AI agents invoke execute_function to trigger actions in Foundry MCP Server. 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 runs functions with user-supplied parameters, making it Execute rather than Write. While not inherently Destructive, it has high severity due to the unpredictable effects of executing arbitrary functions in a Foundry environment (which typically handles enterprise data). The sibling tools are all Read operations (query, list), making this the most dangerous on the server.
From the tool's definition Tool name 'execute_function' and description 'Execute a function using given parameters' indicate arbitrary code execution.
Documented attack patterns abuse exactly the kind of access execute_function gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Foundry MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_function:
{
"version": "1",
"default": "deny",
"tools": {
"execute_function": {
"limits": [
{
"counter": "execute_function_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_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.
Free to start. No card required.
Execute a function using given parameters. It is categorised as a Execute tool in the Foundry MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Foundry MCP Server MCP server in PolicyLayer and add a rule for execute_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 Foundry MCP Server. Nothing to install.
execute_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 execute_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 execute_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.
execute_function is provided by the Foundry MCP Server MCP server (qwert666/mcp-server-foundry). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Foundry MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 Foundry MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.