AI agents call lean_goal to retrieve information from Lean Lsp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'lean_goal' suggests it queries or retrieves goal state information from the Lean theorem prover, which is a read-only operation with no side effects. The empty description reduces confidence slightly, but the context of other sibling tools (all non-destructive analysis and querying tools) and Lean LSP conventions strongly suggest this is a Read operation.
From the tool's definition Tool name is 'lean_goal' with no description provided. Based on naming conventions in Lean LSP contexts, this tool likely retrieves the current proof goal state, similar to sibling tools like 'file_outline' and 'lean_diagnostic_messages' which are…
Documented attack patterns abuse exactly the kind of access lean_goal 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 lean_goal:
{
"version": "1",
"default": "deny",
"tools": {
"lean_goal": {}
}
}lean_goal is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
lean_goal. It is categorised as a Read tool in the Lean Lsp MCP Server, which means it retrieves data without modifying state.
Register the Lean Lsp MCP server in PolicyLayer and add a rule for lean_goal: 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.
lean_goal is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the lean_goal 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 lean_goal. 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.
lean_goal 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.