Deep Agents CLI — Deployment Tooling (Deprecated)

Warning

deepagents-cli is deprecated and no longer maintained. This is the final release. It is superseded by the managed-deepagents package and its mda CLI, which build, deploy, and run agents from a project directory with no local CLI infrastructure. See the Managed Deep Agents overview.

What to do: install the mda CLI and re-scaffold your project:

uv tool install managed-deepagents
mda init my-agent
cd my-agent
mda deploy

The mda CLI covers everything deepagents init / deploy / agents / mcp-servers did — project scaffolding, deployment, agent management, and MCP servers — against the Managed Deep Agents platform. See the quickstart and CLI reference.

The interactive coding agent (dcode) already lives in deepagents-code and is unaffected by this deprecation.

Install

uv tool install deepagents-cli

You'll need a LangSmith API key with access to the Managed Deep Agents private preview (waitlist). Export it before running any command, or put it in a repo .env or ~/.deepagents/.env:

export LANGSMITH_API_KEY="..."

Usage

# Scaffold a new project folder
deepagents init my-agent

# Register any MCP servers you intend to use (one-time, per workspace)
deepagents mcp-servers add --url https://tools.langchain.com \
                            --header X-Api-Key=$LANGSMITH_API_KEY \
                            --name Fleet

# init scaffolds an empty tools.json. Add tools that reference a registered
# MCP server's URL (otherwise the agent has no tools), e.g. the Fleet server
# registered above:
#   { "name": "read_url_content", "mcp_server_url": "https://tools.langchain.com",
#     "mcp_server_name": "Fleet", "display_name": "read_url_content" }

# Upsert the project as a managed agent on /v1/deepagents/*
cd my-agent && deepagents deploy

deepagents init scaffolds an empty tools.json, an example skill under skills/, and an example subagent under subagents/; edit or remove them to suit your agent. tools.json starts empty because every tool must reference an MCP server that is already registered in the workspace (deepagents mcp-servers add) — so a freshly scaffolded project deploys without first registering a server.

New agents default to the state backend. To opt into a managed sandbox, set agent.json's backend.type to sandbox and configure backend.sandbox_config.scope as thread or agent; sandbox_config can also include sandbox policy IDs and TTL fields. The CLI does not create or run sandboxes locally; sandbox lifecycle is handled by the Managed Deep Agents platform.

{
  "backend": {
    "type": "sandbox",
    "sandbox_config": {
      "scope": "thread",
      "policy_ids": ["policy-id"]
    }
  }
}

Project layout

my-agent/
  agent.json              # name, description, backend, runtime.model, permissions
  AGENTS.md               # system prompt
  tools.json              # tools the agent can call (optional)
  skills/<name>/SKILL.md  # frontmatter-tagged skills (optional)
  subagents/<name>/       # delegated subagent definitions (optional)

Other commands

deepagents agents list                  # list workspace agents
deepagents agents get <agent_id>        # show one agent
deepagents agents delete <agent_id>     # delete an agent

deepagents mcp-servers list                  # list workspace MCP servers
deepagents mcp-servers add --url URL          # register a server
deepagents mcp-servers get <id|name|url>      # show one server
deepagents mcp-servers tools <id|name|url>    # list a server's tools
deepagents mcp-servers update <id|name|url>   # update server URL or headers
deepagents mcp-servers delete <id|name|url>   # remove a server
deepagents mcp-servers connect <id|name|url>  # start OAuth for a server

get, update, delete, and connect accept an MCP server's id, exact name, or URL — a non-id value is resolved against mcp-servers list (URLs are matched ignoring case and trailing slash).

📖 Resources

CLI Documentation
Changelog
Source code
Deep Agents SDK — underlying agent harness
Deep Agents Code — coding agent
LangChain Academy — Comprehensive, free courses on LangChain libraries and products, made by the LangChain team.
Code of Conduct — community guidelines and standards

📕 Releases & Versioning

See our Releases and Versioning policies.

💁 Contributing

As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.

For detailed information on how to contribute, see the Contributing Guide.

Metadata

Release files for deepagents-cli 0.3.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for deepagents-cli 0.3.0
File	Size	Uploaded
deepagents_cli-0.3.0.tar.gz	318.7 kB	Aug 24, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for deepagents-cli 0.3.0
File	Interpreter	ABI	Platform	Reset
deepagents_cli-0.3.0-py3-none-any.whl 36.2 kB Aug 24, 2026	Python 3	none	any	Details

Total release size: 354.9 kB

Release files / deepagents_cli-0.3.0.tar.gz

Download URL	deepagents_cli-0.3.0.tar.gz
Size	318.7 kB
Tags	Source
SHA-256 checksum How to use checksums	`b1c561a4da87a1c2c263eae1c22306e729b69e0664d15cdc6ee9924154fde2b1`
BLAKE2b-256 checksum How to use checksums	`c8eecfe2e977a54016d13a80f9e584eff21bdb716f3b6e983bf0a5c5b47df5e0`
Upload date	Aug 24, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Release files / deepagents_cli-0.3.0-py3-none-any.whl

Download URL	deepagents_cli-0.3.0-py3-none-any.whl
Size	36.2 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`4766272f06ef3002f5ec3c0142cc1ecf1a80bb50ffe92d50677be59f290c9d0d`
BLAKE2b-256 checksum How to use checksums	`8a6ee434e61bff5a2f53565a885d576df49ffb9f1ee66260c30a1381177b2187`
Upload date	Aug 24, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`