Lets AI agents observe and control simulated or real robots through MCP-compatible tools and skills.
Also known as YidaYang/embodify, embodify-mcp
- Stars
- 5
- Tools
- 8
- Downloads, 30 days
- 263
- Latest version
- 0.1.0a2
- Last commit
- Oct 2, 2026
- License
- Apache-2.0
What is Embodify MCP?
Embodify lets AI agents observe and control simulated or real robots through MCP-compatible tools and skills. It exposes 8 tools, such as get_session_info, list_tasks, reset_task.
Summary generated from the project's README
About Embodify MCP server
Embodify provides a bridge that allows AI agents to interact with physical or simulated robotic hardware. By using the Model Context Protocol, it enables existing agents like Claude Code or Codex to observe environments through cameras and execute precise movements. The system works by providing an MCP server that exposes tools for robot control, such as moving end effectors, managing grippers, and coordinating multiple arms.
Developers can use this with various backends, including LIBERO and RoboDojo for simulation, or connect to remote servers via SSH or TCP. The setup is designed to work with frontier models that possess embodied manipulation skills, allowing the agent to maintain its own memory and context while gaining a physical presence. It includes specialized skills for managing an observe-act loop and building a profile of the robot hardware. This makes it a versatile tool for both general agent interaction and formal research into robotic manipulation.
What you can do with it
- 1Control simulated robotsAn agent can perform tasks in a virtual environment using the LIBERO or RoboDojo backends.
- 2Evaluate model manipulation skillsResearchers can use the platform to compare how different language models perform on standard benchmarks.
- 3Monitor robot actions liveUsers can watch a live video feed of the robot's progress and camera views in a web browser.
Written from the project's README. Every use case is checked against a quote from it.
How to install Embodify MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Embodify MCP in Claude Code
$ claude mcp add embodify -- uvx embodify-mcpInstall Embodify MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"embodify": {
"command": "uvx",
"args": [
"embodify-mcp"
]
}
}
}Install Embodify MCP in VS Code
.vscode/mcp.json
{
"servers": {
"embodify": {
"type": "stdio",
"command": "uvx",
"args": [
"embodify-mcp"
]
}
}
}Install Embodify MCP in VS Code CLI
$ code --add-mcp '{"name":"embodify","type":"stdio","command":"uvx","args":["embodify-mcp"]}'Install Embodify MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"embodify": {
"command": "uvx",
"args": [
"embodify-mcp"
]
}
}
}Install Embodify MCP in Codex
$ codex mcp add embodify -- uvx embodify-mcpInstall Embodify MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.embodify] command = "uvx" args = ["embodify-mcp"]
Install Embodify MCP in Gemini CLI
$ gemini mcp add -s user embodify uvx -- embodify-mcpInstall Embodify MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"embodify": {
"command": "uvx",
"args": [
"embodify-mcp"
]
}
}
}Embodify MCP tools 8
Detected from the READMEget_session_infolist_tasksreset_taskobservemove_relativeset_grippercontrol_armsstop_episode
| get_session_info | — | |
| list_tasks | — | |
| reset_task | — | |
| observe | — | |
| move_relative | — | |
| set_gripper | — | |
| control_arms | — | |
| stop_episode | — |
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachableyidayang/embodify is public and reachablegithub.com/yidayang/embodify ↗Pass
- Package names this repository as its sourceembodify-mcp names yidayang/embodify as sourcepypi.org/project/embodify-mcp/ ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for embodify-mcppypi.org/project/embodify-mcp/ ↗Pass
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-02github.com/yidayang/embodify ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from embodify-mcpPass
- No critical advisory in the package or its dependencies2 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model8 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubFirst 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:
- 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 use. You can ask how it is going, step in, correct it, or teach it mid-task.
- It has a computer. It writes and runs code, uses its tools, searches the web and reads papers.
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:
- It can think with tools, not only act. When a task needs geometry it can write a script; when it needs a fact it can search; when it needs perception it can run a model.
- It keeps track. Long-horizon manipulation fails when the agent forgets what it already tried. Mature agents manage context and memory well.
- It works with you. It asks you when a task is ambiguous, takes your guidance when it gets stuck, and remembers your corrections next time.
- It controls robots in its native language. Robot control arrives as ordinary MCP tool calls, the same shape as every other tool the agent uses.
- It builds on frontier embodied models. Your agent runs on models with 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.
