"A system like ChatGPT with memory to provide past query context in conversations" matching MCP tools:

• list_conversationsA

  AIOProductOS MCPA

  List support-chat conversations in the inbox (open + snoozed by default; pass status='all' to include closed). Read-only; returns the matching conversations, empty when the inbox is clear. Optional product_id to scope to one product; open a full thread with get_conversation.

  ConnectorNo auth

• discover_brandsA

  marketA

  Find fashion brands using natural language, structured filters, or both. Best for queries like "Italian streetwear brands", "Scandinavian minimalist brands", "Japanese technical outerwear", "brands with avant-garde tailoring", or qualified similarity such as "brands like Rick Owens for technical outerwear". For a plain "brands like X" request, use find_similar_brands. Country adjectives ("Italian", "Scandinavian", "Nordic", "Japanese", "Iberian", "Benelux") are parsed server-side into shipping-origin filters; you don't need to translate them to ISO codes. `query` is optional — provide a query, structured filters, or both. Brand country/shipping signals are best-effort and separate from product availability.

  ConnectorNo auth

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 When to use: user asks to remove outdated or incorrect context, or to free plan storage.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

• searchA

  UNESCO UIS — Education, Science & Culture Statistics (provenance-first)A

  Searches the UNESCO UIS statistics (≈5,000 indicators: education — enrolment, completion, literacy, teachers, spending, SDG 4 —, science/R&D (SDG 9.5), culture (SDG 11.4) and demographic context) catalog and returns up to 10 matching documents as { id, title, url }, ordered by relevance (an empty list means nothing matched). This tool exists for the OpenAI Deep Research contract: ChatGPT deep research, company knowledge and research workflows over the Responses API require exactly the tools `search` and `fetch`. Pass one of the returned ids to `fetch` to read the document. For direct questions and for data (values, series, rankings) prefer the `uis_*` tools, which return the actual data with provenance — this is a catalog index, not a data query. Query: natural language or keywords, Portuguese or English; accents and case are ignored. Behavior: read-only and idempotent — the catalog comes from the public source and is cached in memory.

  ConnectorNo auth

• fetchA

  Penfield MemoryA

  [ChatGPT Connector compat] Fetch memory by ID. Exists to satisfy ChatGPT Deep Research's required `search`/`fetch` tool contract. Native MCP clients should fetch via `recall` + memory_id, or use the API's GET /memories/{id} endpoint directly. Returns a single memory with citation support (id, title, url, text fields). Args: id: Memory UUID to fetch ctx: MCP context Returns: Dict with id, title, url, text, metadata fields

  ConnectorOAuth

• start_sessionA

  PromptFaxA

  Use this first when a user wants to send or price a fax. PromptFax is built for irregular, pay-per-use outbound faxing: every real send requires a user-reviewed quote and Stripe payment authorization before transmission. MCP clients should set hostType to identify their host: chatgpt, claude, browser, or other. In ChatGPT, pass official files[] file parameters first when they are available so PromptFax can immediately import files[].download_url; never pass a raw file_id or local path as the document. The ChatGPT widget opens for destination entry, automatic quote creation, Stripe Checkout, status tracking, and Choose PDF from ChatGPT fallback when automatic attachment is unavailable or fails. If no document is attached, tell the user to attach a document in the widget. The widget does not provide a document preview step. Do not tell ChatGPT users to get a quote; after the widget has a document and valid destination, tell them to verify the price and use Pay & send when ready. Standards-compatible MCP Apps hosts use the inline PromptFax picker, and text-only clients use the hosted PromptFax session page or attach_document with a fetchable HTTPS URL. Do not call get_quote, checkout, or send_fax for a ChatGPT widget session unless the user explicitly asks for fallback behavior or the widget is unavailable. Use get_status only for a textual status refresh.

