agentmods.dev

helix-agent-lab

helix-agent-lab is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from munch2u-a11y/Helix-AGI. Its token cost is not measured, scanned A, original, Apache-2.0.

An MCP server setup that starts the Helix agent lab with Python and passes it two configured data locations. MCP is a way for an AI coding tool to call an external program.

In plain words
What is it for?
It is for launching the Helix agent lab from an MCP-compatible coding tool. The description does not say what experiments or commands the lab provides.
Why use it?
It provides the connection details needed to run the Helix agent lab instead of requiring those settings to be assembled manually.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it. Also seen: listed in a Claude config.

not rated 61repo +1 today A scan tokens not measured original Apache-2.0

Good fit It is for launching the Helix agent lab from an MCP-compatible coding tool. The description does not say what experiments or commands the lab provides.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/munch2u-a11y/helix-agi/helix-agent-lab-helix-agent-lab

Installing this writes the configuration, not the program: `python` runs a file from the repository, so clone it first and make the path in the command match where you put it.

View source ↗ munch2u-a11y/Helix-AGI
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/munch2u-a11y/Helix-AGI

Installing this writes the configuration, not the program: `python` runs a file from the repository, so clone it first and make the path in the command match where you put it.

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for helix-agent-lab

README.md
[![agentmods](https://agentmods.dev/badge/mcp/munch2u-a11y/helix-agi/helix-agent-lab-helix-agent-lab/github.svg)](https://agentmods.dev/mcp/munch2u-a11y/helix-agi/helix-agent-lab-helix-agent-lab)
Your own site
<a href="https://agentmods.dev/mcp/munch2u-a11y/helix-agi/helix-agent-lab-helix-agent-lab"><img src="https://agentmods.dev/badge/mcp/munch2u-a11y/helix-agi/helix-agent-lab-helix-agent-lab/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for helix-agent-lab

Your own site · 80×15
<a href="https://agentmods.dev/mcp/munch2u-a11y/helix-agi/helix-agent-lab-helix-agent-lab"><img src="https://agentmods.dev/badge/mcp/munch2u-a11y/helix-agi/helix-agent-lab-helix-agent-lab.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

helix-agent-lab scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/helix-agent-lab/.mcp.json · 12 lines

What it actually says

{
  "helix-agent-lab": {
    "command": "python",
    "args": [
      "${PLUGIN_ROOT}/scripts/start_server.py"
    ],
    "env": {
      "HELIX_AGENT_LAB_ROOT": "${PLUGIN_ROOT}",
      "HELIX_AGENT_LAB_DATA": "${PLUGIN_DATA}"
    }
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 12 lines scan A d524b0694093

Subscribe to this mod's changes

helix-agent-lab is an MCP server published in the GitHub repository munch2u-a11y/Helix-AGI (61 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-12.

Building agentsagentic-ai-architectureagiaiai-agentai-agenticai-agents-automation
Related

Other mcp servers, from other repositories

Slack

Model Context Protocol (MCP) server for Slack Workspaces. This integration supports both Stdio and SSE transports, proxy settings and does not require any permissions or bots being created or approved by Workspace admins. Runs locally from the @kazuph/mcp-slack npm package. Needs 1 environment variable to run.

monkilabs/opencastle · not measured

Linear

A Linear MCP server for interacting with Linear's API. Runs locally from the @mseep/linear-mcp npm package.

monkilabs/opencastle · not measured

arifos

Constitutional AI kernel with 13 MCP tools, 888JUDGE verdict pipeline, and VAULT999 ledger. Remote server at arifos.arif-fazil.com.

ariffazil/arifOS · not measured

arifos-mcp

Open-source governance decision point for AI agent actions. Evaluates proposed actions against constitutional policy floors (F1-F13) and returns SEAL/HOLD/SABAR/VOID verdicts before execution. 8 MCP tools, append-only audit ledger (VAULT999), Streamable HTTP transport. Designed for regulated AI deployment. Runs…

ariffazil/arifOS · not measured

chrome-devtools

Lets the agent inspect and automate a live Chrome instance through the DevTools protocol: performance traces, network, console. Runs locally from the chrome-devtools-mcp npm package.

monkilabs/opencastle · not measured

docs-langchain

MCP server "docs-langchain", hosted remotely at docs.langchain.com, as configured in langchain-ai/langchain.

langchain-ai/langchain · not measured