Safeagent MCP Server

by azender1 Your server? Claim it

local only

Safeagent runs on your own machine — the client starts it, so there is no endpoint to ping. 134 installs a week from pypi. Last commit 7 Oct 2026.

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

Installs per day peak 138 · avg 30 · -21% w/w

a month agotoday

134

Installs / week

pypi · safeagent-exec-guard

Stars

6 open issues

7 Oct 2026

Last commit

from GitHub

Apache-2.0

License

Python

What the code does

We read the source, 3 d ago · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Runs an external command evidence/crewai-retry-ab-v3/parent.py:124, evidence/stripe-boundary-v1/run_fixture.py:75

    proc = subprocess.Popen(

Builds a file path from a variable control/v15/mutants/generate_mutants.py:203

    with open(os.path.join(PACKAGE_ROOT, name)) as f:

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

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 safeagent -- uvx safeagent-exec-guard

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

{
  "mcpServers": {
    "safeagent": {
      "command": "uvx",
      "args": [
        "safeagent-exec-guard"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.safeagent]
command = "uvx"
args = ["safeagent-exec-guard"]

.cursor/mcp.json

{
  "mcpServers": {
    "safeagent": {
      "command": "uvx",
      "args": [
        "safeagent-exec-guard"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "safeagent": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "safeagent-exec-guard"
      ]
    }
  }
}

Alternatives to Safeagent

same job, measured the same way

402shield

by mitchsingh

x402 payment security and pre-execution transaction risk screening for autonomous AI agents.

1 tools answering

Trust

by agntor

Trust layer for AI agents: identity, guard, redact, escrow, and x402 payments.

50 installs/wk local only

Paddock

by paddock

Pre-payment verification for AI agents.

13 tools answering

Agentpay Sentinel MCP

by rumblingb

Security guardrails for AI agent payments

local only

Azeth Protocol

by azeth-protocol

Smart accounts, x402 payments, on-chain reputation, and service discovery for AI agents

91 installs/wk local only

Hookjar

by comiza

Public webhook inboxes for agents. Receive OAuth redirects, payment callbacks and CI notifications.

6 tools answering

SDK

by mnemopay

Trust OS for AI agents: governed memory, payments, reputation, approvals, and audit evidence.

local only

Secant Agent Research Pack

by jnilrac

Paid MCP web research for agents: search, extraction, citations, and x402 payment discovery.

6 tools answering

Safeagent — questions

Answers built from our own checks of this server.

Why is there no uptime for Safeagent?

Safeagent 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 safeagent-exec-guard was installed 134 times last week.

How do I connect Safeagent?

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 safeagent-exec-guard straight from pypi; nothing to host, nothing to sign up for.

How many people use Safeagent?

The pypi package safeagent-exec-guard was installed 134 times in the last week. Week over week that is -21%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Safeagent open source?

Yes — it is published under the Apache-2.0 licence, written in Python, 8 stars on GitHub and 6 open issues. The source link is on this page, so you can read exactly what it does with your data before you connect it.