Conduct AI MCP Server

by sseshachala Your server? Claim it

local only

Conduct AI runs on your own machine — the client starts it, so there is no endpoint to ping. 1 719 installs a week from pypi. Last commit 13 Aug 2026.

List agents, trigger workflows, and enforce team AI policies with ConductGuard.

Installs per day peak 1 945 · avg 397 · +14% w/w

a month agotoday

1 719

Installs / week

pypi · conduct-cli

Stars

0 open issues

13 Aug 2026

Last commit

from GitHub

—

License

Python

What the code does

We read the source, 2 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.

File ships in the package but is absent from the source [пакет] src/conduct_cli/hooks/copilot.py:1, [пакет] src/conduct_cli/credential_lock.py:1, [пакет] src/conduct_cli/guard_commands/__init__.py:1 и ещё 56

этот файл ставится пользователю, но в репозитории его нет

Runs a command on install [пакет] package.json:1

setup.py: выполняет код при установке пакета

Runs an external command .claude/.claude/hooks/booster-gate.py:37, .claude/.claude/hooks/booster-grep-nudge.py:24, .claude/.claude/hooks/booster-route.py:22 и ещё 20

    r = subprocess.run(

Builds a file path from a variable src/conduct_cli/paxel.py:618, [пакет] src/conduct_cli/paxel/px_sources.py:249

    msg_dir = os.path.join(OPENCODE_DIR, "storage", "message", sid)

Reads files and sends them to the network src/conduct_cli/hooks/session_start.py:129, src/conduct_cli/main.py:318, [пакет] src/conduct_cli/hooks/session_start.py:132

            dirs = sorted(claude_projects.iterdir(), key=lambda d: d.stat().st_mtime, reverse=True)

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 conduct-cli -- uvx conduct-cli

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

{
  "mcpServers": {
    "conduct-cli": {
      "command": "uvx",
      "args": [
        "conduct-cli"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.conduct-cli]
command = "uvx"
args = ["conduct-cli"]

.cursor/mcp.json

{
  "mcpServers": {
    "conduct-cli": {
      "command": "uvx",
      "args": [
        "conduct-cli"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "conduct-cli": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "conduct-cli"
      ]
    }
  }
}

Alternatives to Conduct AI

same job, measured the same way

Clickup

by mcparmory

Manage tasks, lists, checklists, comments, and project workflows

222 installs/wk local only

Yieldagentx402

by fabio662

Policy-gated x402 MCP for agent workflows with TEE receipts, 18 tools, and no custody.

61 installs/wk local only

Harflow MCP

by harflow-dev

Dispatch coding tasks to local headless agents with persistent history and workflows.

3 783 installs/wk local only

Stackguide MCP

by taimiralain

Dynamic context loading for AI assistants with TDD workflow and AST analysis

182 installs/wk local only

Stackguide MCP

by isucorp-taimiralain

Dynamic context loading for AI assistants with TDD workflow and AST analysis

local only

Wever Labs Agentic Rails

by weverlabs

Agentic rails for complex workflows with receipts, fees, and MCP tool access.

5 tools answering

Task Graph MCP

by oortonaut

MCP server for agent task workflows with phases, prompts, gates, and multi-agent coordination

local only

BugBug

by bugbug-io

BugBug workflows for AI agents

answering

Conduct AI — questions

Answers built from our own checks of this server.

Why is there no uptime for Conduct AI?

Conduct AI 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 conduct-cli was installed 1 719 times last week.

How do I connect Conduct AI?

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 conduct-cli straight from pypi; nothing to host, nothing to sign up for.

How many people use Conduct AI?

The pypi package conduct-cli was installed 1 719 times in the last week. Week over week that is +14%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Conduct AI open source?

We cannot say either way: written in Python and 0 stars on GitHub, but we could not determine the licence, and without one the code is not open source by default.