I scanned my own laptop: 6 AI agents, 14 MCP servers, 12 unpinned, 5 plaintext keys

说明与用途

在笔记本电脑上运行了六个 AI 代理，使用了 14 个 MCP 服务器，其中大多数未锁定版本，API 密钥以明文存储。扫描后，将包版本固定，密钥迁移到安全存储，并添加策略门控以限制敏感路径。

问题

Multiple AI agents on a single laptop were using unpinned MCP servers and storing API keys in plaintext, exposing them to supply‑chain attacks and accidental leakage.

结果

After remediation, the laptop’s AI agents no longer expose unpinned MCP packages or plaintext API keys, reducing supply‑chain and credential leakage risk.

工作流

• 1. Run a read‑only scanner (pod scan) to inventory all MCP servers and secret locations.
• 2. Identify unpinned packages and plaintext tokens.
• 3. Pin MCP package versions (e.g., npx -y [email protected]).
• 4. Remove tokens from config files and store them in a keychain or secret manager.
• 5. Implement a policy layer that denies access to sensitive paths, blocks secret output, and hash‑chains tool calls for audit.

证据

12 of the 14 MCP servers are unpinned

来源

five API keys sit in plaintext in agent config files

来源

Pin versions. Move secrets to a keychain. Put a gate in front of tool calls.

来源