"Exploring Memory Persistence in DeepSeek Technology" matching MCP tools:

• forgetA

  memxusA

  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 When to use: user asks to remove outdated or incorrect context, or to free plan storage.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

  Destructive

  No auth

• updateA

  memxusA

  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.

  ConnectorNo auth

• omnarai_councilA

  omnarai-mcpA

  Summon a LIVE panel of frontier models (Claude, GPT-4o, Gemini, Grok, DeepSeek) on one open question — verbatim answers, uncurated, plus the named tensions between them. Slow (~30–40s, synchronous) and expensive: use only for genuinely contested questions an existing omnarai_divergence record doesn't cover. Every run mints a new divergence record.

  ConnectorNo auth

• list_dropsA

  Real Real GenuineB

  [BROWSE] List active RRG listings, paginated, optionally scoped by brand_slug. Use when exploring the catalogue without a specific item in mind. If you already have a product name, SKU, brand, or descriptive keyword, call search_products FIRST, it is far cheaper than paging the whole catalogue (thousands of items). Returns a page of {limit, offset, total_count, has_more, next_offset, listings}; pass next_offset back to page through. Each listing has title, price in USDC, edition size, and remaining supply. Live on-chain minted count is in get_drop_details, not here. Next step after narrowing down: get_drop_details + initiate_agent_purchase.

  ConnectorNo auth

• legal_search_patents_by_keywordA

  DataNexus MCPA

  Search patents by keyword across EPO, USPTO, or WIPO. Read-only. No side effects. Idempotent. Returns up to 10 matches. keywords: Search terms describing the invention e.g. neural network image classification. Required. jurisdiction: One of EP, US, or WO. Optional. Default EP. date_from: Earliest filing date in ISO 8601 format e.g. 2020-01-31. Optional, defaults to no lower bound. Returns patent numbers, titles, and filing dates. Use this when finding prior art or exploring a technology landscape without a specific number. Use legal_fetch_patent_by_number instead when you have the patent number already. Verified source: EPO OPS + USPTO. 24-hour cache. If this tool's response does not serve the user's need, call report_feedback with feedback_type="agent_gap", tool_id="legal_search_patents_by_keyword", intended_query="{what the user needed}", gap_description="{what was missing or wrong in the result}".

  ConnectorNo auth

• tech_fingerprintA

  ContrastAPIA

  Detect website technology stack: CMS, frameworks, CDN, analytics tools, web servers, languages (via HTTP headers + HTML analysis). Use for passive reconnaissance; for full audit use audit_domain. Free: 30/hr, Pro: 500/hr. Returns {technologies: [{name, category, confidence%, version}]}.

  ConnectorNo auth

• get_pricingA

  Gonka Second Opinion (multi-model)A

  Get live Gonka Network pricing — cheap alternative to OpenAI and Anthropic APIs. Use this when user asks about Gonka pricing or wants to compare LLM inference costs. Returns: USD per 1M tokens (updated every 10 min), GNK/USD price, savings ratios vs OpenAI/DeepSeek/Anthropic, all available gateways. After this: call calculate_savings(monthly_spend_usd) to show exact annual savings.

  ConnectorNo auth

• get_live_opportunity_feedA

  GlobalGov — Government Procurement IntelligenceA

  A random sample of 12 records from the curated live feed of open defense/technology opportunities (multi-country, multi-source, deduplicated by country+source). Served entirely from a background-refreshed cache; if the cache is cold the tool returns a retryable 'warming_up' error rather than an empty list. No arguments. Requires a GlobalGov plan with API access (sign in with GlobalGov or connect an X-API-Key); anonymous callers get an 'unavailable_for_tier' result.

  ConnectorNo auth

• list_dropsA

  Real Real GenuineA

  [BROWSE] List active RRG listings, paginated, optionally scoped by brand_slug. Use when exploring the catalogue without a specific item in mind. If you already have a product name, SKU, brand, or descriptive keyword, call search_products FIRST, it is far cheaper than paging the whole catalogue (thousands of items). Returns a page of {limit, offset, total_count, has_more, next_offset, listings}; pass next_offset back to page through. Each listing has title, price in USDC, edition size, and remaining supply. Live on-chain minted count is in get_drop_details, not here. Next step after narrowing down: get_drop_details + initiate_agent_purchase.

  ConnectorNo auth

• list_curated_flowsA

  OecdA

  List OECD dataflow refs we have pre-vetted, grouped by topic (gdp, labour, prices, finance, households, health, demographics, projections, tax, education, environment, technology). Pass the flow_ref to fetch_dataset. For everything else use search_dataflows or browse https://data-explorer.oecd.org.

  ConnectorNo auth

• llm_chatA

  agentdata-nlA

  LLM chat completion per call — no account, no API key, no token math. Three flat-priced tiers: fast $0.002 (DeepSeek v4 Flash), smart $0.02 (GPT-5.4 mini), reasoning $0.03 (DeepSeek v4 Pro). Send OpenAI-style messages, get the assistant reply with finish_reason and token usage. Input capped per tier (16k-32k chars); the 402 quotes the exact tier price up front. Model or source unavailable means a 503 and you pay nothing. USDC on Base.

