Nexus MCP Bridge for VSCode
@wesnermichel
About Nexus MCP Bridge for VSCode
NEXUS MCP- Simple MCP server for Claude Desktop
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"nexus-bridge": {
"url": "http://localhost:3000/mcp",
"disabled": false,
"alwaysAllow": [
"get_system_info",
"read_file",
"write_file",
"create_directory",
"list_directory",
"get_project_status"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Nexus MCP Bridge for VSCode?
A lightweight VSCode extension that enables Claude Desktop to connect to your VSCode workspace through the Model Context Protocol (MCP). It provides file system access, directory management, and configurable security controls for developers using Claude Desktop alongside VSCode.
How to use Nexus MCP Bridge for VSCode?
Install the extension from the VSIX file. Configure settings in VSCode (port, allowed paths, auto-start). Add the server URL to your Claude Desktop claude_desktop_config.json. Use the command palette or status bar to start, stop, or toggle the bridge.
Key features of Nexus MCP Bridge for VSCode
- Minimal memory footprint and lightweight design
- Automatic startup when VSCode launches
- Status bar integration for bridge control
- File system read and write access
- Directory creation and listing
- Security controls for allowed paths
Use cases of Nexus MCP Bridge for VSCode
- Connect Claude Desktop to your VSCode workspace seamlessly
- Reduce memory usage compared to alternative bridges
- Let Claude read and write files without switching applications
- Expose only explicitly allowed directories for safety
FAQ from Nexus MCP Bridge for VSCode
How do I configure the bridge?
Set nexusMcpBridge.port, nexusMcpBridge.startOnLaunch, and nexusMcpBridge.allowedPaths in your VSCode settings. Then configure Claude Desktop with the server URL in claude_desktop_config.json.
Can I start and stop the bridge manually?
Yes. Use the commands "Start Nexus MCP Bridge", "Stop Nexus MCP Bridge", or toggle it via the status bar icon.
What directories can Claude access?
Only the paths listed in nexusMcpBridge.allowedPaths in your settings. By default no paths are allowed until you configure them.
Does the bridge run locally?
Yes. The MCP server runs on http://localhost:3000/mcp by default (port configurable). No remote data transmission is required.
What are the runtime requirements?
Only VSCode and Claude Desktop. No additional dependencies or runtime environments are needed.
Frequently asked questions
How do I configure the bridge?
Set `nexusMcpBridge.port`, `nexusMcpBridge.startOnLaunch`, and `nexusMcpBridge.allowedPaths` in your VSCode settings. Then configure Claude Desktop with the server URL in `claude_desktop_config.json`.
Can I start and stop the bridge manually?
Yes. Use the commands "Start Nexus MCP Bridge", "Stop Nexus MCP Bridge", or toggle it via the status bar icon.
What directories can Claude access?
Only the paths listed in `nexusMcpBridge.allowedPaths` in your settings. By default no paths are allowed until you configure them.
Does the bridge run locally?
Yes. The MCP server runs on `http://localhost:3000/mcp` by default (port configurable). No remote data transmission is required.
What are the runtime requirements?
Only VSCode and Claude Desktop. No additional dependencies or runtime environments are needed.
Basic information
More AI & Agents MCP servers
Solon Ai
opensolonJava AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.
1MCP - One MCP Server for All
1mcp-appA unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.
Sequential Thinking Multi-Agent System (MAS)
FradSerAn advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.
欢迎来到 智言平台
Shy2593666979AgentChat 是一个基于 LLM 的智能体交流平台,内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作,Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术,实现高效的知识检索与工具调用,使用 FastAPI 构建高性能后端服务。
🛡️ A.I.G(AI-Infra-Guard)
TencentA full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
Comments