STRATA
🌌 STRATA — 通用上下文桥接器
STRATA 是一个高性能的 Model Context Protocol (MCP) 服务器,充当 AI 助手和 LLM 代理(Claude Desktop、Cursor、Continue.dev、ChatGPT 等)的通用上下文桥接器。
它借助 Supabase PostgreSQL、全文索引和 pgvector 语义搜索,为 AI 模型提供跨对话和编码会话的持久记忆。
⚡ 功能特性
🧠 持久上下文记忆:AI 代理可以跨会话保存决策、设计系统、API 契约、偏好和代码片段。
🔍 智能记忆搜索:快速全文和上下文搜索,并自动回退到最近记录。
🚀 现代 MCP 2.0 SDK:使用最新的
MCPServer装饰器架构构建,支持 Server-Sent Events (SSE) 流式传输。🗄️ Supabase 与 PostgreSQL:久经考验的云数据库层,支持 pgvector 和行级安全(RLS)。
🔄 单例连接池:缓存客户端实例,实现高吞吐、低延迟的工具执行。
🩺 内置健康检查:用于运行时间监控和连接状态检查的 REST 端点(
/health)。
Related MCP server: memory-mcp
🛠️ 可用的 MCP 工具
工具 | 描述 | 参数 |
| 将上下文、偏好、决策或代码保存到长期记忆中 |
|
| 搜索与关键词或查询匹配的历史上下文和讨论 |
|
| 列出存储在 STRATA 中的最近上下文条目 |
|
| 按 UUID 删除特定的记忆条目 |
|
| 查看数据库连接状态、记忆数量和元数据 | None |
🚀 快速开始
1. 前提条件
Python 3.10 或更高版本
一个 Supabase 账户和项目
2. 克隆并配置环境
# Clone the repository
git clone https://github.com/your-username/STRATA.git
cd STRATA
# Copy environment file and configure your keys
cp .env.example .env使用你的 Supabase 凭据编辑 .env:
SUPABASE_URL=https://your-project.supabase.co
SUPABASE_KEY=your-supabase-service-role-key
DEFAULT_USER_ID=your-user-uuid (optional)3. 安装依赖
cd apps/api
python -m venv venv
# Activate virtual environment:
# Windows (PowerShell):
.\venv\Scripts\Activate.ps1
# macOS / Linux:
source venv/bin/activate
# Install requirements
pip install -r requirements.txt4. 数据库设置
在你的 Supabase SQL Editor 中运行位于 supabase_schema.sql 的 SQL 模式,以初始化表、向量扩展和全文索引。
5. 启动服务器
# From apps/api directory:
uvicorn main:app --reload --port 8000服务器在 http://localhost:8000 上启动,并提供以下端点:
SSE 端点:
http://localhost:8000/sse消息端点:
http://localhost:8000/messages/健康检查:
http://localhost:8000/health
🔌 连接 MCP 客户端
Claude Desktop
将以下内容添加到你的 claude_desktop_config.json:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"strata": {
"url": "http://localhost:8000/sse"
}
}
}Cursor IDE
在 Cursor 设置的 Features > MCP Servers 下,添加一个新服务器:
名称:
STRATA类型:
sseURL:
http://localhost:8000/sse
📁 项目结构
STRATA/
├── apps/
│ └── api/ # Python MCP Server
│ ├── main.py # Server logic, MCPServer instance & tools
│ ├── requirements.txt # Python dependencies
│ └── venv/ # Python virtual environment
├── .env.example # Template environment file
├── .gitignore # Version control ignores
├── package.json # Root monorepo configuration
├── supabase_schema.sql # Database schema, pgvector, and indexes
└── README.md # Documentation🛡️ 许可证
MIT 许可证。详见 LICENSE。
bounce-mcp
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseBqualityDmaintenanceA Model Context Protocol (MCP) server that provides persistent memory capabilities using OpenAI's vector stores, allowing AI assistants to save and search through memories across conversations.2
- AlicenseNot gradedqualityCmaintenanceAn MCP server that stores project memory in Supabase, allowing AI tools to persist context, notes, and decisions across sessions. Enables Claude Code, Codex, and similar assistants to maintain long-term project continuity through persistent memory storage.2
- AlicenseNot gradedqualityCmaintenancePersistent semantic memory server for AI assistants via MCP, enabling long-term context retention and semantic search across conversations.11MIT
- AlicenseNot gradedqualityCmaintenanceA self-hostable MCP server that provides permanent memory for AI agents using Postgres + pgvector for semantic search and Markdown file sync.MIT
Related MCP Connectors
Cloud-hosted MCP server for durable AI memory
An MCP memory server. One memory your agents share — across models, devices and apps.
Shared, governed long-term memory for AI agents across tools and sessions via MCP and REST.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ssundxr/bounce-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server