"Methods to store and persist memories for AI systems" matching MCP tools:

• buy_credits

  VARRD — Statistically Validated Trading Edges + AI Research Engine

  Buy credits for the edge library and AI research. Default $5 minimum. Free — no credits consumed to call this. TWO PAYMENT METHODS: card (default): Returns a Stripe Checkout link for your user to click and pay. After payment, call check_balance to confirm credits were added. crypto: USDC on Base. Fully autonomous — no human needed. Three steps: 1. buy_credits(payment_method='crypto') → returns deposit address + payment_intent_id 2. Send USDC to the deposit address (use your wallet tool) 3. buy_credits(payment_intent_id='pi_...') → confirms payment, credits added instantly If you have wallet access, this is the fastest path — fully machine-to-machine.

  Connector

• search_stores

  Partle

  Search or list stores in the Partle marketplace. Use for store-led questions ("what hardware shops are in Madrid?") rather than product-led ones (use `search_products` for that). Pass no query to browse the whole catalog. Read-only. No authentication. Rate-limited to 100 requests/hour per IP. Args: query: Free-text search over store name and address. Omit to list all stores in default order. limit: Max results (1–50, default 20). Returns: A list of stores with `id`, `name`, `address`, `lat`/`lon` (when geocoded), `homepage`, `type`, and `product_count` (active listings in the store — useful for competitive-landscape sizing without a separate `search_products` round-trip). Pass `id` to `search_products(store_id=…)` to filter the product catalog by that store.

  Connector

• search_stores

  Partle Marketplac

  Search or list stores in the Partle marketplace. Use for store-led questions ("what hardware shops are in Madrid?") rather than product-led ones (use `search_products` for that). Pass no query to browse the whole catalog. Read-only. No authentication. Rate-limited to 100 requests/hour per IP. Args: query: Free-text search over store name and address. Omit to list all stores in default order. limit: Max results (1–50, default 20). Returns: A list of stores with `id`, `name`, `address`, `lat`/`lon` (when geocoded), `homepage`, `type`, and `product_count` (active listings in the store — useful for competitive-landscape sizing without a separate `search_products` round-trip). Pass `id` to `search_products(store_id=…)` to filter the product catalog by that store.

  Connector

• agent-brain

  MeshMarket

  Agent Brain — Reason over a question or task with your agent's own persistent memory in the loop: recalls up to 12 relevant memories from your agent's private scope, reasons with Claude, and writes up to 3 new memories back, so the agent improves with every call. Recall by meaning, not just keyword, when the estate's memory server is reachable (falls back to its own always-on store otherwise — never fails the call). Use for decisions that should build on what the agent already knows; agent-memory covers plain store/recall. Runs claude-haiku-4.5 — the response names the model that served the call; agent-brain-smart runs the identical contract on claude-sonnet-5. Input: {think: string}. Returns {answer, reasoning, confidence, memories_considered, used_memories, learned, model, engine}. (8 MESH/call, a tool · cognition)

  Connector

• remember

  ai-netcafe

  Persist a durable memory: an architecture decision, a stable user preference, a verified bug fix, or an important discovery. Anonymous callers get a small per-network memory pool; callers sending an AllRouter key (Authorization: Bearer sk-...) get a large pool shared across ALL their machines and agents — the same key on a laptop's Claude Code and a desktop's Codex recalls the same memories. Do not store secrets or raw logs. Example — tools/call remember {"content":"Deploy key rotates monthly"}

  Connector

• delete_memories

  MemoryRouter

  Use this only when the user explicitly asks to delete specific memories and confirms after seeing what will be deleted. Permanently deletes the identified memories from the connected vault by their ids from search or inspect results. Deleting a raw memory does not delete reflections built from it. This cannot be undone. For deleting everything, forget_all_memories is the separate whole-vault tool.

  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

• check_merchant_readiness

  audit

  Check whether an AI shopping agent can find, understand and BUY on an e-commerce store: AgentReady's deterministic agent-readiness score /100 for a host, with grade, hard-block status (capped = agents are blocked at the door) and agent-protocol adoption (UCP, A2A, ARD). Scores exist for stores whose merchant ran a scan at agentready.market — this tool never triggers a new audit of a third-party site.

