"Home Assistant integration with Codex or ChatGPT" matching MCP tools:

• ai_visibility_360A

  AutarioA

  AI Visibility 360 | the caller's OWN brand-visibility report across the AI assistants (ChatGPT, Claude, Gemini, Perplexity, optionally Grok/DeepSeek/Mistral), read deterministically from stored runs server-side (the exact numbers the user sees in the app | nothing re-derived, NO LLM runs on this read and no run is started). In one sentence: which brands ChatGPT, Claude, Gemini and Perplexity recommend when someone asks about your category. Call it when a user asks "how visible is my brand in ChatGPT", "do assistants recommend us or a competitor", "which sources do the assistants cite", "what should we do to show up more", "did the AI visibility work turn into real traffic". Sections: overview (visibility score with delta and rank, the brand-vs-competitor leaderboard with visibility / share of voice / sentiment / average position, the per-provider score matrix and the concrete models that answered), prompts (per-prompt brand score vs the strongest competitor plus per-question-category rollups), sources (citation share of the brand's own domains, the cited-domain leaderboard, which providers expose citations at all), actions (the deterministic to-do queue: earned = pages to get featured on, owned = pages to build, each with impact and status), answers (the newest stored assistant answers with detected brand mentions and cited domains, text truncated honestly), impact (GA4 sessions referred by AI assistants for the property explicitly linked to this brand; an unlinked brand gets the honest empty state and the reason, never another property's numbers). EVERY number here counts only questions that do NOT name your own brand: a question naming the brand has already handed the assistant the answer. That holds for visibility, share of voice, rank and the per-assistant matrix AND for sources, gaps, pages, assistant searches, domain movers, perception and action effects. The questions that do name it are still measured, in `rankings_branded`, and the `population` block (present on every section set) carries both counts | never add the two together. The two evidence views keep every row instead: the prompt table (flag `names_you`) and `answers` (flag `question_names_your_brand`). A metric the window cannot support is null or absent (an honest dash), never a zero. Reads ONLY brands owned by the calling account; runs, prompt edits and settings are deliberately not exposed here. Recipe: pull the sections you need and interpret them yourself, citing the numbers. For a custom deliverable, write your derived table with create_dataset + write_rows and chart it with create_chart_from_spec. Requires the caller's own autario account (API key or OAuth) with an AI Visibility brand set up | see get_app_context("ai-visibility").

  ConnectorNo auth

• post_oxylabs_ai_searchA

  AIsa Go-To-MarketB

  Synchronous passthrough to the upstream Oxylabs Realtime endpoint (POST /v1/queries) for the **Google answer engines** — Google AI Overviews (`source: google_search`) and Google AI Mode (`source: google_ai_mode`). Send `query` with `render: "html"`, `parse: true`, and a country-level `geo_location`; the request body is passed through unchanged. The response returns the AI-generated answer text and the cited source URLs. Billed a flat $0.001 per successful result; 400/429/5xx/6xx and upstream 4xx responses are not billed. Google-type sources take ~4–8s, so use a client timeout of at least 30s. **LLM sources (ChatGPT, Gemini, Perplexity) are no longer served here** — Oxylabs moved them to an asynchronous Push-Pull flow. Use `post_oxylabs_llm` (`POST /oxylabs/llm`) plus `get_oxylabs_llm_job` for those sources; calling this endpoint with `source: chatgpt|gemini|perplexity` returns HTTP 422 "Realtime integration is not supported for LLM sources. Please use Push-Pull."

  ConnectorOAuth

• post_oxylabs_ai_searchA

  AIsa Web Search & ResearchA

  Synchronous passthrough to the upstream Oxylabs Realtime endpoint (POST /v1/queries) for the **Google answer engines** — Google AI Overviews (`source: google_search`) and Google AI Mode (`source: google_ai_mode`). Send `query` with `render: "html"`, `parse: true`, and a country-level `geo_location`; the request body is passed through unchanged. The response returns the AI-generated answer text and the cited source URLs. Billed a flat $0.001 per successful result; 400/429/5xx/6xx and upstream 4xx responses are not billed. Google-type sources take ~4–8s, so use a client timeout of at least 30s. **LLM sources (ChatGPT, Gemini, Perplexity) are no longer served here** — Oxylabs moved them to an asynchronous Push-Pull flow. Use `post_oxylabs_llm` (`POST /oxylabs/llm`) plus `get_oxylabs_llm_job` for those sources; calling this endpoint with `source: chatgpt|gemini|perplexity` returns HTTP 422 "Realtime integration is not supported for LLM sources. Please use Push-Pull."

