How do I use GBrainMCP?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@GBrainMCP search my knowledge base for hybrid retrieval methods and summarize" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

GBrainMCP 协同版本

这是 GBrain 的隐私清理版本，专门用于团队协作和分享。

🎯 协同说明

本仓库专为小元协作创建，包含完整的 GBrain MCP 源码，但已移除所有个人隐私信息。

Related MCP server: pce-memory

🚀 快速开始

1. 克隆仓库

git clone https://github.com/cyberbird2048/gbrainmcp-clean.git
cd gbrainmcp-clean

2. 配置个人设置

# 复制配置模板
cp config.example.json ~/.gbrain/config.json

# 编辑配置，填入自己的 API key 和数据库信息
nano ~/.gbrain/config.json

3. 安装依赖

bun install

4. 启动 MCP 服务器

bun run serve

📦 核心功能

混合检索系统：向量搜索 + 全文检索 + 重排序
多模态支持：文本、图片、代码、音频转录
代码智能：调用关系、定义查找、代码分析
时序追踪：trajectory、salience、takes 评分
MCP 协议：标准化工具接口，支持多种客户端

🔒 隐私保护

本版本已移除：

✅ API keys 和个人凭证
✅ 数据库连接字符串
✅ 机器特定配置
✅ 个人路径信息

👥 协作者

创建者: cyberbird2048
协作者: 小元 (待邀请)

📚 文档

详细文档请查看 docs/mcp/ 目录：

DEPLOY.md - 部署选项
CLAUDE_DESKTOP.md - Claude Desktop 集成
CHATGPT.md - ChatGPT 集成

🔧 开发

# 运行测试
bun test

# 构建
bun run build

# Lint
bun run lint

📄 许可证

MIT License - 与原 GBrain 项目保持一致

🌟 GBrain 原项目: https://github.com/garrytan/gbrain 🔧 MCP 协议: https://modelcontextprotocol.io

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivitySlowing

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Related MCP Connectors

Artificial Wit AIOAuth
com.artificialwit
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
ERP Systems CRM Knowledge & Memory
2
mcp A
ai.llmse
Public MCP server for the LLM Search Engine
Search RAG Systems Developer Tools
102
pearl-api-mcp-server A
com.pearl.mcp
Hybrid human + AI expertise for faster, trusted answers and decisions via MCP Server.
Search Knowledge & Memory
52
CustomGPT.ai
ai.customgpt.mcp
The CustomGPT.ai MCP server is a fully managed, RAG-powered endpoint that connects large language models with private knowledge bases and external data sources. It provides tools for retrieval-augmented generation queries (send_message), data ingestion (upload_file), and source listing, enabling AI agents to query private documents like PDFs with high accuracy and real-time citations.
RAG Systems Knowledge & Memory Search
2

Related MCP Servers

nexus-mcp-ci
AI & Machine Learning Code Analysis Developer Tools
jaggernaut007
A
license
A
quality
B
maintenance
Unified MCP server: hybrid search + code graph + semantic memory. 10 tools, <350MB RAM, fully local. No API keys.
Updated 6 days ago (2026-09-18 15:37 UTC)
10
PolyForm Noncommercial 1.0.0
pce-memory
Knowledge & Memory RAG Systems
CAPHTECH
A
license
Not graded
quality
C
maintenance
MCP server for context-aware memory and retrieval with hybrid search, dual-phase memory, and boundary-first security.
Updated 6 months ago (2026-04-01 03:09 UTC)
3
MIT
exo
Knowledge & Memory RAG Systems
guqing
A
license
Not graded
quality
D
maintenance
An MCP server that ingests various data sources and uses LLMs to compile them into structured knowledge pages, enabling hybrid search and integration with AI coding tools like Claude Code and Cursor.
Updated 5 months ago (2026-04-15 06:42 UTC)
14 npm
1
MIT
hybrid-recall
RAG Systems Knowledge & Memory Search
cutlerbenjamin1-cmd
A
license
A
quality
C
maintenance
A local MCP server enabling hybrid search over documents, memory, and knowledge graphs for retrieval-augmented generation, with tools for SQLite, semantic memory, and entity-relationship queries.
Updated 2 months ago (2026-07-13 01:20 UTC)
4
1
MIT