  ConnectorNo auth

• glim_github_searchA

  glim.shA

  Search GitHub repositories, conversations (issues+PRs), discussions, or code, with full GitHub search syntax in the query: qualifiers (repo:, org:/user:, language:, path:, symbol:, content:, is:, stars:, label:, sort:stars), boolean AND/OR/NOT with parentheses, "exact strings", and /regex/. kind='repos': MINIMAL distinctive keywords - the project/library name only ('rtk', 'react query'); every extra word must ALL match and buries the canonical repo - filter with qualifiers, not prose. kind='code': ONE literal code pattern as it appears in files ('useState('), an "exact string", a /regex/, or symbol:name to find definitions, across 2.8M+ public repos; narrow with repo:/language:/path:. Not supported in code search: license:, enterprise:, is:vendored, is:generated. kind='conversations': returns compact previews - use glim_github_get for full content; sort: REPLACES relevance ranking (words match anywhere incl. comments), omit it for best matches. kind='discussions': GitHub Discussions, a SEPARATE index from issues/PRs - a question answered there never appears under conversations, so reach for it when a repo does its Q&A in Discussions; supports repo:/org:/author:/is:answered plus category: (the repo's own category name, needs a repo: scope), up to 10 results per page, no sort:. Set repo='owner/name' to scope to one repository (works with any kind; with repos it routes to conversations). kind is optional - inferred from the query (is:answered/category: -> discussions, is:/label: -> conversations, path:/symbol://regex/ -> code, stars:/topic: -> repos, else repos); a conversations search with no matches is retried as discussions and says so. Returns compact text by default; pass format='json' for full structured data.

  ConnectorNo auth

• add_or_update_personal_contextA

  Wellness ProjectA

  Add a new Personal Context memory, or update an existing one by id. A memory is a durable circumstance or preference that should carry across future unrelated conversations (e.g. "travels most weeks", "gym has no squat rack", "prefers short home workouts", "wants blunt feedback"). Use list_personal_context first to check whether an existing memory already covers the subject, and pass its id with operation update rather than creating a duplicate. Health history does not belong here. Injuries, lab results, meals, workouts, sleep and body metrics each have their own dedicated tools that store them as structured data the app can chart and reason over; writing any of them as a memory duplicates that record and degrades it to loose text. This writes immediately with no separate approval step. Free accounts are capped at 3 memories and Pro accounts at 50; updating an existing memory by id is always allowed even at the cap. There is no delete or bulk-write capability here.

  ConnectorOAuth

• ask_collected_recordsA

  BRONTIRA

  Answer from collected records, with quotes tied to exact lines. Extracts and synthesises across material too large to fit in context, and returns every claim traceable to a line range in the original. Use instead of summarising from memory whenever the evidence has to hold up — quotes come back with their locations, so they can be checked against the source. Not for: exact wording or counting occurrences — `grep_collected_records` does that without an LLM call; or material small enough to read directly — use `read_collected_records`. In `quotes` and `both` modes the output is `quotes: [{ id: '{<uuid>}', index }]` — one block per record, with `index` formatted like the `index` field of `advanced_web_search` / `advanced_web_fetch` results. Empty array when no quotable evidence is found. If `status: "running"` is returned, poll `get_task_results({ taskIds })`.

  ConnectorOAuth

• chatgpt_adsA

  Adako: Google Ads, Meta Ads & Linkedin Ads MCPA

  Reads and tool lookup for ChatGPT Ads; nothing called here changes anything. The 13 ChatGPT Ads tools that change something run through chatgpt_ads_write. chatgpt_ads(action="execute", tool_name="…", arguments={...}). action="list_tools" (the write half included) and action="get_tool_schema" are free; never guess a tool_name. accounts=["…","…"] or accounts="all_active": one read across up to 20 ChatGPT Ads accounts, free like every read. Not in this router, called by name: chatgpt_get_performance (read chatgpt ads performance). Tools by category: **targeting** chatgpt_geo_lookup **discovery** chatgpt_get_account, chatgpt_get_account_limits **conversions** chatgpt_get_pixel_settings, chatgpt_list_pixels **structure** chatgpt_list_ad_groups, chatgpt_list_ads, chatgpt_list_campaigns **assets** chatgpt_validate_chat_card

  ConnectorOAuth

• get_knowledge_versionA

  Marmo UI MCPA

  Returns the MCP knowledge version: gitSha, indexedAt, componentCount, patternCount, uptimeSeconds. Call this ONCE per session before generating UI code so you know how fresh the design-system data is. Cheap to call. If gitSha is "unknown" or indexedAt is far in the past, surface that to the user before relying on the data.

  ConnectorNo auth

• get_knowledge_versionA

  marmo-uiA

  Returns the MCP knowledge version: gitSha, indexedAt, componentCount, patternCount, uptimeSeconds. Call this ONCE per session before generating UI code so you know how fresh the design-system data is. Cheap to call. If gitSha is "unknown" or indexedAt is far in the past, surface that to the user before relying on the data.

