Embodify MCP server

Embodify <!-- mcp-name: io.github.YidaYang/embodify -->

Give your agent a body.

Your best embodied agent is your favorite agent.

Embodify lets the agent you use every day — Claude Code, Codex or any other MCP-capable agent — see and control robots directly, and keeps everything else that makes it yours. Bring in frontier models with embodied manipulation skills, such as GPT-6 Astra and Claude Opus 5.5, and let your AI companion step into the physical world.

中文 · One-line setup · Backends · For research · Skills · Roadmap

First release (0.1.0a1). Supports LIBERO and RoboDojo today; support for

RoboTwin and the LeRobot SO-101 arm is coming soon.

Why Embodify

Most embodied agents are built from scratch: a dedicated harness wraps a model, hands it a fixed set of robot actions, and nothing else. The agent you use every day already has what those harnesses lack:

use. You can ask how it is going, step in, correct it, or teach it mid-task.

• Context and memory. It manages long sessions and remembers across them.
• It knows you. Your preferences, your projects, your lab setup.
• It talks with you in the terminal, IDE, desktop app or chat you already

web and reads papers.

• It has a computer. It writes and runs code, uses its tools, searches the

Embodify keeps all of that and adds a body. Install the plugin and your agent gets robot observation and control tools over MCP — a protocol it already uses for everything else — plus skills that teach it how to operate robots and how to achieve recursive self-improvement (RSI) from its own experience.

Why "best"

A general agent with a body is stronger than a harness that can only move a robot:

write a script; when it needs a fact it can search; when it needs perception it can run a model.

1. It can think with tools, not only act. When a task needs geometry it can

what it already tried. Mature agents manage context and memory well.

1. It keeps track. Long-horizon manipulation fails when the agent forgets

guidance when it gets stuck, and remembers your corrections next time.

1. It works with you. It asks you when a task is ambiguous, takes your

ordinary MCP tool calls, the same shape as every other tool the agent uses.

1. It controls robots in its native language. Robot control arrives as

frontier embodied manipulation skills, such as GPT-6 Astra and Claude Opus 5.5, and every model upgrade makes your robot better, with no retraining.

1. It builds on frontier embodied models. Your agent runs on models with

lessons into rules and rules into new skills, and gets better the more it works.

1. It improves itself recursively. It turns every episode into lessons,

takes on new tasks without training: describe a task in plain language (zero-shot), show it a few examples (few-shot), or put instructions, demonstrations and past experience in its context (in-context learning, ICL).

1. Zero-shot, few-shot and in-context learning come easily. A general agent

What's inside

Embodify is an agent plugin with two parts, and installing the plugin gives your agent both:

Shortened. The full README is on GitHub.