AI agents call lean_diagnostic_messages to retrieve information from Lean LSP MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves diagnostic messages (errors, warnings) from Lean compilation/analysis, which is a read-only operation with no side effects. It queries the state of a project rather than modifying, executing, or deleting anything. Severity is low because diagnostic information is non-sensitive metadata about code analysis.
From the tool's definition Tool name 'lean_diagnostic_messages' combined with server description stating it provides 'accessing diagnostics' indicates retrieval of diagnostic information from the Lean theorem prover.
Documented attack patterns abuse exactly the kind of access lean_diagnostic_messages 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_diagnostic_messages:
{
"version": "1",
"default": "deny",
"tools": {
"lean_diagnostic_messages": {}
}
}lean_diagnostic_messages 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_diagnostic_messages. It is categorised as a Read tool in the Lean LSP MCP MCP Server, which means it retrieves data without modifying state.
Register the Lean LSP MCP server in PolicyLayer and add a rule for lean_diagnostic_messages: 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_diagnostic_messages 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_diagnostic_messages 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_diagnostic_messages. 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_diagnostic_messages 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.