MCP-warden local credential broker so AI agents never see your secrets
I got tired of pasting GitHub PATs, Stripe keys and DB passwords into Claude Code / Cursor MCP configs. One prompt injection or a leaked chat and they’re gone. So I built mcp-warden — a local-first credential broker for the Model Context Protocol. How it works: • You store the secret once in the OS keychain • You define scoped presets (e.g. github-read, stripe-charges) • The agent calls high-level tools (proxy_http, ssh_exec, db_query) • mcp-warden injects the credential server-side and returns
阅读原始来源
来源记录
指标快照
points · 1 votes
2026-10-26 18:00:30.153Z
cumulative since publication
研究分析
来源记录
来源描述：I got tired of pasting GitHub PATs, Stripe keys and DB passwords into Claude Code / Cursor MCP configs. One prompt injection or a leaked chat and they’re gone. So I built mcp-warden — a local-first credential broker for the Model Context Protocol. How it works: • You store the secret once in the OS keychain • You define scoped presets (e.g. github-read, stripe-charges) • The agent calls high-level tools (proxy_http, ssh_exec, db_query) • mcp-warden injects the credential server-side and returns
现有背景
来源票数: 1 votes (2026年10月26日 UTC; cumulative since publication)；前次同口径记录为 1（2026年10月26日 UTC），两个观测值不等于需求增长。 可供比较的近期同类记录：“Shotoku – local authorization layer for AI agents” (Hacker News, 2026年11月5日)；“Mistral Studio adds managed agents, workflows and apps” (Hacker News, 2026年11月5日)。主题相近仅用于导航，未核验其是否属于同一需求或独立证据。
研究状态
这条记录尚不能可靠归入主类，未生成商业或性能结论。
缺失证据
需要核验主要事件、受影响对象与原始证据。
下一步
阅读原文，明确它支持什么决策，再选择对应分析框架。