AI agents invoke gemini_code_golf to trigger actions in Lean Lsp. 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.
Based on the server context (Lean theorem prover interaction) and sibling tools like 'gemini_informal_prover' and 'gpt_informal_prover', this tool likely invokes an external AI (Gemini) to perform code golf (compact code generation) on Lean proofs. This constitutes executing an external operation. However, the empty description significantly lowers confidence.
From the tool's definition Tool name 'gemini_code_golf' suggests interaction with Gemini AI model for code optimization/generation; description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access gemini_code_golf gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Lean Lsp, and nothing reaches the server without passing your rules. This is the rule we recommend for gemini_code_golf:
{
"version": "1",
"default": "deny",
"tools": {
"gemini_code_golf": {
"limits": [
{
"counter": "gemini_code_golf_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}gemini_code_golf 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.
gemini_code_golf. It is categorised as a Execute tool in the Lean Lsp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Lean Lsp MCP server in PolicyLayer and add a rule for gemini_code_golf: 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 Lean Lsp. Nothing to install.
gemini_code_golf 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 gemini_code_golf 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 gemini_code_golf. 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.
gemini_code_golf is provided by the Lean Lsp MCP server (project-numina/lean-lsp-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Lean Lsp, 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.
22 Lean Lsp tools catalogued and risk-classified — across an index of 43,000+ MCP servers.