// SCAN REPORT

agentView

57 tools. 27 can modify or destroy data without limits.

7 destructive tools with no built-in limits. Policy required.

Last updated: 17 Aug 2026

27 can modify or destroy data

30 read-only

57 tools total

Community server · catalogue entry checked 17/08/2026 · full schemas captured for 55 of 57 tools

How to control agentView ↓

TOOL MAP

What agentView exposes to your agents

Read (30) Write / Execute (20) Destructive / Financial (7)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What agentView costs in tokens

11,488 tokens of tool definitions, loaded on every request

5.7% of a 200k context window

643 heaviest tool: create_api_key

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous agentView tools

Destructive · High delete_asset The tool performs irreversible deletion of assets, which is the defining characteristic of the Destructive category. Destructive · High delete_display The tool irreversibly deletes data (display and associated content) with no undo capability. Destructive · Critical delete_organization This tool irreversibly deletes an entire organization and all associated resources (displays, members). Destructive · High remove_display_from_org This tool irreversibly modifies the organizational structure and access control of a display.

27 of agentView's 57 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control agentView

PolicyLayer is an MCP gateway — it sits between your AI agents and agentView, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_asset": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "assign_display_categories": {
    "limits": [
      {
        "counter": "assign_display_categories_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "broadcast_content": {
    "limits": [
      {
        "counter": "broadcast_content_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register agentView — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON AGENTVIEW →

Instant setup, no code required.

FULL CATALOGUE

All 57 agentView tools

DESTRUCTIVE 7 tools

Destructive delete_asset Deletes one or more assets. Displays referencing deleted assets will show broken images. Requires authenticati Destructive delete_data_slot Permanently deletes a data slot. Display HTML fetching its readUrl will receive 404 after deletion. Cannot be Destructive delete_display Permanently deletes a display and all its associated content. This action cannot be undone. Use this only when Destructive delete_organization Permanently deletes an organization, releasing all its displays and removing all members. Only the owner can d Destructive logout Clears the cached login from this MCP session (does not revoke the underlying token). Use when the user wants Destructive remove_display_from_org Removes a display from an organization, clearing its group assignment and all display grants. The display beco Destructive revoke_api_key Permanently revokes an API key. This is irreversible — the key will immediately stop working. Requires admin s

WRITE 20 tools

Write assign_display_categories Assigns displays to categories. mode 'replace' (default) sets the full category list of each display in displa Write authenticate Validates a JWT agent token and caches the identity on this MCP session so later calls work without resending Write clear_display Removes the current live content from a display and returns it to its idle/default state. Viewers will immedia Write configure_display Updates display settings: rename (name), lock or unlock content changes (locked), privacy mode for share links Write configure_organization Updates organization settings: rename (name) and/or network connectivity defaults for all its displays (defaul Write create_api_key Creates a long-lived API key for server-to-server integration without OAuth. The raw key is returned only once Write create_auth_session Starts a browser login and returns a loginUrl plus sessionRequestId. Use as STEP 0 in a fresh conversation bef Write create_display Pre-provisions a display without hardware, personal or inside an organization (org_id). The new display starts Write create_organization Creates a new organization and makes the authenticated user the owner. Use this when the user wants to set up Write manage_display_category Creates or renames a display category (categories group displays for broadcast_content include_category_ids). Write manage_licenses Manages premium display licenses: action 'allocate' sets how many license slots an organization gets (licenses Write manage_org_member Manages organization membership: action 'invite' adds a member by email with a role, 'set_role' changes a memb Write send_html Shows HTML content on a display: menus, dashboards, welcome pages, schedules or any custom design. slot 'live' Write send_store_template_to_display Installs a published store template onto a display: materializes the HTML, auto-creates required data slots (r Write send_url Shows an external web page on a display via full-page iframe: dashboards, websites or web apps. slot 'live' (d Write set_data_slot Creates or updates a mutable JSON data slot (max 2 MB) that display HTML fetches via its readUrl — the live-da Write set_display_grant Grants or revokes a member's access to one display inside an organization. action 'set' (default) creates/upda Write submit_feedback Sends the user's feedback, feature request or bug report about agentView itself (not display content) for late Write update_asset Updates the name and/or description of an existing asset. The URL does not change. At least one of name or des Write upload_asset Upload one or more files (images, fonts, CSS, video, etc.) as assets and receive stable URLs. Use these URLs i

