upload_file_to_gcs
AI agents use upload_file_to_gcs to create or update resources in FFmpeg MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FFmpeg MCP Server environment.
This tool creates or modifies data in Google Cloud Storage by uploading files. It is reversible (files can be deleted or overwritten), so it is categorized as Write rather than Destructive. Severity is high because an AI agent could upload sensitive data, malicious files, or large amounts of data to cloud storage, potentially causing data exposure, storage cost escalation, or denial of service.
From the tool's definition Tool name 'upload_file_to_gcs' indicates writing/uploading data to Google Cloud Storage. Server description mentions 'Google Cloud Storage integration' as a capability.
Attacks that exploit this kind of access
upload_file_to_gcs. It is categorised as a Write tool in the FFmpeg MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the FFmpeg MCP Server MCP server in PolicyLayer and add a rule for upload_file_to_gcs: 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 FFmpeg MCP Server. Nothing to install.
upload_file_to_gcs 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 upload_file_to_gcs 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 upload_file_to_gcs. 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.
upload_file_to_gcs is provided by the FFmpeg MCP Server MCP server (radzevich/ffmpeg_mcp). 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 →