Return all Projects and Designs the authenticated user can render. Designs are pre-made projects with variants available for all users. Projects are created and maintained by the user, and may have custom templates. Each item includes a lightweight preview of its templates/variants (name, aspect ...
AI agents call list_renderable_items to retrieve information from Plainly Videos MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure data retrieval operation. It queries and lists available resources (Projects and Designs) that the user can access, returning metadata and descriptive information. There are no side effects, no code execution, no data modification, and no destructive operations. The tool enables discovery of available video templates but does not trigger any video rendering or other consequential actions.
From the tool's definition Tool name is 'list_renderable_items' and description states it 'Return all Projects and Designs' — it retrieves and enumerates data without modifying or executing any operations.
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access list_renderable_items gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Plainly Videos MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for list_renderable_items:
{
"version": "1",
"default": "deny",
"tools": {
"list_renderable_items": {}
}
}list_renderable_items is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Return all Projects and Designs the authenticated user can render. Designs are pre-made projects with variants available for all users. Projects are created and maintained by the user, and may have custom templates. Each item includes a lightweight preview of its templates/variants (name, aspect ratio, duration) plus a parent-level description and metadata (tags, category, attributes). Filtering guidance (semantic first): - First, determine relevance using: metadata.tags, metadata.category, metadata.attributes, description, and name. - Only after a semantic match, consider technical fit (aspectRatio, durationSeconds) to break ties. - Do not guess or list unrelated items. If nothing is relevant, respond:. It is categorised as a Read tool in the Plainly Videos MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Plainly Videos MCP Server MCP server in PolicyLayer and add a rule for list_renderable_items: 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 Plainly Videos MCP Server. Nothing to install.
list_renderable_items 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 list_renderable_items 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 list_renderable_items. 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.
list_renderable_items is provided by the Plainly Videos MCP Server MCP server (plainly-videos/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Plainly Videos MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Plainly Videos MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.