Skip to main content
Glama
ksh00500

Personal Brain MCP

by ksh00500

Personal Brain MCP v0.2

一个基于 PostgreSQL 的长期个人记忆 MCP 服务器。它支持本地 Docker PostgreSQL 和远程 Neon PostgreSQL,并对外暴露一个 Streamable HTTP MCP 端点,可用于在 Render 上托管。

MCP 工具

  • get_personal_context

  • save_memory

  • query_personal_database — 仅限模型生成的只读 SQL

  • update_context_manifest

Related MCP server: brain-mcp

远程端点

  • MCP: POST /mcp (Streamable HTTP)

  • 健康检查: GET /health

使用 Docker PostgreSQL 进行本地开发

cp .env.example .env
# Remove/comment DATABASE_URL in .env to use the local Docker settings.
docker compose up -d
npm install
npm run check
npm run dev

服务器默认监听 http://localhost:10000

Neon / Render

在 Render 中设置以下环境变量:

DATABASE_URL=<Neon connection string>
MCP_API_KEY=<long random secret, recommended>
USER_ID=main
USER_NAME=<your display name>
USER_LANGUAGE=ko
USER_TIMEZONE=Asia/Seoul

Render 会自动提供 PORT。应用会绑定到 0.0.0.0:$PORT

构建命令:

npm install && npm run build

启动命令:

npm start

健康检查路径:

/health

部署后,MCP 端点为:

https://<your-render-service>.onrender.com/mcp

如果设置了 MCP_API_KEY,客户端必须发送:

Authorization: Bearer <MCP_API_KEY>

数据库初始化

启动时,应用会安全地创建所需的表和索引(如果它们尚未存在)。在 v0.2 中,pgvector 是可选的;如果未能启用它,也不会阻止启动。

安全性

  • .env 被 Git 忽略。

  • 切勿提交 Neon 连接字符串、密码、API 密钥或令牌。

  • query_personal_database 只接受一个 SELECT/WITH 查询,在只读事务中运行,并将输出限制为 100 行。

A
license - permissive license
-
quality - not tested
B
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

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

  • A
    license
    -
    quality
    D
    maintenance
    A Model Context Protocol server that provides AI assistants with persistent semantic memory and knowledge graph capabilities using PostgreSQL and vector embeddings. It enables cross-session storage, hybrid search, and complex relationship tracking for enhanced contextual awareness.
    16
    1
    MIT
  • A
    license
    -
    quality
    D
    maintenance
    An MCP server that provides persistent semantic memory backed by PostgreSQL and pgvector for storing and searching thoughts via vector embeddings. It enables dimensional organization, conflict detection, and historical tracking of facts, decisions, and observations.
    17
    AGPL 3.0
  • A
    license
    A
    quality
    B
    maintenance
    A personal memory MCP server that ingests AI agent conversation logs from multiple platforms into a searchable PostgreSQL+pgvector database, enabling cross-session recall of past reasoning and decisions.
    6
    MIT
  • F
    license
    -
    quality
    C
    maintenance
    A personal memory MCP server that stores and retrieves conversation memories, enabling AI agents to recall past discussions, promises, and preferences using natural language.

View all related MCP servers

Related MCP Connectors

View all MCP Connectors

Latest Blog Posts

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/ksh00500/personal-brain-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server