AIbase
EN
Explore
Bifrostmcp
B

Bifrostmcp

Bifrost is a VSCode extension that provides MCP server functionality, exposing VSCode's development tools and language features for use by AI tools, and supporting code navigation, analysis, and operation.
Developer toolsArtificial intelligence chatbots#Code Analysis#AI Integration#Language Service#Intelligent Navigation.TypeScript
2 points
14

What is the Bifrost MCP Server?

Bifrost is a VS Code extension that creates a Model Context Protocol (MCP) server to expose VSCode's powerful development tools and language features to AI tools. It enables AI coding assistants that support the MCP protocol to implement advanced code navigation, analysis, and operation functions.

How to Use Bifrost?

After installing the extension, Bifrost will automatically start the MCP server. You need to configure your AI assistant to connect to the server endpoint (default port 8008). It supports AI coding assistants such as Cursor and Roo Code.

Applicable Scenarios

When you use an AI coding assistant for code development, refactoring, or analysis, Bifrost can provide more accurate code context and more powerful code navigation functions. It is particularly suitable for large - scale projects or multi - language project development.

Main Features

Language Server IntegrationAccess VSCode's language server features for any supported language
Code NavigationFind references, definitions, implementations, etc.
Symbol SearchSearch for symbols across the entire workspace
Code AnalysisGet semantic markers, document symbols, and type information
Smart SelectionPerform smart code selection using semantic selection ranges
Multi - Project SupportConfigure independent ports and endpoints for each project

Advantages and Limitations

Advantages
Expose VSCode's powerful language features to AI tools
Support multiple programming languages (corresponding language extensions need to be installed)
Provide accurate code context and navigation functions
Support multiple projects working simultaneously
Seamlessly integrate with AI assistants such as Cursor and Roo Code
Limitations
Requires VSCode as the running environment
Some language features require additional installation of language extensions
Multi - project configuration requires manual setting of different ports
Initial use requires certain configuration work

How to Use

Install the Extension
Install the Bifrost MCP extension from the VS Code Marketplace
Configure the AI Assistant
Add the corresponding configuration according to the AI assistant you are using (Cursor or Roo Code)
Start the Server
The extension will automatically start the server, or you can manually start it using the command
Multi - Project Configuration (Optional)
Create a bifrost.config.json file in the project root directory to configure the project - specific port

Usage Examples

Find Symbol ReferencesFind all reference locations of a function or variable in the code
Workspace Symbol SearchSearch for a specific symbol across the entire workspace

Frequently Asked Questions

Why can't my AI assistant connect to the Bifrost server?
How to use different ports for different projects?
What causes some language features to be unavailable?
How to check if the server is running properly?

Related Resources

VS Code Marketplace Page
The marketplace page of the Bifrost extension
GitHub Repository
Project source code and issue tracking
Example Cursor Rules
Example rule file for Cursor usage
Supergateway Project
Supergateway required for Cline installation
Installation
Copy the following command to your Client for configuration
{
  "mcpServers": {
    "Bifrost": {
      "command": "cmd",
      "args": [
        "/c",
        "npx",
        "-y",
        "supergateway",
        "--sse",
        "http://localhost:8008/sse"
      ],
      "disabled": false,
      "autoApprove": [],
      "timeout": 600
    }
  }
}

{
  "mcpServers": {
    "Bifrost": {
      "command": "npx",
      "args": [
        "-y",
        "supergateway",
        "--sse",
        "http://localhost:8008/sse"
      ],
      "disabled": false,
      "autoApprove": [],
      "timeout": 600
    }
  }
}

{
  "mcpServers": {
    "Bifrost": {
      "url": "http://localhost:8008/sse"
    }
  }
}

{
  "mcpServers": {
    "BackendAPI": {
      "url": "http://localhost:5643/backend-api/sse"
    },
    "FrontendApp": {
      "url": "http://localhost:5644/frontend-app/sse"
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.
N
Notte Browser
Certified
Notte is an open-source full-stack network AI agent framework that provides browser sessions, automated LLM-driven agents, web page observation and operation, credential management, etc. It aims to transform the Internet into an agent-friendly environment and reduce the cognitive burden of LLMs by describing website structures in natural language.
661
4.5 points
S
Search1api
The Search1API MCP Server is a server based on the Model Context Protocol (MCP), providing search and crawling functions, and supporting multiple search services and tools.
TypeScript
343
4 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
830
4.3 points
B
Bing Search MCP
An MCP server for integrating Microsoft Bing Search API, supporting web page, news, and image search functions, providing network search capabilities for AI assistants.
Python
229
4 points
M
MCP Alchemy
Certified
MCP Alchemy is a tool that connects Claude Desktop to multiple databases, supporting SQL queries, database structure analysis, and data report generation.
Python
325
4.2 points
P
Postgresql MCP
A PostgreSQL database MCP service based on the FastMCP library, providing CRUD operations, schema inspection, and custom SQL query functions for specified tables.
Python
112
4 points
M
MCP Scan
MCP-Scan is a security scanning tool for MCP servers, used to detect common security vulnerabilities such as prompt injection, tool poisoning, and cross-domain escalation.
Python
616
5 points
A
Agentic Radar
Agentic Radar is a security scanning tool for analyzing and assessing agentic systems, helping developers, researchers, and security experts understand the workflows of agentic systems and identify potential vulnerabilities.
Python
557
5 points
Featured MCP Services
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
141
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
830
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.7K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
87
4.3 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.7K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
567
5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
754
4.8 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
5.2K
4.7 points
AIbase
Zhiqi Future, Your AI Solution Think Tank
English简体中文繁體中文にほんご
© 2025AIbase