---
id: deepagents-cli
version: "0.2.2"
license: MIT
license_treatment: permissive
maintenance: active
---

# deepagents-cli — Deployment tooling for Deep Agents - bundle, run, and ship agents to LangGraph Platform.

License: permissive · Maintenance: active · Downloads: 82.3K/mo

## What it is and what it does

deepagents-cli is a command-line deployment toolkit for LangChain's Deep Agents framework. It provides scaffolding, configuration, and deployment commands to bundle agent definitions (agent.json, tools.json, skills, subagents) and ship them to the LangGraph Platform. The package depends on deepagents, langchain, langgraph, langgraph-sdk, langsmith, httpx, and python-dotenv—all core components of the LangChain ecosystem.

The tool's main workflow is: initialize a project structure with `deepagents init`, register any Model Context Protocol (MCP) servers your agent will use via `deepagents mcp-servers add`, configure tools and backend settings in the project files, then deploy with `deepagents deploy`. It supports both stateless and sandbox backends, with sandbox scope and policy configuration. The package is actively maintained, has no known vulnerabilities, and targets Python 3.11–3.14.

Use it for:

- Scaffold and deploy a new LangChain Deep Agent to the LangGraph Platform without manual API calls.
- Register and manage MCP servers in a workspace to provide tools for multiple agents.
- Configure agent backend behavior (state vs. sandbox) and set sandbox policies for isolated execution.
- List, inspect, and delete agents or MCP servers already deployed in a workspace.
- Integrate agent deployment into CI/CD pipelines via CLI commands.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Command-line tool for scaffolding, configuring, and deploying LangChain Deep Agents to the LangGraph Platform, with support for MCP server registration and sandbox backend configuration.

Yes, if you are already using LangChain and LangGraph and have access to the Managed Deep Agents private preview. The tool significantly reduces friction for agent project scaffolding and deployment. If you do not yet have LangSmith API access to the preview, installation alone will not be useful until that access is granted.

## Install

pip install deepagents-cli
uv add deepagents-cli
poetry add deepagents-cli

## Installing deepagents-cli

Before you install: Low install friction with a pure-Python wheel. Active maintenance (last commit 2026-08-14) and recent release cycle. Depends on langchain, langgraph, and langsmith ecosystem packages, which are standard in the LLM agent space.

License in practice: MIT license permits free use, modification, and distribution with minimal restrictions—suitable for both commercial and open-source projects.

Quickstart:

# Install via uv
uv tool install deepagents-cli

# Set your LangSmith API key
export LANGSMITH_API_KEY="your-key-here"

# Scaffold a new agent project
deepagents init my-agent

# Deploy to LangGraph Platform
cd my-agent && deepagents deploy

Requires a LangSmith API key with access to the Managed Deep Agents private preview (waitlist-gated); Python 3.11 or later.

Verify before relying:

- Whether the private preview waitlist remains the only path to use this tool, or if access has broadened since the fact sheet was generated.
- Whether MCP server registration and agent deployment work offline or require continuous LangSmith connectivity.

## Package facts

- License: MIT (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 82.3K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

langchain agent deployment cli, deep agents project scaffolding, mcp server registration tool, langgraph platform deployment, agent configuration management, managed deep agents cli, agent sandbox configuration, langchain-ecosystem, agent-deployment, mcp-integration

[View on SkillFed](https://skillfed.io/packages/deepagents-cli) · [View on PyPI](https://pypi.org/project/deepagents-cli/)