target: ``api/free`` with ``{"unload_models": true}`` to free GPU memory.

  Connector

• academy_playbooks

  StudioMeyer Academy

  List hands-on playbooks (short, practical how-tos for Claude Code, MCP, memory, agents). Optional category filter.

  Connector

• wm_remember

  connect

  Write one fact to your operator memory in ODEI — the World Model grows from it. Server-side (ODEI-hosted) memory for the paired operator; not the local world-model capsule.

  Connector

• crest_remember

  counterparty-intelligence

  Append a fact/decision/outcome/note to your Crest memory. Every entry is hash-chained (sha256), so your memory is provable and tamper-evident. Returns the entry hash (a receipt) and your new memory_root. Requires your passport_key. Do not store human personal data.

  Connector