Skip to content
mcp/harbor
Verified official

safeagent MCP

v0.1.22

io.github.azender1/safeagent

Exactly-once execution guard for AI agents. Prevents duplicate payments and webhooks on retry.

transport:stdio runtime:pypi
View source

Target client

run in your project directory 

claude mcp add safeagent -- uvx safeagent-exec-guard

Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs

This listing does not declare its tools. Connect the server and your client will discover them on the handshake.