sidclawhq/mcp-guard

View on GitHub ↗

Stop AI agents from doing dangerous things through MCP. Wraps any MCP server with allow/block/hold-for-approval guardrails.

3 ★0 forksTypeScriptUpdated 1mo ago

Topics

agentai-governanceai-safetyapprovalclaudecursorguardrailsmcpmcp-servermodel-context-protocolpolicytool-call
Stars
3★
Forks
0
Language
TypeScript
License
Apache-2.0
Created
2026-04-06
Last push
2026-07-15