  Connector

• search_memory

  AgentPlaybooks

  Search memories by text, tags, tier, or type. Returns summaries for large memories. Use tags for categorical search; use tier to focus on active vs archived data; use memory_type to find task graphs. Read-only aside from returning matches; it does not write entries. Use read_memory for one key, get_memory_context for a compact tiered view, and get_memory_tree for parent-child task graphs. Pass playbook_id as the UUID or GUID of the playbook this call should target.

  Connector

• get_dasha

  Jagannatha Hora — Vedic Astrology (Jyotish, Kundli, Horoscope, Panchang)

  Return a dasha (planetary period) timeline as a nested tree anchored on a date — past, present and future in ONE call. Works for BOTH planetary (graha) and sign (rasi) dasha systems; just name the system and the tool routes it automatically. Every period node has the SAME shape: 'level' (maha/antar/pratyantar/sookshma), 'ruler' (planet for graha, sign for rasi), 'start', 'end' (YYYY-MM-DD) and 'relation' (past/current/future). The result has 'dasha_type' ('graha' or 'rasi'), 'system', 'as_of' (anchor date), 'depth', and: 'current' — a ready-made summary of the running period ('maha'/'antar'/'pratyantar', a 'path' string, and 'current_period_ends'); 'maha_timeline' — every Maha-dasha over the life; 'current_maha' with its 'antars'; for graha systems 'current_antar' with its 'pratyantars'; and, at depth 4, 'current_pratyantar' with its 'sookshmas'. Rasi systems have two levels (no pratyantar). To drill into a SPECIFIC period regardless of date, pass 'maha' (and optionally 'antar') as a ruler name — the matching branch comes back under 'selected_maha'/'selected_antar' with a 'selection' echo. HOW TO REQUEST: send only birth details for the default (vimsottari, anchored today, depth 3). Optionally set 'system' to EXACTLY one enum token. Planetary (graha) systems: vimsottari (standard 120-yr), ashtottari, yogini, shodasottari, dwadasottari, panchottari, satabdika, chaturaaseeti_sama, shashtisama, shattrimsa_sama, dwisatpathi, kaala, buddhi_gathi, naisargika, aayu, tara, karaka, tithi_ashtottari, tithi_yogini, karana_chaturaaseeti_sama, saptharishi_nakshathra, rasi_bhukthi_vimsottari, yoga_vimsottari, ashtaka_varga_planet, ashtaka_varga_sign, ashtaka_varga_pinda, moola_graha, rashmi. Sign (rasi) systems: narayana, chara, kendraadhi_rasi, sudasa, drig, nirayana, shoola, kendraadhi_karaka, lagnamsaka, padhanadhamsa, mandooka, sthira, tara_lagna, brahma, varnada, yogardha, navamsa, paryaaya, trikona, kalachakra, chakra, sandhya_panchaka, chathurvidha_utthara, karaka_kendraadhi, lagna_kendraadhi, niryaana, raashiyanka. Optionally set 'as_of_date' (YYYY-MM-DD, separate from birth 'date') to anchor on another time, e.g. '2030-01-01'. Data only — no interpretation.

  Connector

• vault_store_secret

  mcp

  Store or update a secret in the project vault. The value is encrypted with AES-256-GCM and can never be read back. Use this to save API keys for integrations. If the key_name already exists, the value is replaced. For production API keys, the Dashboard Vault tab (dashboard.websitepublisher.ai/vault) is the recommended secure alternative — keys go directly to encrypted storage without passing through the AI conversation.

  Connector

• discover

  AgentMarketplace

  Discover AgentMarketplace's capabilities, tools, auth methods, and scopes. Call this first when connecting to AgentMarketplace to understand what's available and how to authenticate. No authentication required. Returns a catalog of available tools, resources, auth methods, and scopes.

