Conduct Cli

Name: Conduct Cli
Author: sseshachala

by sseshachalacommunityv0.6.10

A CLI for Conduct AI that lets users authenticate, browse playbooks, create projects, install agents, and run test triggers on those agents. It also supports ConductGuard policy synchronization and exposes MCP tools for checking, syncing, and inspecting guard policy status.

From the registry: List agents, trigger workflows, and enforce team AI policies with ConductGuard.

GitHub Repository

Install & configure

Prerequisites

required
Install conduct-cli
Install the Python package that provides the MCP server executables `conduct-mcp` and `conductguard-mcp`.
```
$ pip install conduct-cli
```
required
Authenticate with Conduct AI
Run `conduct login` once to save Conduct API credentials to `~/.conduct/config.json`. `conduct-mcp` reads credentials from this file.
```
$ conduct login --server https://api.conductai.ai --api-key <your-api-key> --workspace <your-workspace-id>
```
https://conductai.ai
required
Get a ConductGuard member token
For `conductguard-mcp`, obtain a member token from Settings → API Keys in the Conduct AI dashboard.
https://conductai.ai

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `conduct-cli` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install conduct-cli** — Install the Python package that provides the MCP server executables `conduct-mcp` and `conductguard-mcp`. Run: `pip install conduct-cli`
- **Authenticate with Conduct AI** — Run `conduct login` once to save Conduct API credentials to `~/.conduct/config.json`. `conduct-mcp` reads credentials from this file. Run: `conduct login --server https://api.conductai.ai --api-key <your-api-key> --workspace <your-workspace-id>` (https://conductai.ai)
- **Get a ConductGuard member token** — For `conductguard-mcp`, obtain a member token from Settings → API Keys in the Conduct AI dashboard. (https://conductai.ai)

Canonical MCP server config (stdio transport):
- command: `conductguard-mcp`
- args: ["--team","<your-workspace-id>","--token","<your-member-token>"]

Note: This README documents two MCP servers: `conduct-mcp` and `conductguard-mcp`. Canonical stdio config can also be `command: conduct-mcp` with `args: []`; it uses credentials previously stored by `conduct login` in `~/.conduct/config.json` and requires no env vars. The extracted config above uses `conductguard-mcp` because the README provides its full canonical command/args shape explicitly.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: This README documents two MCP servers: `conduct-mcp` and `conductguard-mcp`. Canonical stdio config can also be `command: conduct-mcp` with `args: []`; it uses credentials previously stored by `conduct login` in `~/.conduct/config.json` and requires no env vars. The extracted config above uses `conductguard-mcp` because the README provides its full canonical command/args shape explicitly.