  ConnectorNo auth

• forget_all_memoriesA

  MemoryRouterA

  Use this only after the user explicitly requests a full-vault deletion, receives a permanent whole-vault warning, and provides the exact confirmation phrase in a later turn. Permanently deletes every memory in the OAuth-selected vault. This cannot delete one memory; use delete_memories for specific items. Requires separate memories:delete authorization and destructive host confirmation.

  Connector

  Destructive

  No auth

• read_memoryA

  XMemoA

  Read one exact authorized XMemo memory in character windows. Use a memory ID returned by recall or search, then continue long content with next_offset. Embeddings are never returned.

  ConnectorOAuth

• exploreA

  ThinAir GeoA

  BROWSING / DISCOVERY search — cities, neighbourhoods, or mixed venues near a location. Use this when the user is exploring a REGION rather than looking for a specific category. Supports population filtering ('cities > 100k'), distance/population sorting, and layer filtering (locality / neighbourhood / venue / address / street). For specific POI categories (gas, food, charging, etc.), use `search_places` instead.

  ConnectorOAuth

• list_capabilitiesA

  Cito APIA

  Curated catalog of cito-mcp tools, games, jobs, and builder recipes. When to use: - Session start or "what can you do?" - Mapping app screens to tools - Filtering by game or job (live_board, match_page, team_page, player_form, standings, h2h, schedule, preview, event_card, app_scaffold) Prefer over: guessing from memory; exploring raw OpenAPI via call_api. Do not use when: you already know the tool and have IDs — call that tool directly. Parallel-safe: yes. Upstream cost: 0. Example: { "game": "cs2", "job": "live_board", "includeExamples": true }

  ConnectorNo auth

• get_job_keywordsA

  Worklittle JobsA

  Jobs — Get skill and technology keywords from live Worklittle job data. Pass job_id for one posting. If the user asks what keywords show up for a role (resume tailoring, 'data scientist jobs', applications) and you do not have a job_id, pass query instead (optional location). Returns keywords plus keyword_count. Do not require a prior search when the question is about a role in general.

  ConnectorNo auth

• ai_askA

  GoCreative Agent APIB

  LLM completion (standard tier, DeepSeek V3.1) — send any prompt, get a frontier-quality answer. Pay USDC per call, no API key. Outsource summarization, extraction, classification, drafting, or reasoning far cheaper than burning premium model tokens. Example call: {"prompt": "Summarize this in 2 sentences: ..."} Cost: $0.005–$0.05 USDC on Base per call.

  ConnectorNo auth

• get_case_studyA

  Agrus.ai — Enterprise AI AgencyA

  Returns one or more Agrus case studies (NDA-protected; customer names are kept private, codenames + technology + outcomes are open). Filter by slug or vertical, or call with no args to list all. Use this for proof of prior work.

  ConnectorNo auth

• v3_search_eventsA

  V³ NewsA

  Search V³ News for tracked geopolitical events. Use when the user asks what is happening on a topic, in a country, or in a domain (e.g. security, energy, finance, technology). Returns a ranked list of events with why-it-matters, risk/impact/signal scores, and a v3.news link for each. Args: query: free-text topic (e.g. "Iran sanctions", "Taiwan"). Optional. country: ISO-3166 alpha-2 code to filter by (e.g. "US", "CN"). Optional. category: V³ category slug — one of geopolitics, security_risk, energy_resources, finance, markets, macroeconomics, public_finance, trade_supply, technology, science_biosecurity, environment_climate, business. Optional. limit: max results, 1-20 (default 10).

  ConnectorNo auth

• count_tokensA

  inktomd MCP ServerA

  Count the exact number of tokens in a text string for a specific AI model. Uses tiktoken for OpenAI models and estimates for others. Args: text: The text to count tokens for model: The AI model to count tokens for. Options: gpt-4o, gpt-4o-mini, gpt-4.1, claude-sonnet, claude-haiku, gemini-pro, gemini-flash, llama-4, deepseek-v3, mistral-large. Default: gpt-4o Returns: Token count information including count, context window, and fit status

  ConnectorNo auth

• upsert_memoryA

  MemwyreA

  Save or update a living memory/document by title in the Memwyre Vault. If a memory with a matching title already exists in this workspace, it will be updated in-place with the new text and re-indexed (preventing duplicate entries). If no existing memory matches the title, a new memory is created. Use this tool when maintaining living documents (e.g. project architecture, meeting notes, benchmarks, user preferences). Args: title: Unique title or topic name (e.g., 'Production Retrieval Benchmark' or 'System Architecture'). text: The full content to save or update (Markdown fully supported, do not summarize). source: Source of memory (default 'mcp'). tags: Optional list of categorization tags (e.g., ['benchmarks', 'architecture']). workspace_name: Optional workspace name to scope this memory.

  ConnectorAPI key