- It improves itself recursively. It turns every episode into lessons, lessons into rules and rules into new skills, and gets better the more it works.
- Zero-shot, few-shot and in-context learning come easily. A general agent 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).
What's inside
Embodify is an agent plugin with two parts, and installing the plugin gives your agent both:
| Part | What it gives your agent |
|---|---|
MCP server (embodify-mcp, registered as embodify) |
Tools to list tasks, start an episode, observe cameras and robot state, move end effectors, open and close grippers, and coordinate two arms. |
| Skills | Know-how: running a careful observe–act loop, keeping a profile of the robot body and cameras, and learning from past episodes. More perception skills are coming soon. |
flowchart LR
A["Your agent<br/>Claude Code · Codex · …"] -- "MCP (stdio)" --> B["embodify-mcp<br/>episodes · budgets · logs"]
K["Embodify skills"] -. "loaded by" .-> A
B --> I["Backend interface"]
I --> L["LIBERO"]
I --> R["RoboDojo"]
I --> T["RoboTwin (WIP)"]
I --> H["SO-101 and other real robots (WIP)"]
I -. "SSH / TCP" .-> G["Remote server"]
The MCP server is the front end. Each simulator, benchmark or robot is a backend behind one small interface, so adding a new one does not change what the agent sees. Highlights:
- Works with any MCP host. No LLM calls inside; your agent keeps its own model, memory, skills and tools.
- One call, one motion. The control loop runs next to the simulator. Each action returns the actual displacement, remaining error, a stop reason and fresh camera images.
- Remote simulation. Run the simulator on your lab's GPU server over SSH
while the agent stays on your laptop. Heartbeats keep high-latency links
alive; if the link drops, the episode aborts cleanly and
reset_taskreconnects. - Fair evaluation. When you use Embodify to evaluate an agent's manipulation skills, task success is recorded for humans and never exposed to the agent.
- Live monitor and replay. Watch running episodes live in a browser, or replay past ones frame by frame.
Backends
| Backend | Robot | Status |
|---|---|---|
fake, fake-two-arm |
Kinematic diagnostic, one or two arms | ✅ Included, no simulator needed |
libero |
Franka Panda, 130 tasks in 5 suites | ✅ Included |
robodojo |
Dual ARX X5, all 54 simulation tasks | ✅ Included |
| RoboTwin | Dual-arm manipulation benchmark | 🚧 Coming soon |
| LeRobot SO-101 | Real robot: 5-DoF arm with gripper | 🚧 Coming soon |
remote |
Any backend above, on another machine | ✅ SSH or trusted TCP |
Coming soon: robot arms such as xArm, mobile manipulators, humanoids and dexterous hands. If there is a simulator or robot you would like us to support, open a GitHub issue with details about it. We welcome contributions of new backends.
For research
Embodify doubles as a testbed for the embodied manipulation abilities of language models and agent frameworks. Run GPT, Claude, Gemini, Qwen and other models, through Claude Code, Codex or your own agent framework, on the same simulated benchmarks with the same tools, and compare them directly.
- Standard benchmarks: LIBERO (130 tasks in 5 suites) and RoboDojo (54 tasks), with RoboTwin coming soon.
- Fair by design: task success is recorded for evaluators and never shown to
the agent, and
--lock-taskfixes the scene. - Controlled budgets: episode budgets and per-call step limits are configurable and logged.
- Complete records: tool calls, robot states and camera frames are saved for replay and analysis.
Typical studies include zero-shot robot manipulation by frontier models, comparisons of agent frameworks on the same model, the effect of skills and memory, and recursive self-improvement across episodes. See citation for how to cite Embodify and what to report.
Quick start
One-line setup
Paste this into Claude Code, Codex or any other agent you use:
Install Embodify (https://github.com/YidaYang/embodify) for yourself, then set up a LIBERO environment or connect to my existing simulator.
That's it. Your agent installs the Embodify plugin, sets up the simulator and tells you when to restart the session. (Agents: follow the agent setup guide.)
Manual install
Embodify starts its MCP server with uv, straight
from PyPI. If you do not have uv yet, install it with python -m pip install uv
or the official installer.
Claude Code
claude plugin marketplace add YidaYang/embodify
claude plugin install embodify@embodify
Codex
codex plugin marketplace add YidaYang/embodify
codex plugin add embodify@embodify
The plugin brings both the MCP server, registered as embodify, and the skills.
