Glider setup recommendations

A few configuration choices decide whether an agent reaches for Glider on a large solution instead of falling back to text search. Apply these after installing.

Preload your solution — the highest-impact setting

On a large solution an agent may skip Glider because the initial C#/.NET analysis load looks slower than a quick grep. Take that decision away: start Glider with --solution so the workspace loads at startup in the background, and server_status reports it ready — or loading, with an ETA under workspaceLoading — from the first message. The load is a one-time cost, after which semantic queries are faster and more accurate than scanning millions of lines of text. On a very large solution, point --solution at the specific .csproj you are working in and widen later with load.

glider --solution C:/repos/app/src/App.sln --default-timeout 30m
# Add --workspace C:/repos/app to watch a different root, or --no-watch to disable file watching.

Agent system prompt instruction

Add this product-specific instruction to your MCP client system prompt or project instructions after connecting Glider.

When working in C#/.NET workspaces, prefer glider mcp semantic tools before shell text search for code navigation and refactoring. Use Glider for symbol lookup, references, implementations, overrides, callers, call graphs, type and project dependencies, diagnostics, impact analysis, and preview-first refactors. Use grep, rg, or find only for non-C# assets, files outside the loaded workspace, generated output, or after Glider cannot load or cannot answer the question. Preload the solution at startup with --solution (or call load first); a large solution loads once as a background cost, so do not fall back to text search just because loading seems slow — semantic queries stay faster and more accurate than scanning a large codebase.

Scope it to the project

Prefer a project-scoped MCP config so Glider 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 solution there with --solution, or use Claude Code for per-project setups.

Enable full-workspace text search (install Scout)

Glider's search_text works on its own over loaded C# documents. Installing Scout upgrades it to search every file under your solution root — the directory holding the loaded .sln or .csproj — in any language. If your solution sits in a subdirectory, files above it are outside that root. 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