TGlider setup recommendations

A few configuration choices decide whether an agent reaches for TGlider instead of falling back to text search. Apply these after installing.

Preload your workspace — the highest-impact setting

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.

Agent system prompt instruction

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.

Scope it to the project

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.

Enable full-workspace text search (install Scout)

TGlider's search_text searches with Scout. Without a Scout binary it returns a scout_not_installed hint, so install Scout to use search_text at all. Scout must be a real executable on your PATH, so install it globally — not just as an npx MCP entry. npx -y @glidermcp/scout runs Scout only for that moment and never leaves a scout binary on PATH, so it does not enable this search. Adding Scout as its own MCP server is complementary — the agent then gets Scout's find tool directly — but it does not replace the global install. Only Scout's lexical search is used here, with no model download. Turn the delegation off with --no-scout or GLIDERMCP_NO_SCOUT=1.

# Put a real scout binary on PATH (pick one):
npm install -g @glidermcp/scout
curl -fsSL https://glidermcp.com/install.sh | sh   # Linux/macOS, installs to ~/.local/bin
brew install glidermcp/tap/scout                   # macOS/Linux

# The install script does not edit PATH. If ~/.local/bin is not already on it:
export PATH="$HOME/.local/bin:$PATH"

# Or skip PATH entirely and point at the binary:
#   SCOUT_BINARY_PATH=/absolute/path/to/scout