find_project_items
Find project items by name, type, parent folder, or missing-footage state.
This record as markdown: /tools/synthetic-ai-ae-mcp/find-project-items.md
What find_project_items does on Ae
AI agents call find_project_items to retrieve information from Ae 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 |
|---|---|---|---|
type | string | — | comp, folder, footage, solid, or placeholder. |
timeoutMs | number | — | Process timeout in milliseconds. Defaults to 120000. |
parentName | string | — | Optional parent folder name. |
projectPath | string | — | Optional absolute path to an .aep file to open first. |
nameContains | string | — | Case-insensitive name substring. |
missingFootage | boolean | — | Filter footage by missing state. |
Parameters from the server's own tool schema.
Why find_project_items is rated Low
Even though find_project_items 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.
Attacks that exploit this kind of access
The rule that runs find_project_items 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 find_project_items, this is the rule to start with:
find_project_items 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 Ae, apply this rule, and every find_project_items call is checked against it from then on.
Questions about find_project_items
Find project items by name, type, parent folder, or missing-footage state. It is categorised as a Read tool in the Ae MCP Server, which means it retrieves data without modifying state.
find_project_items accepts 6 parameters: type, timeoutMs, parentName, projectPath, nameContains, missingFootage. 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 find_project_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 Ae. Nothing to install.
find_project_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 find_project_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 find_project_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.
find_project_items 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