AI agents use export_stems to create or update resources in Claud-Ear — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claud-Ear environment.
Export operations create new files or data artifacts, making this a Write action. The severity is medium because exported stems are reversible (can be deleted) and non-destructive, but exporting large audio files could consume storage/bandwidth. Confidence is moderate (0.72) because the description is empty; classification relies on name semantics and server context rather than explicit documentation.
From the tool's definition Tool name 'export_stems' indicates exporting/writing audio stem data. Context: sibling tool 'analyze_stems' suggests this server processes audio into separated stems (vocals, drums, instruments, etc.); export_stems would write this derived data to disk or…
Attacks that exploit this kind of access
export_stems. It is categorised as a Write tool in the Claud-Ear MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claud-Ear MCP server in PolicyLayer and add a rule for export_stems: 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 Claud-Ear. Nothing to install.
export_stems 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 export_stems 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 export_stems. 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.
export_stems is provided by the Claud-Ear MCP server (null-phnix/claud-ear). 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 →