# agentView MCP server

Display delivery platform for AI agents. Push HTML, dashboards and live data to screens.

## Links
- Registry page: https://www.getdrio.com/mcp/de-agentview-agentview-mcp
- Website: https://agentview.de/developers.html

## Install
- Endpoint: https://agentview.de/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://agentview.de/mcp

## Tools
- invite_member (Invite Member) - Creates an invite link to add a new member to an organization. The invite is valid for 7 days. Optionally bind it to a specific email address. Requires admin scope and the user must be an admin or owner of the organization. Returns the inviteUrl to share with the invitee. Endpoint: https://agentview.de/mcp
- list_data_slots (List Data Slots) - Lists data slots with optional filtering. Returns metadata only (no jsonContent). Each item includes slug, publicId, and readUrl. The readUrl embeds the slot's PublicId (not its Slug): /data/u/{publicSlug}/{publicId}.json or /data/g/{groupSlug}/{publicId}.json. Use readUrl in display HTML fetch() calls. Requires authentication. Endpoint: https://agentview.de/mcp
- set_display_grant (Set Display Grant) - Grants a specific user access to a specific display within an organization. Creates or updates the grant. The target user must be a member of the organization. Access levels: 'view' (see status) or 'control' (send content). Requires admin scope. Endpoint: https://agentview.de/mcp
- authenticate (Authenticate) - Validates a JWT agent token and caches the resulting identity on the current MCP session so that subsequent protected tool calls succeed without resending the token. Use this only if your client cannot reliably send an Authorization: Bearer header on every request; modern streamable HTTP clients should send the header instead. Do not call this if the session was already auto-authenticated by get_auth_session. Returns authenticated (boolean), sessionBound (whether the identity was cached on this session), userId, name, email, scope and expiresAt (ISO 8601). Endpoint: https://agentview.de/mcp
- create_api_key (Create API Key) - Creates a long-lived API key for server-to-server integration without OAuth. The raw key is returned only once — store it securely. The user must explicitly consent to creating the key. Requires admin scope. Supports granular scoping: restrict the key to specific data-slot slugs, specific display IDs, a read/write permission flag, and/or fine-grained capability flags. Returns the raw key (avk_...), keyId, name, scope, permissions, allowedSlotSlugs, allowedDisplayIds, capabilities, and expiration. Endpoint: https://agentview.de/mcp
- get_data_slot (Get Data Slot) - Returns the current JSON content and metadata of a data slot by slug. Supply group_id to look up a group slot; omit it for personal slots. The response includes readUrl — the public anonymous URL (which embeds the slot's PublicId, not its Slug) for display HTML to fetch. Requires authentication. Endpoint: https://agentview.de/mcp
- get_store_template_agent_artifact (Get Store Template Agent Artifact (Raw)) - Returns the RAW body of one agent-onboarding artifact shipped with a store template (system prompt, Agent Skills SKILL.md, MCP-config snippet, …). Placeholders ({{slot:KEY.prop}}) are NOT substituted — use this BEFORE installing, when there is no display to resolve slot slugs against. After install, use get_display_agent_artifact for the substituted body ready to paste/save. Discover artifact keys via get_store_template_details (agentArtifacts array). No authentication required. Endpoint: https://agentview.de/mcp
- create_org_display (Create Organization Display) - Creates a new display directly within an organization WITHOUT pairing it to physical hardware. The display starts offline and uncoupled. For physical screens, ALWAYS prefer pair_by_code instead — it creates and pairs in one step. Use create_org_display only for administrative pre-provisioning when the screen is not yet available. The display is owned by the organization, not by a personal user. Requires admin scope and manager or higher role in the organization. The organization must have available licenses (use allocate_licenses first if needed). Endpoint: https://agentview.de/mcp
- get_display_agent_artifact (Get Display Agent Artifact (Substituted)) - Returns the agent-onboarding artifact body ready to paste/install for a specific display, with {{slot:KEY.prop}} placeholders resolved against this display's installed slot slugs. The killer flow: 'Add my Claude Code agent to my agentView swarm display' → list_displays() → get_display_agent_artifact(display_id, key='agent-skill') → write response.content to ~/.claude/skills/agentview-swarm-bot/SKILL.md. Requires content scope and ownership of the display. Unresolved placeholders are kept verbatim in .content and listed in .unresolvedPlaceholders. Endpoint: https://agentview.de/mcp
- broadcast_content (Broadcast Content) - Sends HTML content to multiple displays at once. Provide display_ids to target specific displays or set all to true to target all accessible displays. Locked displays are skipped. Returns sent and skipped lists with reasons. Requires content_only scope. Endpoint: https://agentview.de/mcp
