schemabrain
AI 代理与数据库之间的信任和智能层。架构上只读,语义知识图谱 + 审计日志,MCP 原生。
The trust and intelligence layer between AI agents and your database. Read-only by architecture, semantic knowledge graph + audit log, MCP-native.
怎么安装
git clone https://github.com/Arun-kc/schemabrain ~/.claude/skills/schemabrain 简介
Give them SchemaBrain instead — a read-only trust and intelligence layer where the agent never writes SQL, PII is refused before the query runs, and every call lands in a tamper-evident audit log. SchemaBrain compiles every query from definitions you control — no path from a prompt to raw SQL at your database. Three guarantees that close the trust gap between AI agents and your database: **Read-only by architecture** — twelve MCP tools, none of which can write. No execute() tool, no query() tool, no path from agent prompt to a write at your database. **PII-aware refusal at retrieval** — PII ta…
推荐参考
信息
- 协议
- Apache-2.0
- 语言
- Python
- GitHub 星标
- 9
- 月下载
- –
- 最近更新
- 2026-08-24
- 创建于
- 2026-05-10
基础安全检查
- 检查结果
- curated 收录但无 npm 包/安装命令
- 收录来源
- curated:punkpeye/awesome-mcp-servers
- 主题标签
- agent-tools, agent-trust, agentic-ai, ai-agents, ai-security, audit-log, claude, database-security, knowledge-graph, llm, mcp, mcp-server, model-context-protocol, pii-protection, postgresql, python, schema-intelligence, semantic-firewall, semantic-layer
同类推荐
hindsight
vectorize-io/hindsight/tree/main/hindsight-integrations/coding-agents
Hindsight:会学习的 Agent 长期记忆系统,自动召回/保存、知识页、深度反思与按仓库隔离的记忆银行。
firecrawl-mcp-server
firecrawl/firecrawl-mcp-server
🔥 官方Firecrawl MCP服务器 - 为Cursor、Claude及任何其他LLM客户端添加强大的网页抓取和搜索功能。
dsh-mnemon
omdsh-dev/dsh-mnemon
由 Mnemon 驱动的 DeepSeek Harness(DSH)跨 Agent、本地优先的持久记忆插件。它可在支持 Mnemon 的 Agent 之间共享长期记忆,并提供运行时记忆、可检索项目档案、语义召回、知识图谱和 Sidebar UI。
get-shit-done
gsd-build/get-shit-done
由 TÂCHES 开发的轻量且强大的元提示、上下文工程和规格驱动开发系统,适用于 Claude Code。