AI agents invoke lean_build to trigger actions in Lean LSP MCP. 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.
The 'lean_build' tool triggers compilation of a Lean project, which executes code and external processes. While the primary effect is creating build artifacts (not destructive), the execution of arbitrary build logic and potential side effects from build scripts/dependencies justifies Execute classification.
From the tool's definition Tool name 'lean_build' and server context showing interaction with Lean theorem prover through LSP. Building/compiling code is an Execute operation that runs external processes. Description is empty, reducing certainty slightly.
Documented attack patterns abuse exactly the kind of access lean_build gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Lean LSP MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for lean_build:
{
"version": "1",
"default": "deny",
"tools": {
"lean_build": {
"limits": [
{
"counter": "lean_build_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}lean_build 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.
lean_build. It is categorised as a Execute tool in the Lean LSP MCP 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 lean_build: 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 MCP. Nothing to install.
lean_build 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 lean_build 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_build. 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_build is provided by the Lean LSP MCP server (ooo0ooo/lean-lsp-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 23 Lean LSP MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
23 Lean LSP MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.