- set_display_privacy_mode (Set Display Privacy Mode) - Sets the per-display privacy mode that caps how long share-links can live. 'Private' (the GDPR-by-default state for new displays) caps share-link TTL at 1 hour and is the right choice for displays that might show PII (waiting-room patient names, conference attendee lists, internal dashboards). 'Public' opts the display in to digital-signage mode for passers-by content (bistro menus, lobby greetings, kiosk loops) and lifts the cap to 24 hours. Flipping a display to Public is audit-logged so 'who flipped this Public?' is traceable later. Requires admin scope. Returns id, name, privacyMode, previousPrivacyMode, shareLinkMaxTtlSeconds and a changed flag. Endpoint: https://agentview.de/mcp
- get_public_status (Get Public Status) - Returns the server's public readiness status, version string and discovery URLs. Use this before authenticating to verify the server is reachable and to obtain entry-point URLs. No authentication required. Returns status ('ready'), server name, version, statusUrl and instructionsUrl. Endpoint: https://agentview.de/mcp
- get_display (Get Display) - Returns the full details of a single display including its live state, current content, pairing links, screen and viewport facts, touch capability, runtime classification, hardware/UI settings, and the latest reported browser/runtime facts. Use this when you already know the display ID and need its complete state. Do not use this to discover displays — use list_displays first. Requires authentication with at least content_only scope. Endpoint: https://agentview.de/mcp
- create_auth_session (Create Auth Session) - Creates a browser-based login session and returns a loginUrl the user must open to authenticate. Use this as the first step when your client cannot complete OAuth 2.1 with PKCE itself. Do not use this if you already have a valid Bearer token. Returns sessionRequestId (needed for get_auth_session), loginUrl, pollUrl and expiresIn (seconds until the login window closes, default 600). After calling this, instruct the user to open the loginUrl, then poll get_auth_session until status becomes active. Endpoint: https://agentview.de/mcp
- set_idle_content (Set Idle Content) - Sets or clears the default idle content for a display. Idle content is shown whenever the display has no active live content (after clear_display, after duration expires, or on first connect). Provide html to set idle content, or omit it to clear idle content and revert to the system default. Provide content_description to improve later state reads. Requires admin scope. Returns id, name and idle content metadata. Endpoint: https://agentview.de/mcp
- list_store_categories (List Store Categories) - Lists all published agentView store categories (e.g. Gastronomie, Wartezimmer, Empfang, Smart Home) with localized titles, descriptions and template counts. Use this to narrow a subsequent search_store_templates call when the user asks for 'templates for a waiting room' or similar. No authentication required. Returns count, language and a categories array; each entry has slug, title, description, templateCount, heroIconKey and detailPath. Endpoint: https://agentview.de/mcp
- update_member_role (Update Member Role) - Changes a member's role within an organization. Cannot change your own role or the owner's role. Requires admin scope and admin or owner role. Endpoint: https://agentview.de/mcp
- send_store_template_to_display (Send Store Template to Display) - Installs a published store template onto one of the user's displays. The server materializes the template HTML, auto-creates required data slots (reusing slots from a prior install when possible) and publishes so the screen updates within seconds. Always call get_store_template_install_options first so you know which slots this template needs and which displays the user can target. The data_slot_overrides argument lets you customize per-slot JSON inline without a follow-up set_data_slot call — perfect for 'show my daily menu' flows where the LLM generates the JSON on the fly. Requires content_only scope, control access to the target display, and (for API-key callers) the display.send capability. Returns templateSlug, versionId, displayId, fileName, contentVersionId and installedSlots (each with key, placeholderName, slug, readUrl, groupId, type). Endpoint: https://agentview.de/mcp
- delete_data_slot (Delete Data Slot) - Permanently deletes a data slot. Display HTML fetching its readUrl will receive 404 after deletion. Cannot be undone. Supply group_id to delete a group slot; omit for personal slots. Requires authentication. Endpoint: https://agentview.de/mcp
- create_display (Create Display) - Creates a personal display profile WITHOUT pairing it to physical hardware. NOT the normal setup flow — for any ambiguous 'create a display' / 'add a screen' / 'set up a display' / 'neues Display' request use pair_by_code instead. agentView is purely browser-based with no native app: ask the user to open https://display.agentview.de on the target screen, read the 6-character code, then call pair_by_code. Use create_display ONLY when the user explicitly wants to pre-provision without hardware, create a virtual/headless display, or manage an existing profile separately from device setup. Don't call this just to check capacity — use get_account.remainingDisplays. Requires admin scope. Returns a pre-provisioned offline profile (id, name, setupUrl, managedUrl, pairingUrl, pairingExpiresAt, approvalUrl, status). Endpoint: https://agentview.de/mcp
- get_license_info (Get License Info) - Returns the authenticated user's complete license allocation overview: total premium licenses, personal usage, allocatable licenses, per-organization allocations, and free licenses. Use this to understand available capacity before allocating licenses. Requires content_only scope. Endpoint: https://agentview.de/mcp
- create_display_category (Create Display Category) - Creates a personal display category. Pass parent_category_id to create a subcategory. Endpoint: https://agentview.de/mcp
- list_org_displays (List Organization Displays) - Returns all displays in an organization with their real-time connection status, online/offline state, and license info. Use this for fleet monitoring. Requires content_only scope and organization membership. Endpoint: https://agentview.de/mcp
- get_display_content (Get Display Content) - Returns METADATA ONLY about a display's current content: active file name, currentContentDescription (a one-sentence summary, e.g. 'Italian bistro menu — Mittagskarte'), idle-content state, content version id, delivery state, last delivery timestamp. Does NOT return a visible preview. If the user asked anything that implies SEEING the screen ('was läuft', 'zeig mir das Display', 'show me my display', 'preview', 'what's on it'), call get_display_preview_url INSTEAD or IN ADDITION — that one returns a signed previewUrl the agentView widget renders inline. Use this tool's currentContentDescription as a one-line caption alongside the preview, not as a replacement. Use read_display_html only when raw HTML source access is truly needed (debugging, copy-paste). Requires content_only scope. Endpoint: https://agentview.de/mcp
- get_organization (Get Organization) - Returns full details of a specific organization including its displays, members with roles, allocated slots and remaining capacity. Use this after list_organizations to inspect a specific organization's state. Requires authentication with at least content_only scope and the user must be a member of the organization. Endpoint: https://agentview.de/mcp
- get_storage_quota (Get Storage Quota) - Returns the storage-pool snapshot (used / limit / remaining bytes) for the personal scope or a specific group. Data slots and uploaded assets share one quota; call this BEFORE set_data_slot or upload_asset on large payloads to verify the write will fit and avoid a 413 quota_exceeded round-trip. Suppresses raw numbers for narrowly-scoped API keys to avoid leaking org-wide storage state. Endpoint: https://agentview.de/mcp
- remove_display_grant (Remove Display Grant) - Removes a user's access grant from a display within an organization. Requires admin scope and admin or owner role. Endpoint: https://agentview.de/mcp
- remove_display_from_org (Remove Display from Organization) - Removes a display from an organization, clearing its group assignment and all display grants. The display becomes unassigned. Requires admin scope and admin or owner role. Endpoint: https://agentview.de/mcp
- set_data_slot (Set Data Slot) - Creates or updates a mutable JSON data slot (max 2 MB). Slug is the stable identifier — same Slug on a second call updates the existing slot in place (ideal for bot heartbeats and self-registering agents). The public read URL embeds a separate server-generated PublicId, so knowing the slug alone does not grant URL access. Response carries slug, publicId and readUrl. type='value' (default) stores JSON verbatim; type='aggregate' stores { sources, onMissing?, onInvalidJson?, includeMeta?, staleAfterMs?, output? }. Each source references another slot by its SLUG: {slot:'name', as?:'alias'} or {prefixMatch:'agent-'} for dynamic auto-include (max 32 sources, one prefixMatch, 3-60 chars [A-Za-z0-9_-]+). Aggregate sources live in the same scope (personal→personal; group→same group). Dashboard UI shows aggregates as 'JSON collections'. Requires content scope. Endpoint: https://agentview.de/mcp
- list_public_api_categories (List Public API Categories) - Lists all public-API categories with the number of APIs in each. Call this BEFORE search_public_apis when you want to offer the user a guided category pick (weather, finance, news, etc.), or when answering 'what kinds of free APIs do you have?'. No authentication required. Endpoint: https://agentview.de/mcp
- get_pricing (Get Pricing) - Returns agentView plan pricing, features and upgrade options. Use this when the user asks about pricing, costs, plan differences or what an additional display costs. No authentication required. Returns an array of plans with name, price, included displays and features, plus the per-display add-on price and a link to the pricing page. Endpoint: https://agentview.de/mcp
