Install Safe Agent in Claude Code
claude mcp add safe-agent -- uvx safe-agent-mcp{
"mcpServers": {
"safe-agent": {
"command": "uvx",
"args": [
"safe-agent-mcp"
]
}
}
}Frequently asked questions
What does the Safe Agent MCP server do?
Audit API-key privileges, check idempotency patterns, explain AI-agent guard patterns. Read-only.
Is the Safe Agent MCP server free?
Yes, most likely. Open source and no paid account or API key is mentioned in the listing. Check the provider for current pricing.
Does Safe Agent run locally or remotely?
Local. Runs on your machine (stdio). You install it with npx, uvx, Docker or from source.
How do I add Safe Agent to Claude Code?
Run: claude mcp add safe-agent -- uvx safe-agent-mcp
More ai agents & coding agents MCP servers
View allSAGE
pragnakar/Project_Sage
LLM-native optimization solver: LP, MIP, portfolio & scheduling via HiGHS/OR-Tools.
SaC — Software as Content
Software-As-Content/software-as-content-sdk
Give your AI agent the ability to respond with live, interactive apps that evolve.
SalesMap
solozerolabs/salesmap-plugin
Checked buying signals and ranked lead lists for your agent. Never contacts anyone.
Runhooks
runhooks/runhooks-mcp
Schedule and manage recurring and one-off HTTP jobs on Runhooks from your AI agent.
Sanctionwise
qinisolabs/sanctionwise
Verified UK sanctions screening for AI agents — official FCDO UK Sanctions List, not guesses.
Rubric py
0xsims/rubric-mcp-py
Attest agent decisions and verify records on a public ledger. Evidence, not just data.