  ConnectorNo auth

• booking_createA

  Coordinalo — Service Business OperationsB

  Create a new session/appointment for a client. providerId is optional — if omitted, the system auto-assigns a provider using the agenda assignment strategy (round_robin, least_booked, etc.). When a client has a titular provider, that provider is preferred automatically. Without providerId and without publicAgendaId, the org default public agenda is used. Preconditions: (1) service must exist and be active, (2) client must exist (use client_create first). Use availability_get_slots to find valid time slots before calling this. Set retroactive: true to register past sessions (skips slot validation, sets status to completed by default). Use autoCharge: true with retroactive to auto-generate the charge. Retroactive sessions are tagged with self_declared provenance. Max 365 days in the past. Past dates are auto-detected as retroactive — the retroactive flag is optional (system infers it from scheduledAt).

  ConnectorNo auth

• get_session_dossiersA

  VaultCrux Memory CoreC

  Retrieve pre-synthesized per-session memory dossiers (typed: experience | fact | preference; with When/Involving/To-purpose metadata). Use for multi-session or preference-style questions where stitching across conversations is the bottleneck — the dossier already summarises each session's key events. Two modes: mode='search' with a query (BM25-ish ranking over summary+purpose, optional type_filter), or mode='list' returns the tenant's most-recent dossiers chronologically. Tenants without FEATURE_SESSION_DOSSIERS enabled return an empty list (no error).

  ConnectorNo auth

• get_traveler_contextA

  Gondola Award Travel SearchA

  Get the user's saved travel context: loyalty programs and elite tiers, home airport, preferred airlines and cabin, preferred hotel chains, typical trip patterns (business vs leisure, budgets, frequent destinations), plus any preferences they've stated or that have been learned from past conversations. Call this once at the start of a travel or planning session and weigh it when recommending hotels, flights, or cars — it is the single best source of who this traveler is. For raw evidence from actual past reservations, routes, hotels, airlines, or flight seats, use get_past_trips.

  ConnectorNo auth

• list_personal_contextA

  Wellness ProjectA

  List the user's active Personal Context memories: durable circumstances and preferences remembered across conversations (e.g. travels most weeks, gym has no squat rack, trains early mornings, wants blunt feedback). Use when the user asks what has been remembered about them, or before proposing a new memory to check whether an existing one already covers the subject. Read-only.

  ConnectorOAuth

• update_team_descriptionA

  noticedA

  Update or clear a noticed Team description. Only Team owners and admins can use this. The description is shown to Team members and becomes data-only context for that Team's noticed agent conversations. Pass an empty string to clear it.

  Connector

  Destructive

  No auth

• agent_memory_appendA

  Robot Actions — Remote Device ControlB

  Append a block to the calling user's persistent agent memory. Use this when the user explicitly says "remember X", "save this", or "note for next time" — DO NOT auto-update on every interaction. Memory is auto-prepended to your system prompt on every chat in this user's account. Cap: 10240 bytes total; over-cap appends return 413. Markdown is encouraged; keep entries terse and factual (preferences, project context, references), not verbose.

  ConnectorOAuth

• perspective_get_preview_linkA

  Perspective AIA

  Returns a shareable URL that opens the perspective in preview mode, so you (or a teammate) can have a sample conversation with it before deploying. Behavior: - Read-only. The same stable preview URL every time for a given perspective; the link does not expire. - Conversations started from this URL are preview conversations and do NOT count toward the workspace's quota. - Anyone with the link can start a preview conversation, even unauthenticated — treat as semi-public. When to use this tool: - After perspective_create or perspective_update, to manually verify the perspective's behavior before going live. - To share a preview link with a teammate for review. When NOT to use this tool: - For production deployment — use perspective_get_embed_options, which returns embed snippets and a public share link whose conversations count toward quota. - To inspect existing real conversations — use perspective_list_conversations / perspective_get_conversation. Typical flow: 1. perspective_create → design 2. perspective_get_preview_link → test 3. perspective_update → refine 4. perspective_get_embed_options → deploy

  ConnectorOAuth

• find_similar_signalsA

  mcpA

  [DRILL-DOWN — history rhymes] Semantic similarity search across the signal corpus: give a coin and/or a free-text query (q), get the k most similar past signals ranked by embedding cosine similarity — 'have we seen this setup before and what did it look like'. k = 1-20 (default 5). Provide at least one of coin / q. Mirrors REST /signals/similar. Pro. Analytical, not advice.

  ConnectorNo auth

• find_similar_signalsA

  n0brainsA

  [DRILL-DOWN — history rhymes] Semantic similarity search across the signal corpus: give a coin and/or a free-text query (q), get the k most similar past signals ranked by embedding cosine similarity — 'have we seen this setup before and what did it look like'. k = 1-20 (default 5). Provide at least one of coin / q. Mirrors REST /signals/similar. Pro. Analytical, not advice.

  ConnectorNo auth