Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.ipezygj/agent-guard

PYPI · AGENT-TRIPWIRE · SCANNED SEP 24

Safety checks an agent runs before it acts: package malware, destructive command, secret leak.

Available components

pypi · agent-tripwire 16
0 this week 16 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security50
  • No malware found by supply-chain analysis.Pass
  • Known CVEs could not be checked: the version this server declares is not published in its registry.Unverified
  • Install-script risk not yet assessed.Unverified
  • Dependency health could not be checked: the version this server declares is not published in its registry.Unverified
Provenance & Transparency6
Schema Quality & AI Usability0
  • Schema quality not yet verified: our sandbox could not run this package, so we have no schema to assess.Unverified
Stability & Change Management0
  • Stability not yet verified: our sandbox could not run this package, so we have no schema to compare.Unverified
Tool Coverage0
  • Tool coverage not yet verified: our sandbox could not run this package, so we have no tool definitions to assess.Unverified
Tool Safety0
  • Tool safety not yet verified: our sandbox could not run this package, so we have no tool text to scan.Unverified
Capabilities0
  • Protocol version not yet verified: our sandbox could not run this package, so we never saw its MCP handshake.Unverified

Unverified: 5 categories

Categories scored 0 because our sandbox could not run this package, so we have no schema for these checks to read. That is a gap on our side rather than a finding about the package, and we only credit what we can confirm, so the score stands at 0 until we can run it. How we score packages →

Install

How do I install the io.github.ipezygj/agent-guard MCP server?

io.github.ipezygj/agent-guard runs locally as a PyPI package, launched with uvx agent-tripwire. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · agent-tripwire

# add to Claude Code
claude mcp add ipezygj-agent-guard -- uvx agent-tripwire
// .cursor/mcp.json
{
  "mcpServers": {
    "ipezygj-agent-guard": {
      "command": "uvx",
      "args": [
        "agent-tripwire"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "ipezygj-agent-guard": {
      "command": "uvx",
      "args": [
        "agent-tripwire"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add ipezygj-agent-guard -- uvx agent-tripwire
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ipezygj-agent-guard": {
      "type": "local",
      "command": [
        "uvx",
        "agent-tripwire"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add ipezygj-agent-guard --command uvx --arg agent-tripwire
# ~/.hermes/config.yaml
mcp_servers:
  ipezygj-agent-guard:
    command: "uvx"
    args: ["agent-tripwire"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "ipezygj-agent-guard": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "agent-tripwire"
      ]
    }
  }
}
# add to Vellum
assistant mcp add ipezygj-agent-guard -t stdio -c uvx -a agent-tripwire
// mcp.json
{
  "mcpServers": {
    "ipezygj-agent-guard": {
      "command": "uvx",
      "args": [
        "agent-tripwire"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 26 Aug 26 16
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 11 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 10 Aug 26 0
    • Source repository: pass → fail ▼ security
  • 2 Aug 26 0
    • Malware scan: unverified → pass ▲ security
  • 1 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 31 Jul 26 0
    • Malware scan: pass → unverified ▼ security
  • 28 Jul 26 0
    • Schema quality: Schema quality not yet verified: our sandbox run of this package did not complete, so we have no schema to assess. functional
    • Tool coverage: Tool coverage not yet verified: our sandbox run of this package did not complete, so we have no tool definitions to assess. functional
  • 26 Jul 26 0

    First indexed and scored.

    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 24 Sept 2026 · Analysed pypi/agent-tripwire@0.2.1

Provenance Version not published

The package exists but this version is not published, so there is no artifact to attest.

Result Version not published
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

MCP tools

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tools for package channels are captured by running the package in an isolated sandbox. Our sandbox could not run this package, so no tool list has been captured. That is a gap on our side, not a finding about the package.

Common questions

What is the io.github.ipezygj/agent-guard MCP server?

io.github.ipezygj/agent-guard is an MCP server listed in the public MCP registry as io.github.ipezygj/agent-guard. Safety checks an agent runs before it acts: package malware, destructive command, secret leak. This page covers its PyPI package (agent-tripwire).

Is the io.github.ipezygj/agent-guard MCP server safe to use?

io.github.ipezygj/agent-guard scores 16 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

Is the io.github.ipezygj/agent-guard MCP server still maintained?

io.github.ipezygj/agent-guard is still listed as active in the MCP registry. We last reached this channel on 24 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.