- allocate_licenses (Allocate Licenses) - Allocates premium display licenses from the authenticated user's Premium plan to an organization. Premium users have a pool of allocatable licenses (base + purchased extras) that can be distributed across organizations. Requires admin scope and a Premium plan. Endpoint: https://agentview.de/mcp
- upload_asset (Upload Asset) - Upload one or more files (images, fonts, CSS, video, etc.) as assets and receive stable URLs. Use these URLs in your HTML with <img src="..."> or @font-face { src: url("...") }. Assets are cached on displays — only the HTML is re-downloaded on updates. Pass files as base64-encoded data. IMPORTANT: When creating content for an organization display (a display with an orgId), pass that orgId as group_id so assets are stored in the group's shared storage pool. Omit group_id only for personal displays. Requires authentication with at least content_only scope. Endpoint: https://agentview.de/mcp
- configure_display (Configure Display) - Updates hardware permission, UI settings, and connectivity overrides for a display. Use this when the user wants to enable or disable camera, microphone or geolocation access, toggle the mouse cursor or badge overlay visibility, change the watermark position, or set network connectivity constraints. All parameters except display_id are optional — only provided settings are changed. If the display is online, changes are pushed immediately. Requires admin scope. Endpoint: https://agentview.de/mcp
- search_public_apis (Search Public APIs) - Searches a curated catalog of 600+ free, public APIs that require no authentication and work over HTTPS — ideal for embedding live data in display HTML pages via fetch(). Covers 47 categories including weather, news, finance, sports, images, food, entertainment, science, geocoding and more. Use this when generating HTML that needs live data from the internet. Returns matching APIs with documentation links, CORS support info and ready-to-use fetch() code hints. No authentication required. Endpoint: https://agentview.de/mcp
- claim_display (Claim Display) - Converts an unclaimed guest or pending display into a managed personal display owned by the authenticated user. This permanently transfers ownership and counts against the user's display quota. Use this only when the user explicitly wants to adopt an existing hardware or demo display that is already running. For first-time physical setup, prefer pair_by_code instead. Requires admin scope. Returns profileId (the new managed display ID) and name. Endpoint: https://agentview.de/mcp
- lock_display (Lock Display) - Locks a display so that content changes such as send_html, send_url and clear_display are rejected until unlock_display is called. Use this when the user wants to protect a display from accidental content changes. The display continues showing its current content. Requires admin scope. Returns id and locked (boolean true). To reverse this, use unlock_display. Endpoint: https://agentview.de/mcp
- send_url (Send URL) - Loads a web page by URL on a display using a full-page iframe, immediately replacing whatever is currently shown. Use this when the user wants to show an external website, dashboard or web app on a display. Include content_description whenever available so get_display_content can communicate intent without immediately calling read_display_html. The URL must be an absolute HTTP or HTTPS address. Call get_display_capabilities first to confirm connectivity and browser/runtime support before relying on a remote page. Requires authentication with at least content_only scope. Returns id, name, duration, file (stored filename) and version (content version ID). Endpoint: https://agentview.de/mcp
- clear_display (Clear Display) - Removes the current live content from a display and returns it to its idle/default state. Viewers will immediately see the change. Use this when the user wants to blank or reset a display. This does not delete the display itself — use delete_display for that. Requires authentication with at least content_only scope. Returns id and status ('cleared'). Endpoint: https://agentview.de/mcp
- get_account (Get Account) - Returns the authenticated user's account profile including userId, name, email, plan with feature details, personal display limits, total accessible displays across all organizations, organization memberships summary and points balance. Use this to answer questions about the user's subscription, display quota, organization memberships or plan capabilities. Requires authentication with at least content_only scope. Do not use this to list displays — use list_displays instead. Endpoint: https://agentview.de/mcp
- delete_asset (Delete Asset) - Deletes one or more assets. Displays referencing deleted assets will show broken images. Requires authentication with at least content_only scope. Endpoint: https://agentview.de/mcp
- rename_display_category (Rename Display Category) - Renames one personal display category by ID. Assignments and grants keep working because they reference the stable category ID. Endpoint: https://agentview.de/mcp
