test_display_content
Dry-run validator for generated HTML: runs agentView's size and description checks WITHOUT touching a real display. Use after composing complex HTML and before send_html or broadcast_content. No display_id needed; the response carries simulated=true. Capped at 1 MB. Requires authentication.
This record as markdown: /tools/de-agentview-agentview-mcp/test-display-content.md
What test_display_content does on agentView
AI agents call test_display_content to retrieve information from agentView without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
html | string | — | Complete HTML document to validate. Mutually exclusive with base64_html — provide exactly one. |
base64_html | string | — | Base64-encoded HTML payload. Mutually exclusive with html. |
description | string | Yes | Short human-readable description of what the HTML represents (1-1000 chars). Same validation rules as send_html. |
access_token | string | — | Optional bearer token; prefer session_request_id. |
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 test_display_content is rated Low
Even though test_display_content only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsHandles credentials or secrets (access_token) · Accepts raw HTML/template content (html)
Attacks that exploit this kind of access
The rule that runs test_display_content 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 test_display_content, this is the rule to start with:
test_display_content is read-only, so it stays allowed. 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 test_display_content call is checked against it from then on.
Questions about test_display_content
Dry-run validator for generated HTML: runs agentView's size and description checks WITHOUT touching a real display. Use after composing complex HTML and before send_html or broadcast_content. No display_id needed; the response carries simulated=true. Capped at 1 MB. Requires authentication. It is categorised as a Read tool in the agentView MCP Server, which means it retrieves data without modifying state.
test_display_content accepts 5 parameters: html, base64_html, description, access_token, session_request_id. Required: 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 test_display_content: 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.
test_display_content is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the test_display_content 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 test_display_content. 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.
test_display_content 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