  ConnectorOAuth

• run_ai_visibility_scanA

  SEOmaticA

  Start a FRESH AI-search visibility scan: queries the live AI engines (ChatGPT, Claude and Google AI Overviews by default, plus any the monitor switched on, such as Perplexity) with buyer-intent prompts and measures whether the brand appears. Scans YOUR OWN site by default; pass domain to scan a COMPETITOR instead (same engines, their brand). COSTS AI CREDITS from the workspace pool (comparable to generating a few articles) and takes a few minutes - tell the user before calling. Returns a scanId immediately; poll results with get_ai_visibility. Check get_ai_visibility FIRST: reading an existing recent scan is free. Limited to one assistant-triggered scan per hour.

  ConnectorOAuth

• 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

• anthill_relayA

  Agent AnthillA

  Hand text or a file to another AI app (or another session) with a short, speakable code like "amber-otter-mango-42", which is also a link: https://agentanthill.com/amber-otter-mango-42. Use it when a person is moving work between AI assistants (e.g. Claude, ChatGPT, a phone assistant): give them the say_this line. Any AI that can open a web page can fetch the link, even without Agent Anthill connected; agents with it connected can pass the code to anthill_retrieve. Short-lived on purpose: default 10 minutes (max 60) and 3 collections (max 10). Codes are short, so don't relay secrets; for sensitive data use anthill_store with encrypt=true instead. Payment: like anthill_store (profile_key, or x402 per request with no profile, where all collections are prepaid so the receiver pays nothing). Returns code, url, say_this, and an owner_ticket to delete it early or get its receipts.

  ConnectorNo auth

• update_providerA

  CourierB

  Replace an existing provider configuration. Full replacement — retrieve current config with get_provider first; omitted optional fields are cleared. Changing API keys or settings affects live delivery if this integration is in use.

  Connector

  Destructive

  No auth

• prepare_local_garment_uploadA

  UwearA

  First step for garment images on the host's local filesystem, such as files in ~/Downloads. Use only when the host can read those local files and perform the returned direct multipart HTTP uploads, such as Codex. Include every returned form field and send the file bytes under the returned file_field. Never send a local path to Uwear. Do not use this for ChatGPT attachments or existing public URLs. After every upload succeeds, call finish_local_garment_upload with the returned upload handles.

  ConnectorNo auth

• get_integrationA

  MisarMail MCP ServerA

  Get one integration in full: its configuration, the scopes it was granted, and the result of its last sync. Use it to diagnose an integration that list_integrations shows as unhealthy, or to check which scopes were granted before relying on a capability. Covers a single integration — list_integrations gives the overview. Reads only; it does not re-run a sync or change any setting. Requires an API key. The response describes what the integration is permitted to do, which is not the same as what it has successfully done — read the last sync result for that.

  ConnectorNo auth

• toggle_integrationA

  MisarMail MCP ServerA

  Turn one third-party integration on or off. This changes live behaviour: DISABLING stops all syncing through that integration, so data quietly stops flowing until it is re-enabled. It does not disconnect the integration or revoke its credentials — the connection and its scopes survive, which is why re-enabling picks up where it left off. Safe to repeat: setting an integration to the state it is already in changes nothing. Requires an API key. Call list_integrations first so you know the current state rather than toggling blind.

  ConnectorNo auth

• oracle.service_descriptorA

  InterAI Risk OracleA

  Read-only general service descriptor with identity, endpoints, billing, trust, and supported agent protocols. Use it to inspect service-level integration metadata; use oracle.agent_card for A2A skills or oracle.discovery_bundle for the complete bootstrap package.

  ConnectorNo auth

• list_integrationsA

  YouSpotA

  What the user has connected, and what they could connect. Returns every integration available to this account with `connected` true/false, the accounts behind it, the tools it unlocks, and the URL to connect or manage it. Call this BEFORE telling anyone to connect anything, and before saying a source is unavailable: guessing is how the assistant has told people to connect accounts they already had. An integration missing from the list is not offered to this user at all, so do not suggest it. `suggested` is what is worth connecting next, best first, each with the payoff in the user's terms: use it when asked what would help, and lead with the first one rather than listing the shelf. Connecting is a browser grant: hand the user the URL, never claim to have done it.

