AI agents use submagic_update_project to create or update resources in Submagic — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Submagic environment.
The tool modifies existing project state (update pattern) within the Submagic video editing service. This is a reversible write operation—users can typically modify project settings, metadata, or content again. Without the description, confidence is moderate, but the naming convention and API context support Write category over Execute.
From the tool's definition Tool name "submagic_update_project" indicates modification of project data. Description is empty, but sibling tools include create, export, get, and list operations typical of a video editing API.
Attacks that exploit this kind of access
submagic_update_project. It is categorised as a Write tool in the Submagic MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Submagic MCP server in PolicyLayer and add a rule for submagic_update_project: 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 Submagic. Nothing to install.
submagic_update_project 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 submagic_update_project 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 submagic_update_project. 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.
submagic_update_project is provided by the Submagic MCP server (sidart10/submagic-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →