run_function
Run a deployed HTTP function. function_name excludes method prefix. Example:
This record as markdown: /tools/webcake-storefront/run-function.md
What run_function does on Webcake Storefront
AI agents invoke run_function to trigger actions in Webcake Storefront. 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.
Why run_function is rated High
The tool executes arbitrary deployed functions without specified constraints on what those functions can do. While the description is minimal, the core functionality is to invoke code execution. Given the storefront context (orders, products, domains), a compromised function could modify business-critical data, trigger external APIs, or affect customer transactions.
From the tool's definition Tool name is 'run_function' and description states it 'Run[s] a deployed HTTP function.' This directly executes code on a remote system.
Attacks that exploit this kind of access
The rule that runs run_function safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Webcake Storefront, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For run_function, this is the rule to start with:
run_function stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Webcake Storefront, apply this rule, and every run_function call is checked against it from then on.
Questions about run_function
Run a deployed HTTP function. function_name excludes method prefix. Example:. It is categorised as a Execute tool in the Webcake Storefront MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Webcake Storefront MCP server in PolicyLayer and add a rule for run_function: 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 Webcake Storefront. Nothing to install.
run_function 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 run_function 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 run_function. 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.
run_function is provided by the Webcake Storefront MCP server (webcake-storefront-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Webcake Storefront, and thousands of servers like it.
Across the catalogue