AI agents invoke generate_code to trigger actions in Mcp Llm. 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.
Generating code can lead to execution of arbitrary logic depending on how the output is used. While the tool may only return code as text (which would be Write), the combination with sibling tools like 'generate_code_to_file' suggests outputs may be written to disk or executed.
From the tool's definition 'Generate code based on a description' — the tool produces and potentially runs executable code
Documented attack patterns abuse exactly the kind of access generate_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Llm, and nothing reaches the server without passing your rules. This is the rule we recommend for generate_code:
{
"version": "1",
"default": "deny",
"tools": {
"generate_code": {
"limits": [
{
"counter": "generate_code_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}generate_code 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.
Generate code based on a description. It is categorised as a Execute tool in the Mcp Llm MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Llm MCP server in PolicyLayer and add a rule for generate_code: 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 Llm. Nothing to install.
generate_code 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 generate_code 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 generate_code. 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.
generate_code is provided by the Mcp Llm MCP server (sammcj/mcp-llm). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 Mcp Llm tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 Mcp Llm tools catalogued and risk-classified — across an index of 42,500+ MCP servers.