vibe-workspace
Manage a vibe workspace with many repos
claude mcp add --transport stdio toolprint-vibe-workspace docker run -i toolprint/vibe-workspace
How to use
Vibe Workspace exposes an MCP (Model Context Protocol) server that integrates vibe-coding patterns, multi-repo management, and developer tooling templates with AI-assisted workflows. The MCP endpoint enables Claude Code integrations and other AI agents to interact with your workspace metadata, repositories, and templates, allowing actions like querying repository configurations, listing available vibe templates, and triggering setup or provisioning steps through natural language prompts. Use the built-in MCP capabilities to harmonize AI-driven coding patterns across multiple repos, propagate templates, and guide automated workflows within your organization.
How to install
Prerequisites:
- Docker installed and running on your machine
- Access to the toolprint/vibe-workspace Docker image (public or credentials if private)
Installation steps:
- Pull the MCP-enabled vibes image from Docker Hub (or your registry): docker pull toolprint/vibe-workspace:latest
- Run the MCP server container in interactive mode (adjust ports if you need direct access): docker run -it --rm -p 8080:8080 toolprint/vibe-workspace:latest
- Confirm the MCP endpoint is reachable (example URL placeholder; adapt to your setup): http://localhost:8080/mcp
- If you need to customize environment variables, prepare a docker run with -e VAR=value options (see notes below for common vars).
Notes:
- The server runs as a Docker container. If you prefer local development, consider building from source and running a local binary, if you have the Docker image built from the source.
- For CI environments, ensure the container has network access to your repositories and any required credentials.
Additional notes
Environment variables and configuration tips:
- BOARDING: If the MCP server requires authentication or API keys for integrated tools, provide them via environment variables (e.g., MCP_AUTH_TOKEN).
- IMAGE_TAG: Pin to a specific image tag to ensure reproducible behavior (e.g., toolprint/vibe-workspace:1.2.3).
- NETWORK: If running behind a corporate proxy, set HTTP_PROXY/HTTPS_PROXY as needed for container networking.
- Port configuration: Expose the MCP endpoint port (default 8080) in your deployment to allow clients to connect.
- Common issues: container not starting due to missing dependencies in the image, or port conflicts with another service. Check docker ps and container logs for troubleshooting.
Related MCP Servers
neurolink
Universal AI Development Platform with MCP server integration, multi-provider support, and professional CLI. Build, test, and deploy AI applications with multiple ai providers.
langfuse
A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability
just
Share the same project justfile tasks with your AI Coding Agent.
cco
Real-time audit and approval system for Claude Code tool calls.
the -company
TheMCPCompany: Creating General-purpose Agents with Task-specific Tools
cadre-ai
Your AI agent squad for Claude Code. 17 specialized agents, persistent memory, desktop automation, and a common sense engine.