MCP Sage
An MCP server project that provides a service for automatically selecting the OpenAI O3 or Google Gemini 2.5 Pro model based on the number of tokens, supports recursive embedding of file paths in prompts, and is suitable for code review and solving complex problems.
2.5 points
9.7K

What is MCP-Sage?

MCP-Sage is an intelligent development assistant tool that can send your code files as context to an AI model to obtain professional code review opinions, modification suggestions, or implementation plans. It is particularly suitable for handling large codebases and can automatically select the most suitable AI model for analysis.

How to use MCP-Sage?

Simply provide the path to your code file and a problem description. MCP-Sage will automatically package the code, analyze the context size, and select the most suitable AI model (OpenAI O3 or Google Gemini) to generate suggestions.

Use Cases

1. Require expert-level code review 2. Need more context when handling large codebases 3. Obtain implementation plans for complex functions 4. Need a 'second opinion' from different AI models

Main Features

Expert Opinion (sage-opinion)
Obtain professional analysis and opinions from AI on the code, supporting large context processing
Code Review (sage-review)
Get specific code modification suggestions, returned in SEARCH/REPLACE format for direct application
Implementation Plan (sage-plan)
Generate high-quality implementation plans for complex functions through multi-model debate
Intelligent Model Selection
Automatically select OpenAI O3 (≤200K tokens) or Google Gemini (≤1M tokens) based on the context size
Advantages
Strong ability to handle large codebases (supports up to 1 million tokens of context)
Automatically select the most suitable AI model to save costs
Provide directly applicable code modification suggestions (in SEARCH/REPLACE format)
Generate more reliable implementation plans through multi-model debate
Automatic fallback mechanism for network failures
Limitations
Generating complex plans may take 5 - 15 minutes
API call costs may be high (especially when using multiple models)
Need to configure both OpenAI and Google API keys for the best experience

How to Use

Installation
Ensure that Node.js (v18 or higher) is installed, clone the repository, and install the dependencies
Configure API Keys
Set environment variables to provide the API keys for OpenAI and/or Google Gemini
Start the Service
Run the service and connect it to your development environment
Use the Tool
Call one of the three main tools through the MCP protocol

Usage Examples

Code Review Example
Add error handling to an existing function
Implementation Plan Example
Add user authentication functionality to an application

Frequently Asked Questions

Do I need to configure both API keys?
Why does sage-plan take so long?
How can I control the API usage cost?
What is the maximum supported file size?

Related Resources

OpenAI API Documentation
Official OpenAI API documentation
Google Gemini API Documentation
Official Google Gemini development documentation
MCP Protocol Description
Official description of the Model Context Protocol
Example Project Repository
Example project using MCP-Sage

Installation

Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
4.5K
4.5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
6.6K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
7.2K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
7.4K
5 points
R
Rsdoctor
Rsdoctor is a build analysis tool specifically designed for the Rspack ecosystem, fully compatible with webpack. It provides visual build analysis, multi - dimensional performance diagnosis, and intelligent optimization suggestions to help developers improve build efficiency and engineering quality.
TypeScript
9.3K
5 points
N
Next Devtools MCP
The Next.js development tools MCP server provides Next.js development tools and utilities for AI programming assistants such as Claude and Cursor, including runtime diagnostics, development automation, and document access functions.
TypeScript
9.7K
5 points
T
Testkube
Testkube is a test orchestration and execution framework for cloud-native applications, providing a unified platform to define, run, and analyze tests. It supports existing testing tools and Kubernetes infrastructure.
Go
6.5K
5 points
M
MCP Windbg
An MCP server that integrates AI models with WinDbg/CDB for analyzing Windows crash dump files and remote debugging, supporting natural language interaction to execute debugging commands.
Python
10.5K
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
71.6K
4.3 points
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
20.3K
4.5 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
34.2K
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
25.4K
4.3 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#
31.0K
5 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
65.2K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
21.0K
4.5 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
48.4K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase