omni-coding-agent MCP server
Commit Nov 14, 2026An AI coding assistant that reads and edits code, runs shell commands, and performs browser automation through desktop, web, and IDE integrations.
Also known as LiuHarry1/omni-coding-agent
- Stars
- 5
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 14, 2026
- License
- MIT
What is omni-coding-agent MCP?
omni-coding-agent is an AI coding assistant that reads and edits code, runs shell commands, and performs browser automation through desktop, web, and IDE integrations.
Summary generated from the project's README
About omni-coding-agent MCP server
Automating web tasks and managing codebases through a single interface is what omni-coding-agent enables for developers. This locally runnable assistant functions as a coding partner that can read and edit files, execute shell commands, and search through entire codebases. It operates via an Electron desktop app, a Web UI, or through direct integrations in IDEs like VS Code, Cursor, and IntelliJ.
Users can interact with the agent using various modes, including an isolated browser for automation or an extension mode that pairs with a personal Chrome profile to access authenticated websites. Setting up the environment requires Node.js 20+ and a configuration file containing your specific model API key, base URL, and model selection. The system manages context through automatic memory compaction and session memory to maintain efficiency during long development tasks.
What you can do with it
- 1Automate web-based workflowsDirect the agent to navigate websites, fill out forms, and capture screenshots of specific pages.
- 2Perform complex code modificationsAsk the assistant to search your codebase and apply edits to your files directly.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableliuharry1/omni-coding-agent is public and reachablegithub.com/liuharry1/omni-coding-agent ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-14github.com/liuharry1/omni-coding-agent ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubCoding Agent
Formerly known as Baize (白泽).
First time here? Start with the Quick Start (download the code → install dependencies → run the desktop app → pair a browser).
A locally runnable AI coding assistant for chat, reading and editing code, tool use, and browser automation. Supports the desktop app, Web UI, and VS Code / Cursor / IntelliJ integrations.
How do you want to use it?
| I want to… | Start here |
|---|---|
| Get started and try browser automation | Quick Start |
| Develop the frontend locally or debug the agent | Local Development |
| Use Coding Agent in VS Code or Cursor | VS Code Integration |
| Use Coding Agent in IntelliJ | IntelliJ Integration |
| Deploy Coding Agent to a private network | Docker Deployment |
| Extend Coding Agent or add tools | Agent Source Guide |
Core capabilities
- Coding assistance — Read and edit files, run shell commands, search the codebase, and explore in parallel with subagents
- Browser automation — Open web pages, click controls, fill forms, take screenshots, and read page content; can control your own Chrome profile for sites that require authentication
- Extensibility — Skills, Commands, Plugins, MCP, and custom Subagents
- Multiple interfaces — Electron desktop app, Web UI, ACP (IDE sidebar), and HTTP API / SDK
- Memory and compaction — Session memory, Auto memory, and automatic context compaction
Five-minute desktop quick start
Prerequisites: Node.js 20+ and API configuration supplied by your team (see .ai-agent/settings.json)
git clone <your-repository-url>
cd coding-agent
npm install # root + workspaces (web, protocol, sdks/typescript)
cp .ai-agent/settings.example.json .ai-agent/settings.json # Add your API configuration
npm run desktop:dev
When the desktop window opens, select Browser Automation and enter a prompt such as:
Open https://example.com and tell me the page title.
For sites that require authentication, see extension mode and pairing in the Browser Automation Guide.
Configuration quick reference
| Configuration | Location |
|---|---|
Model API (baseURL, apiKey, model) |
.ai-agent/settings.json |
| Runtime settings such as the port and workspace path | .env (optional; see .env.example) |
Browser mode (isolated / extension) |
browser in .ai-agent/settings.json |
User-level configuration: ~/.ai-agent/settings.json. Project-level configuration: <workspace>/.ai-agent/settings.json, which takes precedence.
Common commands
| Command | Description |
|---|---|
npm run desktop:dev |
Start the desktop app (recommended for new users) |
npm start |
Start only the agent backend (:4567) |
npm run dev:web |
Start the Web UI in development mode (run npm start in another terminal) |
npm run cloud:start |
Build and start the local Docker-backed Cloud profile |
npm run browser:pair |
Check that the Chrome extension can reach the agent |
npm run desktop:pack |
Package the desktop installer |
npm run desktop:pack:win |
Package the Windows installer |
npm run build:web |
Build the frontend into web/dist |
npm run docs:dev |
Start the documentation site in development mode |
npm run docs:build |
Build the documentation site |
npm run typecheck |
Run TypeScript type checking |
npm run format |
Format the code with Prettier |
Browser automation
Coding Agent can open web pages, click controls, fill forms, take screenshots, and read page content. By default, it launches an isolated browser with no configuration required. It can also control your own Chrome profile, allowing access to authenticated sites without login scripts.
npm start # Isolated mode works out of the box
npm run browser:pair # Check the extension, to use your own Chrome profile
For complete instructions, see docs/readme/browser.md.
Production deployment
Deploy the Web UI with Docker. See deploy/README.md for details.
docker compose -f deploy/docker-compose.admin.yml --env-file deploy/.env up -d
# Open http://localhost:9999 (credentials: WEB_USERNAME / WEB_PASSWORD)
Project structure
├── start.js # Unified entry point (HTTP / --acp / --stdio)
├── src/ # Agent core (tools / core / services / server)
│ ├── tests/ # Legacy test scripts, run through vitest (suites/, suites/live/)
│ └── dev/ # Developer utilities (browser pairing, dev Chrome)
├── web/ # React frontend (npm workspace)
├── desktop/ # Electron shell + electron-builder config
├── chrome-extension/ # Browser extension (extension mode)
├── protocol/ # Shared wire protocol (npm workspace)
├── sdks/ # Client SDKs: typescript/ (npm workspace), python/
├── analytics/ # Telemetry service (Python / FastAPI)
├── integrations/ # Third-party bridges (stpl-lsp-bridge)
├── evals/ # SWE-bench / aider-polyglot evaluation harnesses
├── deploy/ # Docker images, compose files, workspace seeds
├── scripts/ # Build / staging scripts
├── docs/ # VitePress documentation
└── .ai-agent/ # Project-level skills / agents / commands / settings.example.json
Documentation index
User guides
| Topic | Documentation |
|---|---|
| Installation and first run | docs/readme/getting-started.md |
| Browser automation | docs/readme/browser.md |
| Local Web development | docs/readme/development.md |
| VS Code / Cursor | docs/readme/integrations/vscode-acp.md |
| IntelliJ IDEA | docs/readme/integrations/intellij-acp.md |
| Docker deployment | deploy/README.md |
| Client SDK | sdks/typescript/ |
Development and architecture
| Topic | Documentation |
|---|---|
| Documentation overview | docs/README.md |
| Agent source and extensions | src/README.md |
| System architecture | docs/architecture/ |
| Memory system | docs/architecture/memory-guide.md |
| Execution architecture | docs/architecture/execution.md |
License
Licensed under the MIT License. Copyright © 2026 Harry Liu.
omni-coding-agent MCP questions
Can I deploy this agent to a private network?
Yes, you can deploy the agent using Docker.
What are the core coding capabilities?
The agent can read and edit files, run shell commands, search the codebase, and use subagents to explore in parallel.