preview_still
Render a single frame of the current project to a PNG and return it as an image you can look at. This is how you check your work — in chat there is no other way to see what a composition actually looks like. Use it liberally: after composing, after edits, and at different times to inspect motion....
This record as markdown: /tools/dev-clipkit-clipkit/preview-still.md
What preview_still does on Clipkit
AI agents call preview_still to retrieve information from Clipkit 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 |
|---|---|---|---|
time | number | — | Composition time in seconds to capture. Default 0 (first frame). |
project_id | string | — | Which project to act on — the id returned by create_project / set_project / create_promo / load_project. Omit when working on a single local project. |
Parameters from the server's own tool schema.
Why preview_still is rated Low
This tool reads/renders a preview frame from the current project and returns it as an image. It has no side effects, does not modify data, costs no credits, and is explicitly described as a way to inspect (not change) the composition. This is a read/query operation.
From the tool's definition Render a single frame of the current project to a PNG and return it as an image you can look at. Stills are FREE (credits are only spent by render_video).
Attacks that exploit this kind of access
The rule that runs preview_still safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Clipkit, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For preview_still, this is the rule to start with:
preview_still 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 Clipkit, apply this rule, and every preview_still call is checked against it from then on.
Questions about preview_still
Render a single frame of the current project to a PNG and return it as an image you can look at. This is how you check your work — in chat there is no other way to see what a composition actually looks like. Use it liberally: after composing, after edits, and at different times to inspect motion. Stills are FREE (credits are only spent by render_video). Pass time (seconds) to choose the frame; defaults to 0. It is categorised as a Read tool in the Clipkit MCP Server, which means it retrieves data without modifying state.
preview_still accepts 2 parameters: time, project_id. The full parameter table on this page comes from the server's own tool schema.
Register the Clipkit MCP server in PolicyLayer and add a rule for preview_still: 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 Clipkit. Nothing to install.
preview_still 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 preview_still 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 preview_still. 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.
preview_still is provided by the Clipkit MCP server (https://www.clipkit.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Clipkit, and thousands of servers like it.
This server
Across the catalogue