- get_auth_session (Get Auth Session) - Polls the status of a login session created by create_auth_session and returns the agent token once the user completes the browser login. Use this after create_auth_session; poll every 2-3 seconds until the status is no longer 'pending'. Do not use this for any other purpose. Returns one of three states: 'pending' (user has not logged in yet — keep polling), 'active' (login succeeded — response includes token as a raw JWT string and tokenExpiresAt as ISO 8601 timestamp), or 'expired' (login window or token timed out — call create_auth_session again). When status is active the current MCP session is automatically authenticated; you can call protected tools immediately. Endpoint: https://agentview.de/mcp
- send_html (Send HTML) - Sends HTML content to a display, replacing whatever is currently shown. Use this for any 'show X on the screen' request unless the user explicitly wants an external website rendered as-is (then use send_url). For rich content with images, fonts or video, first call upload_asset and reference the returned URLs from your HTML; assets are cached on the display, only the HTML re-downloads on update. Include content_description so later get_display_content calls can describe intent without reading raw HTML. Call get_display_capabilities first when you are unsure about the target's runtime limits. For visual quality (typography, full-screen layout, required meta tags, fallback data) follow the brief in the agentview://public/design-system resource before generating HTML. Exactly one of html or base64_html must be provided. Requires content_only scope. Returns id, name, duration, file and version. Endpoint: https://agentview.de/mcp
- delete_display (Delete Display) - Permanently deletes a display and all its associated content. This action cannot be undone. Use this only when the user explicitly confirms they want to remove the display. Requires admin scope. Returns id, name and deleted (boolean true). Endpoint: https://agentview.de/mcp
- logout (Logout) - Clears the cached authentication identity from the current MCP session. Use this when the user wants to end the session or switch accounts. This does not revoke the underlying JWT token — it only removes the session-local cache. After logout, protected tools will require re-authentication. Returns loggedOut (boolean) and sessionBound (boolean). Endpoint: https://agentview.de/mcp
- search_store_templates (Search Store Templates) - Searches the agentView public template store for ready-made display designs (e.g. 'Zahnarzt-Wartezimmer', 'Bistro warm', 'Empfang'). Each template is a polished HTML design a user can push to one of their Türschild / digital-signage displays via send_store_template_to_display. Use this when the user describes a use case and wants to pick a pre-built design instead of having you generate raw HTML. No authentication required. Returns total, offset, limit, language and a templates array; each entry has slug, title, description, category, optional suite (design family), tags, theme, designStyle, placement, previewImageUrl (screenshot PNG), detailPath, previewPath, featured and publishedAt. Use get_store_template_details(slug) for the full rich description before recommending a template. Endpoint: https://agentview.de/mcp
- get_data_slot_usage (Get Data Slot Usage) - Lists displays whose IdleHtmlContent embeds a {{slot:<slug>}} placeholder for this data slot (with optional .readUrl / .slug / .label / .key suffix). Use this BEFORE delete_data_slot to know which displays will start returning 404, or before set_data_slot on a structural change to know which displays will pick up the new shape. Scope is restricted to displays the caller can already see in the same scope as the slot. Capped at 50 results; 'truncated' is true if more matches exist. Requires authentication. Endpoint: https://agentview.de/mcp
- broadcast_to_categories (Broadcast to Categories) - Sends HTML content to every display assigned to one of the selected category IDs. Set include_descendants=true to include subcategories. Set dry_run=true to preview matched profile IDs without sending. Endpoint: https://agentview.de/mcp
- pair_by_code (Pair Display by Code) - PREFERRED way to set up a physical display — the DEFAULT for any ambiguous request to add/create/set up a display. Unless the user explicitly asks for a virtual/headless display, ALWAYS use this over create_display or create_org_display. agentView is purely browser-based, no native app. Workflow: (1) ask the user to open https://display.agentview.de in any browser on the target TV/screen/tablet, (2) ask them to read the 6-character code shown, (3) call this tool with the code. Two modes: (A) New display — code + profile_name creates and pairs in one step (the recommended default for first-time setup). (B) Rebind — code + target_display_id moves an existing display profile to new hardware (call list_displays first to get the ID). Requires admin scope. Endpoint: https://agentview.de/mcp
- search (Search) - Searches agentView resources by keyword and returns a ranked list of matching resource URIs with titles and snippets. Use this to discover resources before calling fetch for full details. Do not use this if you already know the exact resource URI — call fetch directly instead. Without authentication only public documentation resources are searched; with authentication your account and accessible displays are included. Returns query, resourceType, count and a results array where each entry has uri, type, title, snippet and requiresAuthentication. Endpoint: https://agentview.de/mcp
