Frequently Asked Questions about VS Code MCP Server

Q: What is the VS Code MCP Server?

A: The VS Code MCP Server is a Visual Studio Code extension that exposes VS Code’s editing features to an LLM (Large Language Model) for AI coding. It allows AI models and other MCP clients to interact with your VS Code workspace.

Q: What is MCP?

A: MCP stands for Model Context Protocol. It’s an open protocol that standardizes how applications provide context to LLMs, enabling AI models to access and interact with external data sources and tools.

Q: How does the VS Code MCP Server work?

A: The extension creates an MCP server that runs locally on a configurable port. It handles MCP protocol requests via HTTP and exposes VS Code’s functionality as MCP tools to AI models.

Q: What features does the VS Code MCP Server offer?

A: The extension allows AI models to list files, read file contents, create new files, replace lines in files, check for diagnostics (errors and warnings), search for symbols, get symbol definitions, and execute shell commands in the VS Code integrated terminal.

Q: What are the use cases for the VS Code MCP Server?

A: It can be used for AI-powered code completion, automated refactoring, smart debugging, code generation, and code explanation.

Q: How do I install the VS Code MCP Server?

A: You can install the extension from the Visual Studio Code Marketplace by searching for “VS Code MCP Server”.

Q: How do I configure my LLM client to use the VS Code MCP Server?

A: Configure your LLM client to connect to the MCP Server using the address http://localhost:3000/mcp (or the configured port).

Q: Is the VS Code MCP Server secure?

A: The extension allows for the execution of shell commands, which presents a potential security risk. Use with caution, trust the MCP client, and ensure that the port is not exposed to untrusted networks.

Q: What is UBOS and how does it relate to the VS Code MCP Server?

A: UBOS is a full-stack AI Agent Development Platform. The VS Code MCP Server can be used in conjunction with UBOS to orchestrate AI Agents, connect them with enterprise data, and build custom AI Agents.

Q: What is the default port for the VS Code MCP Server?

A: The default port is 3000, but it can be configured in the extension settings.

Q: Can I use the VS Code MCP Server with multiple workspaces?

A: Currently, only one workspace is supported.

Q: Does the VS Code MCP Server work remotely?

A: The extension only works locally to avoid exposing your VS Code instance to any network you may be connected to.

Q: How do I contribute to the VS Code MCP Server project?

A: Contributions are welcome! Feel free to submit issues or pull requests on the project’s GitHub repository.