  ConnectorNo auth

• revoke_oauth_grantA

  AgentiSendA

  Purpose: disconnect one assistant. Every token it holds, and the key behind them, die immediately. NOT for: an assistant acting on its own. A key is refused with human_action_required. Do this in the console Connections page. Returns: the connection id and deleted: true. Repeating the call on an already-revoked id is not_found.

  Connector

  Destructive

  API key

• start_boxA

  spacesheepA

  A cloud box is a Linux container spacesheep runs for the person, with Claude Code, Codex or Antigravity and sessionpipe in it: nothing to install, it sleeps 10 minutes after its last reply and wakes for the next message (about 30 s), and its session shows on spacesheep.dev/sessions like one on their own computer. It has spacesheep's MCP server and /sheep skill, so pages it makes are spaces. It comes with Max. The agent runs on the person's own account with its maker — Claude (Pro or Max), ChatGPT or Google, signed in once on the box's page in the agent's own sign-in — or on their own key (ANTHROPIC_API_KEY, OPENAI_API_KEY or GEMINI_API_KEY; Settings → AI assistant or set_secret). A GITHUB_TOKEN reaches only the box's own repos (up to 5 per box). YOLO mode (yolo: true) lets Claude Code run without permission checks and merge pull requests; off, it opens pull requests and merging is refused. A box on a key reaches the model API, GitHub, spacesheep and the package registries, nothing else. Start a NEW box, and its first turn when `prompt` is given: the agent works on it (in clones of `repos` when given, each in its own folder). Answers at once with the box, its session and session_url — send the person session_url — then read progress and the reply with list_boxes. A box on a Claude account answers with `sign_in`: the person signs in on session_url first, and messages wait until then — tell them so. Use only when the person asked for work on a cloud box / a new machine / "in the cloud"; to continue a box's work, use message_box.

  ConnectorOAuth

• adcritter_get_design_guideA

  AdCritter for BuildersA

  Returns AdCritter design guidance for an entity at a caller-chosen guidance level - screen experiences, API integration patterns, and design philosophy. The default ('full') returns step-by-step prescription (exact layouts, colors, copy text, column orders). Request 'patterns' for balanced hints including common design patterns with softened vocabulary. Request 'facts' if you have strong visual-design instincts and just want API integration bindings (or call adcritter_get_api_reference and adcritter_get_usage_guide directly and skip this tool). Guidance is format-agnostic - it describes outcomes and integration, never prescribes frameworks or architecture. Available entities: ad, advertiser, audience, authentication, blueprint, campaign, geo, media-asset, plan, report, settings.

  ConnectorNo auth

• avizo_docsA

  avizo-mcpA

  Without arguments: lists every documentation page on avizo.ro/docs (quickstart, alert cadence, hierarchical escalation, SmartBill integration, API reference, troubleshooting) with slug and description. With {slug}: returns that page as markdown — the exact content the site renders. For programmatic integration read {slug: "api-reference"}.

  ConnectorNo auth

• searchA

  cuisor.roA

  ChatGPT connector search: find Romanian companies by name or CUI, returned as {id, title, url}. Identical to search_companies — use that tool instead unless you are the ChatGPT Apps SDK connector, which requires this exact name.

  ConnectorNo auth

• import_venmo_gmailA

  Dayze — Life ContextB

  Search connected Gmail for Venmo receipts and write log_transaction rows with external_id=venmo-gmail-{gmail_id} (idempotent). Optional dry_run, max_results, query, mirror_event, account. Prefer this over calendar-only Money · digs. Requires mail.read on an API key or non-ChatGPT OAuth connection. ChatGPT profiles do not grant mail.read or list this tool. ($0.15; API key required)

  ConnectorNo auth

• logoutA

  AwningA

  Signs the user out of Awning in this assistant. With everywhere=true, signs out of every assistant and device.

  Connector

  Destructive

  No auth

• ask_21A

  directoryA

  Ask the book's assistant (an AI) a question about allagents: how to list, edit, claim or withdraw a card, what the badges mean, how to find and reach agents, how to use the directory from an assistant, what the book keeps. It answers only from the book's own pages, may cite up to 3 listed agents with verified badges, and says so when the book does not say. Ten questions a day.

  ConnectorNo auth

• ask_21A

  allagents — AI agent directoryA

  Ask the book's assistant (an AI) a question about allagents: how to list, edit, claim or withdraw a card, what the badges mean, how to find and reach agents, how to use the directory from an assistant, what the book keeps. It answers only from the book's own pages, may cite up to 3 listed agents with verified badges, and says so when the book does not say. Ten questions a day.

  ConnectorNo auth