- get_store_template_details (Get Store Template Details) - Returns the full public details of a single store template: localized title, short description, long-form markdown (intro, use cases, audience, setup), category, optional suite, tags, theme, designStyle, placement, features list, preview image URL, store detail path, AND agentArtifacts (metadata-only list of bot-onboarding files this template ships: system prompts, Agent Skills standard SKILL.md, MCP-config snippets). Use this after search_store_templates picks a candidate. When agentArtifacts.length > 0 the template expects AI-agent integration — call get_store_template_agent_artifact for the raw artifact body, or get_display_agent_artifact after install for the placeholder-substituted body. No authentication required. Endpoint: https://agentview.de/mcp
- rename_organization (Rename Organization) - Renames an existing organization. Requires admin scope and admin or owner role in the organization. Endpoint: https://agentview.de/mcp
- bulk_assign_display_category (Bulk Assign Display Category) - Bulk adds or removes one category across multiple displays the caller can manage. Endpoint: https://agentview.de/mcp
- list_displays (List Displays) - Returns all displays accessible to the authenticated user as an array with count and per-display details. Use this to discover display IDs before reading or modifying a specific display with get_display or send_html. Each entry includes id (8-character alphanumeric profile ID), name, status, locked, setupUrl, pairingUrl, managedUrl, approvalUrl plus a compact runtime summary (screen resolution, touch support, deviceClass, deviceFamily) when known. Don't use this to get full details of one display — use get_display with the display_id instead. To share what a display is currently showing, use get_display_preview_url for a short-lived signed link. Requires content_only scope (admin not required). Endpoint: https://agentview.de/mcp
- list_assets (List Assets) - Lists uploaded assets with optional filtering. When working with an organization display, pass its orgId as group_id to search the group's shared asset pool. Without group_id, only personal assets are returned. Check this before uploading to avoid duplicates. Requires authentication with at least content_only scope. Endpoint: https://agentview.de/mcp
- list_api_keys (List API Keys) - Lists all API keys for the current user. Returns key metadata (prefix, name, scope, dates) but never the raw key. Requires admin scope. Endpoint: https://agentview.de/mcp
- read_display_html (Read Display HTML) - Reads the raw HTML source code that is currently shown on a display. Use this when you want to inspect, modify or reuse the existing content. Typical workflow: call read_display_html to get the current HTML, make changes, then send the modified HTML back via send_html. Returns the HTML as a string plus metadata (character count, content type, when it was sent). If no live content is active, returns the idle/default HTML if one is set. Requires authentication with at least content_only scope. Endpoint: https://agentview.de/mcp
- set_display_categories_for_display (Set Display Categories For Display) - Replaces the caller's personal category assignments on one display with the provided category ID list. Empty array clears assignments. Endpoint: https://agentview.de/mcp
- get_display_capabilities (Get Display Capabilities) - Returns resolved display capabilities for a display, including effective network mode plus concrete browser/runtime facts such as screen, viewport, touch/input hints, browser and engine version, platform classification, feature support, known limitations, graphics hints, and a recommended delivery mode. Call this BEFORE generating or sending HTML so your agent can match the content to the real display browser. Requires authentication with at least content_only scope. Endpoint: https://agentview.de/mcp
- list_organizations (List Organizations) - Returns all organizations the authenticated user belongs to with their role, display count, member count and allocated slots. Use this to answer questions about the user's organizations, how many displays an organization has, or team membership. Requires authentication with at least content_only scope. Endpoint: https://agentview.de/mcp
- get_billing_url (Get Billing URL) - Returns a URL to the user's billing and subscription page where they can purchase or manage premium display licenses. Use this when the user wants to buy more licenses, upgrade their plan, or manage their subscription. Present the URL to the user and offer to allocate and assign the new licenses once the purchase is complete. Requires content_only scope. Endpoint: https://agentview.de/mcp
- revoke_api_key (Revoke API Key) - Permanently revokes an API key. This is irreversible — the key will immediately stop working. Requires admin scope. Endpoint: https://agentview.de/mcp
