Skip to content
mcp/harbor
LangChain

safeagent for LangChain

io.github.azender1/safeagent

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

client:LangChain transport:stdio runtime:pypi

Install safeagent in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "safeagent": {
            "transport": "stdio",
            "command": "uvx",
            "args": ["safeagent-exec-guard"],
        }
})

tools = await client.get_tools()

get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs

safeagent in other clients

safeagent MCP server