send_html
Shows HTML content on a display: menus, dashboards, welcome pages, schedules or any custom design. slot 'live' (default) replaces the current content; slot 'idle' stores the default/fallback content shown when nothing live is active (idle requires admin scope). Always pass a short description so ...
This record as markdown: /tools/de-agentview-agentview-mcp/send-html.md
What send_html does on agentView
AI agents use send_html to create or update resources in agentView, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your agentView environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
html | string | — | Complete HTML document to render. Mutually exclusive with base64_html. |
slot | string | — | Target slot: 'live' (default) replaces current content; 'idle' sets the default shown when idle (admin scope). |
token | string | — | Display-specific demo/preview token for unauthenticated access. NOT the OAuth token. |
duration | integer | — | Seconds the content stays; 0 = indefinite (default). Live slot only. |
display_id | string | Yes | 8-character display profile ID, e.g. 'ABCD1234'. |
base64_html | string | — | Base64-encoded HTML (standard base64). Use only when raw HTML cannot survive JSON transport. Mutually exclusive with html. |
description | string | Yes | Short human-readable summary of the content, e.g. 'Weekly KPI dashboard'. |
access_token | string | — | Optional bearer token; prefer session_request_id. Distinct from the display-specific 'token'. |
session_request_id | string | — | Session handle from create_auth_session; pass it on every authenticated call. |
Parameters from the server's own tool schema.
Why send_html is rated Medium
An AI agent can call send_html faster than any human can review: one bad instruction and it creates or modifies resources in agentView by the hundred, each call as confident as the last.
Risk signalsHandles credentials or secrets (token) · Accepts raw HTML/template content (html) · Admin/system-level operation
Attacks that exploit this kind of access
The rule that runs send_html safely
PolicyLayer is an MCP gateway: it sits between your AI agents and agentView, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For send_html, this is the rule to start with:
send_html stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect agentView, apply this rule, and every send_html call is checked against it from then on.
Questions about send_html
Shows HTML content on a display: menus, dashboards, welcome pages, schedules or any custom design. slot 'live' (default) replaces the current content; slot 'idle' stores the default/fallback content shown when nothing live is active (idle requires admin scope). Always pass a short description so later content reads stay meaningful. Exactly one of html or base64_html. For external web pages use send_url; to edit current content call read_display_html first. For polished results load prompt render_premium_display_html or resource agentview://public/design-system. Requires content scope. It is categorised as a Write tool in the agentView MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
send_html accepts 9 parameters: html, slot, token, duration, display_id, base64_html, description, access_token, session_request_id. Required: display_id, description. The full parameter table on this page comes from the server's own tool schema.
Register the agentView MCP server in PolicyLayer and add a rule for send_html: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches agentView. Nothing to install.
send_html is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the send_html rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for send_html. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
send_html is provided by the agentView MCP server (https://agentview.de/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on agentView, and thousands of servers like it.
This server
Across the catalogue