MCP4Humans - Model Context Protocol Client for VS Code
LocalAbout MCP4Humans - Model Context Protocol Client for VS Code
MCP4Humans is a VS Code extension for people who want to connect to MCP servers and run their tools from the editor. It supports local stdio and remote HTTP servers, including parallel use of multiple servers.
Key features
- 01Add, edit, and delete server configurations
- 02Connect to local stdio and remote HTTP servers
- 03Browse and execute server tools
- 04Use multiple servers in parallel
- 05View results and event logs
Use cases
- 01Configure MCP servers in VS Code
- 02Browse and run tools from multiple servers
- 03Review tool results and connection status
MCP support
As an MCP client, it manages local stdio and remote HTTP (SSE or Streamable HTTP) MCP servers and invokes their tools.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP4Humans - Model Context Protocol Client for VS Code
![]()
MCP4Humans is a user-friendly VS Code extension that allows you to connect to and interact with Model Context Protocol (MCP) servers directly from your editor. It provides an intuitive interface for managing MCP servers, executing tools, and viewing results.
What is MCP?
The Model Context Protocol (MCP) is an open standard for AI tools and agents to interact with external systems. It enables AI models to access tools, resources, and capabilities beyond their training data, such as:
- Retrieving information from databases or the web
- Executing code
- Accessing file systems
- Interacting with APIs
- And much more
Features
Easy Server Management
- Add, edit, and delete MCP server configurations
- Connect to both local (stdio) and remote HTTP MCP servers (SSE or StreamableHTTP)
- View server connection status at a glance

Tool Execution
- Browse available tools from connected MCP servers
- Execute tools with a simple form interface
- View tool execution results in a collapsible panel
- Work with multiple servers in parallel
- View raw logs for main events in a tree view format for easy consumption

Seamless Integration
- Access MCP servers directly from the VS Code sidebar
- Persistent storage of server configurations
- Intuitive UI
Getting Started
- Install the MCP4Humans extension from the VS Code Marketplace
- Click the MCP4Humans icon in the activity bar to open the MCP Servers view
- Click "+ Add Server" to add a new MCP server
- Fill in the server details:
- You may start by pasting the usual JSON configurations in the JSON box and letting it populate part of the form for you.
- Fill in the rest as needed.
- Click "Connect" to test and save the server configuration
- Click on a server in the list to view and execute available tools
Supported Server Types
Local (stdio) Servers
MCP4Humans supports local MCP servers that communicate via standard input/output (stdio). You can configure:
- Command: The executable to run (e.g.,
python,node,uv) - Arguments: Command-line arguments (e.g.,
run,server.py) - Working Directory: For local installations or development.
- Environment Variables: Custom environment variables to pass to the server process.
Remote HTTP Servers
MCP4Humans also supports remote MCP servers that communicate via Server-Sent Events (SSE) or Streamable HTTP. You can configure:
- URL: The server endpoint (format:
http(s)://{host}:{port}/sseorhttp(s)://{host}:{port}/mcp) - Headers: Custom HTTP headers for authentication or other purposes
Requirements
- VS Code 1.96.3 or higher (Compatible with latest Cursor and VSCode)
- An MCP-compatible server to connect to
Feedback and Contributions
- File issues and feature requests on our GitHub repository
- Contribute to the development by submitting pull requests
License
This extension is licensed under the MIT License. See the LICENSE file for details.
Enjoy using MCP4Humans!
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.