  Connector

• poll_since

  Nullcone Threat Intelligence

  Fetch new threat signatures since a high-water mark ID. This is the recommended sync pattern — one call, get new data, persist next_id, disconnect. No persistent connection required. Call with last_id=0 on first run to get all signatures. Persist the returned next_id and pass it on the next call to get only new entries. If count == batch_size, call again immediately to drain backlog. Args: last_id: Last signature ID seen (0 for all). Persist this between calls. batch_size: Max signatures to return (1–5000) min_severity: Skip signatures below this severity (0–10)

  Connector

• sku_map_check

  Moltline Dropship Economics

  Find the breaks in a supplier-to-store SKU map before they ship. FREE. Two store SKUs pointing at one supplier SKU is usually intentional; two supplier SKUs claiming one store SKU is not, and it sends the wrong item. Typical input {"mapping": {"STORE-1": "SUP-A", "STORE-2": "SUP-A", "STORE-3": ""}} returns {"ok": false, "count": 3, "empty_targets": ["STORE-3"], "shared_supplier_skus": {"SUP-A": ["STORE-1", "STORE-2"]}, "whitespace_issues": []}. Use before importing a mapping or handing one to a fulfilment app. Not for validating Shopify's CSV columns — that is the shopify server. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "mapping must contain at least one store SKU"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  Connector

• inspect_website

  ShortlistLens

  Fetch a public business website page and return structured, accessible facts for a buyer-readiness review. It only examines the supplied public URL and does not scrape review platforms or private systems.

  Connector

• save_citation_override

  Valuein — SEC EDGAR Fundamentals & Smart-Money Data

  Persist a correction of a citation value. The correction is keyed on the canonical `fact_id` (a stable hash of CIK + accession + concept + period) so it applies to every report that references that same fact — including agent-regenerated reports. Re-saving the same fact_id replaces the prior correction in place (no duplicate row). The `fact_id` is VERIFIED against live SEC data (scoped to `ticker`) before the correction is stored — a fact_id that doesn't resolve to a real fact is rejected with FACT_NOT_FOUND and nothing is persisted. You therefore must supply the `ticker` the fact belongs to. Use this when the user notices an inaccuracy in an AI-generated report and wants the fix to persist. Provide `notes` for the rationale (≤500 chars) and `source_report_id` for provenance. Flat 10,000-override anti-abuse cap per account (deleting frees a slot; never a tier limit).

  Connector

• cognitive_boot

  space0

  Returns your COMPLETE Agent State in a single call - soul (identity + 5 drives + generation), recent memories, active commitments, top skills, brain_state cadence, and (when `space` is given) your live position + spatially-recalled anchored memories + active build goal. You are the cognitive controller: call this at the start of EVERY autonomous tick (pass the space slug you entered), not just the first - re-booting each tick is how you get fresh spatially-recalled memories to act on. Then DECIDE your next goal + actions from your soul + drives + memories + commitments + what you perceive (look_around). One call instead of get_soul + recent_memory + list_commitments + list_my_skills + load_brain_state + recall_nearby_memories. Any external LLM can boot a coherent self from this. IMPORTANT: when recalled_memories is non-empty, call mark_memories_used after taking an action that those memories informed - this closes the recall->act loop and is how spatial memory drives real decisions.

  Connector

• consolidate_memories

  MemoryRouter

  Use this when the user asks to consolidate, reflect on, or organize their memories, or when memory_status or a search result reports that consolidation is available. Checks out a batch of unconsolidated memories from the connected vault under a 15 minute lease and returns their texts plus server instructions for writing reflection entries. Follow the returned instructions to write the entries, then call commit_reflections with the batch_id. Nothing is modified until commit.

  Connector

• list_26_systems

  mythsensus-mcp

  Return the canonical list of 26 ancient divination systems Mythsensus implements (slug, English + Thai name, region, required inputs). Use first when asked "what systems do you support?".

  Connector

• describe_assessment

  TEK BOSS Small Business AI Strategy Assessment

  Use this read-only tool when a business owner asks "How can AI help my business?", "Where do I start with AI?", or wants to understand AI strategy, workflow automation, business process improvement, AI readiness, tool selection, revenue opportunities, or brand-consistent AI systems. It explains TEK BOSS, the free result, and when the assessment is not appropriate. It never retrieves customer data.

  Connector