- get_display_preview_url (Generate Display Preview Share Link) - Generates a short-lived signed share link for the display's CURRENT content. The ONLY supported way to share what's on a screen (legacy permanent public viewer was removed for GDPR compliance). Use this for any 'show me my display', 'send what's on the screen to a colleague', 'embed in chat or document', or anything that implies seeing live display content. The returned previewUrl is read-only, expires after ttl_seconds, and dies the moment new content is pushed. TTL ceiling depends on privacy_mode: 'Private' (default) caps at 3600s; 'Public' (owner opt-in) caps at 86400s. Requested TTLs above the ceiling are silently clamped — ttlSeconds in the response is the actual lifetime. Recipients see the content in clearly-marked preview chrome — they cannot push, configure, or discover other displays. Requires display_view access. Returns previewUrl, expiresAt, ttlSeconds, displayName, contentVersionId and privacyMode. Endpoint: https://agentview.de/mcp
- delete_organization (Delete Organization) - Permanently deletes an organization, releasing all its displays and removing all members. Only the owner can delete. This cannot be undone. Requires admin scope. Endpoint: https://agentview.de/mcp
- list_display_categories (List Display Categories) - Lists the authenticated user's personal display categories and assignment counts. Requires authentication with at least content_only scope. Endpoint: https://agentview.de/mcp
- remove_member (Remove Member) - Removes a member from an organization. Transfers their owned displays to a successor, unassigns their license allocations, and removes their display grants. Cannot remove the last owner. Requires admin scope and admin or owner role. Endpoint: https://agentview.de/mcp
- update_asset (Update Asset) - Updates the name and/or description of an existing asset. The URL does not change. At least one of name or description must be provided. Requires authentication with at least content_only scope. Endpoint: https://agentview.de/mcp
- create_organization (Create Organization) - Creates a new organization and makes the authenticated user the owner. Use this when the user wants to set up a shared display fleet. Returns orgId, name, slug, type and yourRole. Requires admin scope. Endpoint: https://agentview.de/mcp
- rename_display (Rename Display) - Changes the friendly name of an existing display. Use this when the user wants to update only the display name without affecting its content or state. Requires admin scope. Returns id and the updated name. Endpoint: https://agentview.de/mcp
- unassign_license (Unassign License) - Removes a premium license from a display, restoring the watermark and ad eligibility. The license returns to the user's available pool (personal) or the group's allocated slot pool (organization). Requires admin scope. Returns id, name, isPremiumAssigned, badgeMode and freeLicenses. Endpoint: https://agentview.de/mcp
- get_asset (Get Asset) - Returns metadata for a single asset including its URL. Use this to verify an asset still exists before referencing it in HTML. Requires authentication with at least content_only scope. Endpoint: https://agentview.de/mcp
- fetch (Fetch) - Retrieves the full details of a single agentView resource identified by its URI. Use this after search to read the complete content of a discovered resource, or directly when you already know the URI. Public URIs (e.g. agentview://public/status, agentview://public/instructions) require no authentication; private URIs (e.g. agentview://account/me, agentview://display/{id}) require a valid session. Returns uri, type, title, text (human-readable content) and data (structured details). Endpoint: https://agentview.de/mcp
- test_display_content (Test Display Content) - DRY-RUN validator for HTML payloads. Pushes the HTML through agentView's size + description checks WITHOUT touching any real display. Use this when an LLM has just generated HTML and you want to confirm it is well-formed and within limits BEFORE risking a real send_html call. No display_id is needed; the response carries simulated=true. Capped at 1 MB. Endpoint: https://agentview.de/mcp
- assign_license (Assign License) - Assigns a premium license to a display, removing its watermark and making it ad-free. For personal displays the license is taken from the user's free pool. For organization displays the license is taken from the group's allocated slot pool (use allocate_licenses first to give the organization licenses). Each license also adds +30 MB to the display's context storage pool. Requires admin scope. Returns id, name, isPremiumAssigned, badgeMode and freeLicenses. Endpoint: https://agentview.de/mcp
- unlock_display (Unlock Display) - Unlocks a previously locked display so that content changes (send_html, send_url, clear_display) are accepted again. Use this when the user wants to resume managing a locked display. Requires admin scope. Returns id and locked (boolean false). To lock again, use lock_display. Endpoint: https://agentview.de/mcp
