Run a model synchronously and automatically download any image URLs in the response. The model is run synchronously using the fal.run endpoint. Returns the model output with embedded base64 image data for any image URLs found.
AI agents invoke fal-run-sync to trigger actions in Mcp Gmail. 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.
This tool executes code/models on external infrastructure (the fal.run endpoint) and performs automated downloads based on the results. It has side effects that cannot be predicted without knowing the model and inputs. This is Execute rather than Read because it actively runs computations and downloads resources; it's not merely querying.
From the tool's definition Tool description states it 'Run[s] a model synchronously' and 'automatically download[s]' content, triggering external operations (model inference, file downloads) whose effects depend on which model is invoked and what inputs are provided.
Attacks that exploit this kind of access
Run a model synchronously and automatically download any image URLs in the response. The model is run synchronously using the fal.run endpoint. Returns the model output with embedded base64 image data for any image URLs found. It is categorised as a Execute tool in the Mcp Gmail MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Gmail MCP server in PolicyLayer and add a rule for fal-run-sync: 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 Mcp Gmail. Nothing to install.
fal-run-sync 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-run-sync 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-run-sync. 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-run-sync is provided by the Mcp Gmail MCP server (@monsoft/mcp-gmail). 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 →