Quickstart
Complete this guide to make one local repository available to AI agents through Frigg’s shared MCP service.
Prerequisites
Section titled “Prerequisites”- macOS or GNU/glibc Linux for the shell installer, or another path from Installation.
- A Git repository to index.
- An MCP client that supports streamable HTTP.
1. Install Frigg
Section titled “1. Install Frigg”curl -fsSL https://raw.githubusercontent.com/bnomei/frigg/main/scripts/install.sh \ | FRIGG_VERSION=0.9.0 shfrigg --versionExpected version output:
frigg 0.9.02. Index the repository
Section titled “2. Index the repository”Run from the repository root:
frigg initfrigg indexIn non-interactive output, successful commands end with summaries like:
ok init: complete status=ok repos=1ok index: complete status=ok mode=full3. Start the shared service
Section titled “3. Start the shared service”frigg serveFrigg listens at:
http://127.0.0.1:37444/mcpKeep this process running while clients use Frigg.
4. Configure the project
Section titled “4. Configure the project”Preview and apply managed agent instructions plus project MCP configuration:
frigg adopt --target agents-md --target mcp-project --dry-runfrigg adopt --target agents-md --target mcp-projectThe managed MCP entry points to the loopback HTTP service above.
5. Verify from the client
Section titled “5. Verify from the client”Reload the client, call workspace, and adopt the repository explicitly if Frigg does not select it automatically:
{ "path": "/absolute/path/to/repo"}Then use search_hybrid for discovery, search_text for an exact string, and read_match or read_file for source proof.
Next steps
Section titled “Next steps”Source Anchors
Section titled “Source Anchors”../frigg/README.md../frigg/scripts/install.sh../frigg/crates/cli/src/cli_args.rs../frigg/crates/cli/src/http_runtime.rs