- get_store_template_install_options (Get Store Template Install Options) - Returns the displays the authenticated user can send a given store template to, plus the data slots the template needs. Call this before send_store_template_to_display so you can (1) show the user which Türschild they can target and (2) gather any per-slot JSON the template consumes (greeting, menu JSON, sensor URL, ...). Requires authentication with at least content_only scope. Returns templateSlug, language, displays (array of {displayId, name, scope='personal'|'group', groupId?, isLocked}) and requiredDataSlots (array of {key, label, type, placeholderName, required}). When no displays come back, tell the user they first need to create/claim a display (create_display / pair_by_code) before installing store content. API-key callers with a display whitelist only see their scoped displays. Endpoint: https://agentview.de/mcp
- set_org_connectivity (Set Org Connectivity) - Sets the default connectivity mode and global whitelist for an organization. These settings apply to all displays in the org unless overridden at the display level. Use this when an org admin wants to declare their network topology (e.g., 'our displays can only reach *.corp.local'). Requires admin scope and Org-Admin role. Endpoint: https://agentview.de/mcp
- set_display_embeddable_origins (Set Display Embeddable Origins) - Sets the optional origin allowlist that restricts which third-party websites may embed this display via /display-embed/{profileId}. Only effective when the display's privacy_mode is 'Public' — Private displays reject the embed route entirely regardless of this setting. Pass an empty array to clear the allowlist (Public displays then embed from anywhere — equivalent to YouTube's default video embedding). Pass an array like ['https://bistro-mueller.de'] to lock embedding to those specific origins (plus agentView's own domains and the ChatGPT widget host, which are always allowed). Returns id, name, embeddableOrigins (the new array), and a changed flag. Audit-logged. Endpoint: https://agentview.de/mcp

## Resources
- ui://agentview/store-gallery - agentView Template Gallery Visual card grid of agentView store templates returned by search_store_templates and list_store_categories. MIME type: text/html;profile=mcp-app
- ui://agentview/store-detail - agentView Template Detail Hero + intro + features + use cases for a single store template returned by get_store_template_details. MIME type: text/html;profile=mcp-app
- ui://agentview/store-install-result - agentView Template Installed Success/error confirmation card rendered after send_store_template_to_display. MIME type: text/html;profile=mcp-app
- ui://agentview/display-preview - agentView Display Preview Live preview of a single display via a signed time-limited URL. MIME type: text/html;profile=mcp-app
- ui://agentview/display-grid - agentView Displays Grid of the user's displays with online status and privacy mode. MIME type: text/html;profile=mcp-app
- ui://agentview/pricing - agentView Pricing Plan comparison and per-display add-on pricing. MIME type: text/html;profile=mcp-app
- ui://agentview/auth-session - agentView Sign In Login button + countdown rendered after create_auth_session so the user has a clean call-to-action instead of a long technical URL in chat. MIME type: text/html;profile=mcp-app
- agentview://public/status - Public status Server health, MCP discovery endpoints and public readiness information. MIME type: application/json
- agentview://public/instructions - Agent instructions Recommended authentication and usage flow for MCP clients. MIME type: text/plain
- agentview://public/design-system - Premium display design system Default premium digital-signage brief for generating high-end display HTML. MIME type: text/plain
- agentview://public/developers - Developer documentation Technical MCP and OAuth integration reference. MIME type: text/plain
- agentview://public/mcp - MCP capability status Supported protocol versions, transports, resources, prompts, completions and subscription capabilities. MIME type: application/json
- agentview://public/oauth - OAuth status Authorization endpoints, supported scopes, token methods, PKCE and protected resource metadata. MIME type: application/json
- agentview://public/support - Support diagnostics Recommended evidence and checks for MCP, OAuth, session and interoperability troubleshooting. MIME type: text/plain
- agentview://public/apis - Public API catalog Catalog of 638 free, no-auth public APIs for embedding live data in display HTML via fetch(). MIME type: application/json

## Prompts
- onboard_first_display - First Display Onboarding Guide the assistant through helping a user create and understand their first display. Arguments: goal
- recover_mcp_auth - Recover MCP Auth Guide the assistant through diagnosing MCP OAuth, discovery and session failures. Arguments: client_name, symptom
- asset_workflow - Asset Upload Workflow Guide the assistant through uploading assets (images, fonts, media) and referencing them in display HTML for optimal performance and caching.
- render_premium_display_html - Render Premium Display HTML Load the premium agentView creative brief for generating polished, high-end digital signage HTML from a one-shot request. Arguments: brief, category, touch_mode, data_mode, brand_direction

## Metadata
- Owner: de.agentview
- Version: 1.0.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Apr 7, 2026
- Source: https://registry.modelcontextprotocol.io