Comprehensive LSP diagnostics combining environment, health, and performance checks. This unified tool consolidates: - Environment and setup diagnostics (formerly swift_diagnose_lsp) - LSP client health status (formerly lsp_health_check) - Performance statistics (formerly lsp_manager_stats) Args:...
AI agents call swift_lsp_diagnostics to retrieve information from SwiftLens without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
swift_lsp_diagnostics is a diagnostic and monitoring tool that retrieves system state, environment configuration, and performance metrics from the LSP server. All operations are observational—querying health, statistics, and environment setup—without modifying any code, files, or system configuration. The optional 'include_recommendations' parameter produces informational output only.
From the tool's definition Tool performs 'diagnostic' checks, 'health status', and 'performance statistics' queries with optional 'include_recommendations'. No modification, deletion, execution of code, or financial operations are described.
Documented attack patterns abuse exactly the kind of access swift_lsp_diagnostics gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SwiftLens, and nothing reaches the server without passing your rules. This is the rule we recommend for swift_lsp_diagnostics:
{
"version": "1",
"default": "deny",
"tools": {
"swift_lsp_diagnostics": {}
}
}swift_lsp_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.
Comprehensive LSP diagnostics combining environment, health, and performance checks. This unified tool consolidates: - Environment and setup diagnostics (formerly swift_diagnose_lsp) - LSP client health status (formerly lsp_health_check) - Performance statistics (formerly lsp_manager_stats) Args: project_path: Optional path to Swift project for testing include_recommendations: Whether to include setup recommendations. It is categorised as a Read tool in the SwiftLens MCP Server, which means it retrieves data without modifying state.
Register the SwiftLens MCP server in PolicyLayer and add a rule for swift_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 SwiftLens. Nothing to install.
swift_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 swift_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 swift_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.
swift_lsp_diagnostics is provided by the SwiftLens MCP server (swiftlens/swiftlens). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 15 SwiftLens tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
15 SwiftLens tools catalogued and risk-classified — across an index of 42,500+ MCP servers.