Upload media files to your Cosmic bucket.
AI agents use upload_media to create or update resources in Cosmic MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cosmic MCP Server environment.
Uploading files creates new data in the CMS bucket. This is a reversible write operation (uploaded files can be deleted via delete_media), not a read-only query or destructive action. Medium severity because an agent could upload large/malicious files, consuming storage or introducing unwanted content, but the damage is bounded by available bucket capacity and can be remediated through deletion.
From the tool's definition Tool description states 'Upload media files to your Cosmic bucket.' Upload is a write operation that creates new media resources.
Attacks that exploit this kind of access
Upload media files to your Cosmic bucket. It is categorised as a Write tool in the Cosmic MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cosmic MCP Server MCP server in PolicyLayer and add a rule for upload_media: 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 Cosmic MCP Server. Nothing to install.
upload_media 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_media 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_media. 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_media is provided by the Cosmic MCP Server MCP server (patgpt/cosmic-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 →