bake_expression
Sample a property over time and write keyframes, optionally disabling its expression afterward.
This record as markdown: /tools/synthetic-ai-ae-mcp/bake-expression.md
What bake_expression does on Ae
AI agents use bake_expression to create or update resources in Ae, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ae environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
save | boolean | — | Save after updating. Defaults to false. |
endTime | number | — | End time. Defaults to work area end. |
compName | string | Yes | Composition name. |
frameStep | number | — | Frame increment between samples. Defaults to 1. |
layerName | string | Yes | Layer name. |
startTime | number | — | Start time. Defaults to comp work area start. |
timeoutMs | number | — | Process timeout in milliseconds. Defaults to 120000. |
projectPath | string | — | Optional absolute path to an .aep file to open first. |
propertyPath | array | Yes | Property path, preferably match names. |
disableExpression | boolean | — | Disable expression after baking. Defaults to true. |
Parameters from the server's own tool schema.
Why bake_expression is rated Medium
An AI agent can call bake_expression faster than any human can review: one bad instruction and it creates or modifies resources in Ae by the hundred, each call as confident as the last.
Risk signalsHigh parameter count (10 properties)
Attacks that exploit this kind of access
The rule that runs bake_expression safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ae, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For bake_expression, this is the rule to start with:
bake_expression 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 Ae, apply this rule, and every bake_expression call is checked against it from then on.
Questions about bake_expression
Sample a property over time and write keyframes, optionally disabling its expression afterward. It is categorised as a Write tool in the Ae MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
bake_expression accepts 10 parameters: save, endTime, compName, frameStep, layerName, startTime, timeoutMs, projectPath, propertyPath, disableExpression. Required: compName, layerName, propertyPath. The full parameter table on this page comes from the server's own tool schema.
Register the Ae MCP server in PolicyLayer and add a rule for bake_expression: 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 Ae. Nothing to install.
bake_expression 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 bake_expression 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 bake_expression. 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.
bake_expression is provided by the Ae MCP server (@synthetic-ai/ae-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ae, and thousands of servers like it.
This server
Across the catalogue