The server starts on the Fake backend, so you can try the tools right away;
connect a real simulator next. It reads its
settings from ~/.embodify/config.json (see backend setup).
To check the package on its own, without an agent:
uvx --from embodify-mcp embodify-mcp-smoke # end-to-end check: no simulator, GPU or model needed
Other agents
- Register the server in your agent's MCP configuration using examples/mcp.json.
- If your agent supports Agent Skills (
SKILL.mdfolders), copy or link the folders in plugin/skills/ into its skills directory.
Restart the session, then ask your agent something like "Reset the task, describe what the cameras show, then raise the gripper 5 cm."
Connect a real simulator
Let your agent do this step. Paste:
Connect Embodify to a real simulator for me: set up LIBERO on this machine, or connect to my existing simulator. Follow https://github.com/YidaYang/embodify/blob/main/docs/agent-setup.md.
Your agent installs the simulator or connects to yours over SSH, writes the
server settings to ~/.embodify/config.json and asks you to restart the
session. To do it by hand, see backend setup.
Watch robots live and replay episodes
Add "monitor-port": 8765 to ~/.embodify/config.json and open
http://127.0.0.1:8765 to watch the robot work live, with every camera view,
the robot state and each tool call your agent makes, or to replay any past
episode frame by frame. To browse saved runs without a running server:
uvx --from embodify-mcp embodify-mcp-monitor # reads ~/.embodify/runs
The monitor listens on localhost only.
MCP tools
| Tool | Purpose |
|---|---|
get_session_info |
Current run, task, step budget and robot state; no images |
list_tasks |
Browse the backend's task catalogue |
reset_task |
Start an episode and return the first camera images |
observe |
Camera images and robot state, without moving |
move_relative |
Move one end effector by a translation and optional rotation |
set_gripper |
Open or close a gripper |
control_arms |
Move several arms together with common progress (two-arm backends) |
stop_episode |
End the episode and write its record |
Translations are in meters, rotations in radians, quaternions in xyzw order. Frames and stop reasons are defined in the action contract.
Skills
The plugin contains these skills:
| Skill | Status | What it does |
|---|---|---|
| embodied-control | v0 | The observe–act loop: small moves, reading stop reasons, verifying grasps, releasing in a separate call |
| robot-profile | v0 | Keep a profile of the robot: arms, cameras, frames, calibration and measured behavior |
| task-experience | v0 | Write a lesson after every episode, read relevant lessons before the next, promote repeated lessons to rules |
| object-segmentation | Coming soon | Open-vocabulary segmentation of camera images |
| depth-ranging | Coming soon | Pixel to 3D position from depth and calibration |
Skills are grouped into three families that will keep growing:
- Embodiment knowledge: how this particular robot is built, where its cameras are and how it actually moves.
- Manipulation tools: perception, measurement and planning tools, including ideas from work such as Code as Policies.
- Recursive self-improvement: turning experience into lessons, lessons into rules and eventually into new skills, improving recursively.
Roadmap
- Backends: RoboTwin; LeRobot SO-101 as the first real robot, with workspace limits, human-judged success and an emergency stop; more real robots and simulators.
- Embodiments: mobile manipulators, humanoids, dexterous hands.
- Observations: depth images, camera calibration and more through the tools.
- Skills: segmentation, depth ranging and other perception tools; code-as-policy style tools; a stronger recursive self-improvement loop, and more.
Development
python -m pip install -e ".[dev]"
python -m pytest -q
python tools/check_release.py
See contributing, writing a backend, backend setup, action contract and security.
License and citation
Original code is licensed under Apache-2.0. Bundled third-party code keeps its original notices. See citation for how to cite Embodify.
Embodify MCP questions
How do I add Embodify MCP to Claude Code?
Run claude mcp add embodify -- uvx embodify-mcp in your terminal. Add --scope user to make it available in every project.
How do I add Embodify MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Embodify MCP provide?
It exposes 8 tools, including get_session_info, list_tasks, reset_task, observe, move_relative.
What robot simulators are supported?
Currently, it supports LIBERO and RoboDojo, with RoboTwin coming soon.
Can I run the simulator on a remote machine?
Yes, you can run the simulator on a GPU server via SSH or trusted TCP while keeping the agent on your local machine.
How can I monitor the robot's actions?
You can watch running episodes live in a browser or replay past ones frame by frame by enabling the monitor port in the configuration.
Does it work with existing AI agents?
Yes, it works with any MCP-capable agent like Claude Code or Codex.