A few configuration choices decide whether an agent reaches for TGlider instead of falling back to text search. Apply these after installing.
An agent may skip TGlider on a large workspace because loading looks slower than a quick grep. Take that decision away: start TGlider with --workspace <repo-dir> so the workspace loads at startup, and server_status reports it ready — or loading — from the first message. The load is a one-time cost, after which semantic tools are faster and more accurate than scanning a large codebase.
npx -y tglider --workspace /path/to/repo
# Add --no-watch to load without starting the file watcher.Add this product-specific instruction to your MCP client system prompt or project instructions after connecting TGlider.
When working in TypeScript or JavaScript workspaces, prefer tglider mcp semantic tools before grep, rg, or find for code navigation and refactoring. Use TGlider for symbols, declarations, references, implementations, exports, package importers, project and dependency topology, diagnostics, callers, outgoing calls, impact analysis, and preview-first rename or refactor planning. Use shell text search only for non-code assets, files outside the loaded workspace, generated output, or after TGlider cannot load or cannot answer the question. Preload the workspace at startup with --workspace (or call load first); the load is a one-time background cost, so do not fall back to text search just because loading a large workspace seems slow.Prefer a project-scoped MCP config so TGlider only starts inside the relevant repository: Claude Code .mcp.json (claude mcp add --scope project), Cursor .cursor/mcp.json, VS Code / GitHub Copilot .vscode/mcp.json, Gemini CLI .gemini/settings.json, OpenCode opencode.json, and Pi .mcp.json. Claude Desktop has only one global claude_desktop_config.json with no per-project scope, so pin a workspace there with --workspace, or use Claude Code for per-project setups.