AI agents call lsp_diagnostics to retrieve information from Lsp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and reports diagnostic information (compiler errors, warnings, hints) from a language server without modifying code, executing commands, or triggering external operations. It is purely informational and read-only, making it a Read category with low severity. An AI agent misusing this tool could only waste resources or overwhelm the user with diagnostic output, but cannot cause damage.
From the tool's definition Tool description states it "Get[s] compiler errors, warnings, and hints for a file" and that "Results are cached from language server notifications." The verb "Get" and the passive nature of retrieving diagnostic output indicates a read-only operation with no…
Attacks that exploit this kind of access
Get compiler errors, warnings, and hints for a file. Use after making changes to check for type errors, missing imports, or other issues. Results are cached from language server notifications. It is categorised as a Read tool in the Lsp MCP Server, which means it retrieves data without modifying state.
Register the Lsp MCP server in PolicyLayer and add a rule for lsp_diagnostics: 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 Lsp. Nothing to install.
lsp_diagnostics 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 lsp_diagnostics 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 lsp_diagnostics. 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.
lsp_diagnostics is provided by the Lsp MCP server (lsp-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →