Inspect, open, reveal, or transform local media files. Prefer workspace-relative paths with workspaceId, and omit outputPath to write outputs back into that workspace.
AI agents invoke fal_media to trigger actions in Simple Fal. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool can inspect (Read), open/reveal (Execute/OS action), and transform (Execute with Write side effects) local media files. 'Transform' implies running processing operations whose effects depend on arguments, and outputs are written to disk. The most severe applicable category is Execute due to arbitrary transformation operations and OS-level file actions.
From the tool's definition 'transform local media files' and 'write outputs back into that workspace' — the tool both processes/executes transformations on files and writes output, spanning Execute and Write categories
Attacks that exploit this kind of access
Inspect, open, reveal, or transform local media files. Prefer workspace-relative paths with workspaceId, and omit outputPath to write outputs back into that workspace. It is categorised as a Execute tool in the Simple Fal MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Simple Fal MCP server in PolicyLayer and add a rule for fal_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 Simple Fal. Nothing to install.
fal_media is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the fal_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 fal_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.
fal_media is provided by the Simple Fal MCP server (pintar-team/simple-fal-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 →