VSCode MCP Server
by Block
The VSCode MCP Server enables AI agents and assistants to interact with VSCode through the Model Context Protocol. It provides a set of tools for AI agents to perform actions within the VSCode environment.
Last updated: N/A
What is VSCode MCP Server?
The VSCode MCP Server is a component that allows AI agents and assistants (like Goose or Claude) to interact with the VSCode editor. It acts as a bridge, enabling AI to perform tasks such as opening files, creating diffs, and managing projects within VSCode.
How to use VSCode MCP Server?
To use the VSCode MCP Server, first install the server using npx vscode-mcp-server install
. Then, install the VSCode extension. Configure your AI agent (e.g., Goose or Claude) to communicate with the server using the provided configuration examples.
Key features of VSCode MCP Server
Enables AI agent interaction with VSCode
Provides tools for file manipulation and project management
Supports user approval for sensitive actions like creating diffs
Offers configuration examples for popular AI agents like Goose and Claude
Use cases of VSCode MCP Server
Automating code modifications based on AI suggestions
Allowing AI agents to navigate and explore codebases
Integrating AI-powered refactoring tools into VSCode
Enabling AI assistants to help developers with coding tasks
FAQ from VSCode MCP Server
What is the Model Context Protocol (MCP)?
What is the Model Context Protocol (MCP)?
MCP is a protocol that enables communication between AI models and development environments like VS Code.
How do I install the MCP Server?
How do I install the MCP Server?
Use the command npx vscode-mcp-server install
.
Where can I find the VSCode MCP Extension?
Where can I find the VSCode MCP Extension?
The extension is available on the VSCode Marketplace.
How do I configure Goose to use the MCP Server?
How do I configure Goose to use the MCP Server?
Refer to the Goose Desktop Setup section in the README for the required configuration.
What tools are available for AI agents?
What tools are available for AI agents?
The server provides tools like create_diff
, open_file
, open_project
, check_extension_status
, get_extension_port
, and list_available_projects
.