READ 30 tools

Read broadcast_content Sends HTML to many displays at once. Target explicit display_ids, all=true for every accessible display, or in Read claim_display Adopts an unclaimed guest or pending display as a managed personal display (permanent ownership transfer, coun Read fetch Fetches one agentView resource by agentview:// URI, e.g. agentview://public/status, agentview://account/me or Read get_account Returns the user's account profile: plan and features, personal display limits and remaining quota, accessible Read get_agent_artifact Returns an agent-onboarding artifact shipped with a store template: system prompt, Agent Skills SKILL.md or MC Read get_asset Returns metadata for a single asset including its URL. Use this to verify an asset still exists before referen Read get_auth_session Polls a login session created by create_auth_session until the user completes the browser login. Poll every 2- Read 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; Read get_display Returns one display's state: status, lock, URLs, settings, language and current content summary. response_form Read get_display_preview_url Creates a short-lived signed link showing what a display is presenting RIGHT NOW, rendered inline as a preview Read get_license_info Returns the authenticated user's complete license allocation overview: total premium licenses, personal usage, Read get_organization Returns one organization's details: plan, your role, display count, allocated and remaining license slots. res Read get_public_status Returns the server's public readiness status, version string and discovery URLs. Use this before authenticatin Read get_storage_usage Returns the storage pool snapshot (used, limit and remaining bytes) for the personal scope or a group — data s Read get_store_template_content Returns the raw display HTML of a published store template plus its slot definitions and allowed external orig Read get_store_template_details Returns full details of one store template: localized title and description, long-form markdown, category, sui Read get_store_template_install_options Returns the displays the user can install a store template on plus the data slots it needs (key, label, type, Read list_api_keys Lists all API keys for the current user. Returns key metadata (prefix, name, scope, dates) but never the raw k Read list_assets Lists the user's uploaded assets (images, videos, fonts, documents) with public URLs for use in display HTML. Read list_data_slots Lists data slots with optional filtering. Returns metadata only (no jsonContent). Each item includes readUrl. Read list_display_categories Lists the authenticated user's personal display categories with stable IDs, paths and assignment counts. Use t Read list_displays Lists all displays the user can access, with id, name, online status, lock state and device class — the starti Read list_organizations Returns all organizations the authenticated user belongs to with their role, display count, member count and a Read list_store_categories Lists all published agentView store categories (e.g. Gastronomie, Wartezimmer, Empfang, Smart Home) with local Read pair_by_code Pairs a physical screen with the 6-character code shown on https://display.agentview.de — the recommended firs Read read_display_html Reads the raw HTML source currently shown on a display so you can inspect or edit it and push it back with sen Read search Searches agentView resources by keyword: documentation, server status, your account, your displays and the API Read search_public_apis Searches a curated catalog of 600+ free public APIs (no key, HTTPS) for embedding live data in display HTML vi Read search_store_templates Searches the agentView template store for ready-made display designs ('Zahnarzt-Wartezimmer', 'Bistro', 'recep Read test_display_content Dry-run validator for generated HTML: runs agentView's size and description checks WITHOUT touching a real dis

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about agentView

Can an AI agent delete data through the agentView MCP server? +

Yes. The agentView server exposes 7 destructive tools including delete_asset, delete_data_slot, delete_display. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through agentView? +

The agentView server has 20 write tools including assign_display_categories, authenticate, clear_display. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach agentView.

How many tools does the agentView MCP server expose? +

57 tools across 3 categories: Destructive, Read, Write. 30 are read-only. 27 can modify, create, or delete data.

How do I enforce a policy on agentView? +

Register the agentView MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every agentView tool call.

Deterministic rules across all 57 agentView tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AGENTVIEW →

Instant setup, no code required.

57 agentView tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from agentView's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →