Get diagnostic messages (errors, warnings) for files. Use this tool to identify problems in code files such as syntax errors, type mismatches, or other issues detected by the language server. When used without a file_path, returns diagnostics for all open files. Requires files to be opened first.
AI agents call get_diagnostics to retrieve information from LSP MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
get_diagnostics performs read-only queries of language server diagnostics. It retrieves and reports information about code problems without creating, modifying, deleting, or executing any code. The tool has no side effects beyond returning data. While it depends on files being open first, opening a document is itself a read operation in this context. This is a low-severity read operation with minimal risk of misuse.
From the tool's definition Tool retrieves diagnostic messages (errors, warnings) for files. Description states it 'identifies problems in code files' and 'returns diagnostics' - purely informational queries with no modification, deletion, or execution.
Documented attack patterns abuse exactly the kind of access get_diagnostics gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and LSP MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_diagnostics:
{
"version": "1",
"default": "deny",
"tools": {
"get_diagnostics": {}
}
}get_diagnostics 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.
Get diagnostic messages (errors, warnings) for files. Use this tool to identify problems in code files such as syntax errors, type mismatches, or other issues detected by the language server. When used without a file_path, returns diagnostics for all open files. Requires files to be opened first. It is categorised as a Read tool in the LSP MCP Server MCP Server, which means it retrieves data without modifying state.
Register the LSP MCP Server MCP server in PolicyLayer and add a rule for get_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 MCP Server. Nothing to install.
get_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 get_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 get_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.
get_diagnostics is provided by the LSP MCP Server MCP server (tritlo/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 9 LSP MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
9 LSP MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.