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
7.8K

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

A
Acemcp
Acemcp is an MCP server for codebase indexing and semantic search, supporting automatic incremental indexing, multi-encoding file processing, .gitignore integration, and a Web management interface, helping developers quickly search for and understand code context.
Python
8.6K
5 points
B
Blueprint MCP
Blueprint MCP is a chart generation tool based on the Arcade ecosystem. It uses technologies such as Nano Banana Pro to automatically generate visual charts such as architecture diagrams and flowcharts by analyzing codebases and system architectures, helping developers understand complex systems.
Python
7.1K
4 points
M
MCP Agent Mail
MCP Agent Mail is a mail - based coordination layer designed for AI programming agents, providing identity management, message sending and receiving, file reservation, and search functions, supporting asynchronous collaboration and conflict avoidance among multiple agents.
Python
8.4K
5 points
K
Klavis
Klavis AI is an open-source project that provides a simple and easy-to-use MCP (Model Context Protocol) service on Slack, Discord, and Web platforms. It includes various functions such as report generation, YouTube tools, and document conversion, supporting non-technical users and developers to use AI workflows.
TypeScript
12.9K
5 points
M
MCP
The Microsoft official MCP server provides search and access functions for the latest Microsoft technical documentation for AI assistants
11.9K
5 points
A
Aderyn
Aderyn is an open - source Solidity smart contract static analysis tool written in Rust, which helps developers and security researchers discover vulnerabilities in Solidity code. It supports Foundry and Hardhat projects, can generate reports in multiple formats, and provides a VSCode extension.
Rust
10.6K
5 points
D
Devtools Debugger MCP
The Node.js Debugger MCP server provides complete debugging capabilities based on the Chrome DevTools protocol, including breakpoint setting, stepping execution, variable inspection, and expression evaluation.
TypeScript
10.0K
4 points
S
Scrapling
Scrapling is an adaptive web scraping library that can automatically learn website changes and re - locate elements. It supports multiple scraping methods and AI integration, providing high - performance parsing and a developer - friendly experience.
Python
11.8K
5 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
17.5K
4.5 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
18.4K
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
27.4K
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
53.5K
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
51.1K
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#
23.1K
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
17.1K
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
36.5K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2025AIBase