Safe Agent MCP Server

by naoanao Your server? Claim it

local only

Safe Agent MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 142 installs a week from pypi. Last commit 30 Oct 2026.

Audit API-key privileges, check idempotency patterns, explain AI-agent guard patterns. Read-only.

Installs per day peak 333 · avg 19 · -68% w/w

a month agotoday

142

Installs / week

pypi · safe-agent-mcp

Stars

0 open issues

30 Oct 2026

Last commit

from GitHub

MIT

License

Python

Nothing serious here today

Today is the operative word: we check Safe Agent MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add safe-agent-mcp -- uvx safe-agent-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "safe-agent-mcp": {
      "command": "uvx",
      "args": [
        "safe-agent-mcp"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.safe-agent-mcp]
command = "uvx"
args = ["safe-agent-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "safe-agent-mcp": {
      "command": "uvx",
      "args": [
        "safe-agent-mcp"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "safe-agent-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "safe-agent-mcp"
      ]
    }
  }
}

Alternatives to Safe Agent MCP

same job, measured the same way

Regex

by rog0x

Regex test, explain, replace patterns for AI agents

46 installs/wk local only

AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks

by agenttrust-ai

Check an AI agent endpoint before you call it: read-only, no API key, returns a trustDecision.

6 tools answering

Recoup: AI agent refund audit

by recoupaudit

Checks AI support agent refunds against Shopify and Stripe. Read-only pricing, fit and estimates.

4 tools answering

Base Intel MCP

by datakoot

Read-only on-chain intel for AI agents on Base: balances, tokens, gas, tx status. No API keys.

5 tools answering

Rls Check

by muhandis-online

Read-only Supabase RLS check: explains in Arabic which tables anyone can read or change. No keys.

122 installs/wk local only

Agent Bay

by sobuk2500-max

Public board of agent questions, attempts and verified results. Read-only, no API key.

7 tools answering

AITeamGuide AI agent prices

by aiteamguide

Read-only lookups of public AI agent pricing, free plans and source links. No API key.

4 tools answering

klanex

by chrassy

Reliable async execution for agent tool calls: schema gating, retries, idempotency, audit trail.

38 installs/wk 6 tools answering

Safe Agent MCP — questions

Answers built from our own checks of this server.

Why is there no uptime for Safe Agent MCP?

Safe Agent MCP runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package safe-agent-mcp was installed 142 times last week.

How do I connect Safe Agent MCP?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls safe-agent-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use Safe Agent MCP?

The pypi package safe-agent-mcp was installed 142 times in the last week. Week over week that is -68%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Safe Agent MCP open source?

Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.