MCP server
Agent Guard
io.github.ipezygj/agent-guard
Checked 26 Oct 2026, 08:31 UTC · Removed from its registry; checked against OSV.dev; never run by us
Safety checks an agent runs before it acts: package malware, destructive command, secret leak.
Runs on your computerRemoved from its registry: not on PyPI (version 0.2.1)
At a glance
- Type
- MCP server
- Publisher
- Not verified
- Status
- Runs on your computer
- Sets up in
- Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code
- Last checked
- 26 Oct 2026, 08:31 UTC
Connect it to your agent
Claude Code
claude mcp add agent-guard -- uvx agent-tripwire@0.2.1
Claude Desktop
{"mcpServers":{"agent-guard":{"command":"uvx","args":["agent-tripwire@0.2.1"]}}}
Codex (config.toml)
[mcp_servers.agent-guard] command = "uvx" args = ["agent-tripwire@0.2.1"]
Gemini CLI
{"mcpServers":{"agent-guard":{"command":"uvx","args":["agent-tripwire@0.2.1"]}}}
Cursor
{"mcpServers":{"agent-guard":{"command":"uvx","args":["agent-tripwire@0.2.1"]}}}
VS Code
{"servers":{"agent-guard":{"type":"stdio","command":"uvx","args":["agent-tripwire@0.2.1"]}}}
Runs on your computer with your permissions: check the package and its source before installing.
Browse
Related MCP servers
- DepScout
Scan packages and lockfiles (npm, PyPI, Go, Maven, Cargo, NuGet) for vulnerabilities and malware. - KarmaDue
Pre-install safety check for agents: known traps, tested fixes, malware reports. No account. - HeyClaude — Claude & AI workflow directory
Search the HeyClaude directory of Claude Code agents, MCP servers, skills, and tools. - DropEngine x402 Agent Services
AI Agent Utility Layer for agent safety, web monitoring, crypto research and tool discovery. - Diogenes Agent Guardrails & Sandbox MCP
Autonomous agent guardrails, bash sandboxing, MCP rugpull diffing & prompt firewalls. - VITNA – Containment for rogue AI agents
Guard wraps stdio MCP servers: risky calls wait for a person; no answer, no run. Remote: cooperative - presign-guard
Safety checks before an AI agent pays, signs or buys (MCP) - Agent Tested
Hands-on agent test results for small AI tools and MCP servers, live AI outages, malware name check.
Badge for your README
[](https://aptlynx.net/servers/io.github.ipezygj/agent-guard)
Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents