discussion_partner
AI agents call discussion_partner 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.
Given the lack of a description, classification relies on the tool's name and context. 'Discussion partner' most naturally suggests an interactive query or conversational tool that reads and responds to information about Lean code, similar to other read-oriented tools on this server (diagnostic inspection, file analysis, completions). No evidence suggests data modification, deletion, or execution of arbitrary code.
From the tool's definition Tool name 'discussion_partner' with empty description; contextually situated among sibling tools (file_outline, lean_completions, lean_diagnostic_messages, lean_file_contents) that are all introspective/analytical.
Documented attack patterns abuse exactly the kind of access discussion_partner 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 discussion_partner:
{
"version": "1",
"default": "deny",
"tools": {
"discussion_partner": {}
}
}discussion_partner 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.
discussion_partner. 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 discussion_partner: 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.
discussion_partner 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 discussion_partner 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 discussion_partner. 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.
discussion_partner 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.