에이전트 강화
게시자의 자체 명령입니다. PlugMCP 엔드포인트가 아닙니다.
Host a copy with our keys and logs.
uvx wavexis-mcp==1.6.24Claude Code에는 로컬 명령용 설치 링크가 없습니다. 아래 명령을 복사해 터미널에서 실행합니다.
claude mcp add io.github.mathiaspaulenko-wavexis-mcp -- uvx wavexis-mcp==1.6.24터미널에서 실행합니다.
{ "mcpServers": { "io.github.mathiaspaulenko-wavexis-mcp": { "command": "uvx", "args": [ "wavexis-mcp==1.6.24" ] } }}claude_desktop_config.json
원격 URL인가요, 내 컴퓨터에서 실행하는 명령인가요? 두 설치 방식의 차이
PlugMCP에서 실행
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
실행MCP server that exposes the wavexis browser automation library to LLMs. 220 tools across 13 capability tiers. No Node.js, no Chromium download — uses your existing Chrome/Edge. 100% Python.
30 seconds to your first screenshot. Add this to your MCP client config (Claude Desktop, Cursor, Windsurf, VS Code):
{
"mcpServers": {
"wavexis": {
"command": "uvx",
"args": ["wavexis-mcp", "--caps", "all"]
}
}
}
Then ask your LLM:
"Take a full-page screenshot of https://example.com"
The LLM calls wavexis_screenshot(url="https://example.com", full_page=true) and returns the screenshot. No Node.js, no Chromium download, no setup beyond the config above.
WaveXisMCP wraps the wavexis browser automation library and exposes it as an MCP server. You don't need Node.js, Playwright, or a separate Chromium download — WaveXisMCP launches your existing Chrome or Edge installation directly.
--caps. Start with core (72 tools), add tiers as neededstealth=true hides navigator.webdriver, fakes plugins/languages/chrome runtimesuggestion field so the LLM self-corrects without human helpYou (natural language)
→ LLM decides which tool to call
→ WaveXisMCP receives the tool call
→ wavexis library executes it via CDP or BiDi
→ Chrome/Edge/Firefox performs the action
← Result returned as JSON (text, base64, file path)
← JSON passed back to LLM
← LLM summarizes the result for you
The LLM never sees the browser directly. It only sees tool definitions (name, description, parameters) and JSON responses. This means any MCP-compatible LLM client works out of the box — no custom integrations needed.
url parameter. The browser launches, executes, and closes automatically.core (72 tools) to all (220 tools). Enable only what you need via --caps.suggestion field that tells the LLM what to do next, enabling self-correction without human intervention.pip install wavexis-mcp
The CDP backend (Chromium) is included by default. For the BiDi backend (Firefox):
pip install "wavexis-mcp[bidi]"
Or run without installing (recommended):
uvx wavexis-mcp
Add to your MCP client config (Claude Desktop, Cursor, Windsurf, VS Code):
{
"mcpServers": {
"wavexis": {
"command": "uvx",
"args": ["wavexis-mcp", "--caps", "all"]
}
}
}
Or with pip:
{
"mcpServers": {
"wavexis": {
"command": "wavexis-mcp",
"args": ["--caps", "all"]
}
}
}
Call any tool with a url parameter — the browser launches, executes, and closes automatically:
wavexis_screenshot(url="https://example.com", full_page=true)
Open a session, chain multiple actions, close when done:
wavexis_session_open(backend="cdp", headless=false)
→ {"session_id": "abc-123"}
wavexis_navigate(session_id="abc-123", url="https://example.com")
wavexis_click(session_id="abc-123", selector="#login")
wavexis_screenshot(session_id="abc-123")
wavexis_session_close(session_id="abc-123")
Use wavexis_act to interact with pages using natural language:
wavexis_session_open(backend="cdp")
wavexis_navigate(session_id="abc-123", url="https://example.com")
wavexis_act(session_id="abc-123", instruction="click the login button")
→ {"action": "click", "element": {"ref": "el-3", "role": "button", "name": "Login"}, "status": "ok"}
The wavexis_act tool takes an a11y snapshot, matches the instruction to an element using keyword scoring, and executes the detected action (click, type, fill, hover). No external LLM calls — pure heuristic matching.
Default: --caps=core (72 tools). Enable all: --caps=all. Enable specific: --caps=network,storage,emulation.
Tip: Start with
--caps coreand add tiers as needed. Each tier adds tool definitions to the LLM's context, which consumes tokens. For most tasks,core,network,storage(110 tools) is a good balance.
WaveXisMCP supports two backends with full feature parity:
pip install "wavexis-mcp[bidi]"Select per session:
# CDP (default, Chrome/Edge only)
wavexis_session_open(backend="cdp")
# BiDi with Chrome (auto-launches chromedriver)
wavexis_session_open(backend="bidi", browser="chrome")
# BiDi with Firefox (auto-launches geckodriver)
wavexis_session_open(backend="bidi", browser="firefox")
Use connect_existing=True to launch Chrome with --remote-debugging-port and connect to it. Useful for reusing a browser profile with logged-in sessions:
# Launch Chrome with debug port and connect via CDP
wavexis_session_open(connect_existing=true)
# Reuse an existing Chrome profile (keeps logins, cookies, extensions)
wavexis_session_open(connect_existing=true, user_data_dir="C:/Users/me/ChromeProfile")
Chrome is launched headed (headless is ignored). The browser subprocess is terminated when the session is closed.
Chain multiple actions in a single tool call by passing a YAML string:
wavexis_multi_action(
config="""
actions:
- navigate: https://example.com
- screenshot:
full_page: true
- eval: document.title
- click: "#login"
- type:
selector: "#username"
text: [email protected]
- screenshot: {}
""",
session_id="abc-123"
)
Supported action types: navigate, screenshot, eval, click, type, fill. Set continue_on_error: true to keep executing on failures.
Resources (read-only browser state):
wavexis://session/{id}/url — current page URLwavexis://session/{id}/cookies — cookies as JSONwavexis://session/{id}/console — console messageswavexis://session/{id}/tabs — open tabsPrompts (workflow templates):
scrape_page(url, selector) — scrape and extract contentaudit_page(url) — full a11y + performance auditfill_form(url, fields) — fill a form on a pagedebug_page(url) — debug console, network, performanceRun WaveXisMCP as an HTTP server for CI/CD, shared instances, or Docker:
# HTTP on localhost
wavexis-mcp --transport http --port 8765
# HTTP with all tiers
wavexis-mcp --transport http --port 8765 --caps all
# HTTP with remote access (use behind a reverse proxy!)
wavexis-mcp --transport http --allow-remote --port 8765
Binds to 127.0.0.1 by default. Use --allow-remote for 0.0.0.0.
Per-session token bucket rate limiting:
# 10 calls/sec, burst of 5
wavexis-mcp --rate-limit 10 --rate-burst 5
When exceeded, the tool returns the standard structured error: {"error": "Rate limit exceeded. Retry after Nms.", "type": "RuntimeError", ...}. Set --rate-limit 0 to disable.
# Pull and run
docker run -p 8765:8765 ghcr.io/mathiaspaulenko/wavexis-mcp
# Or build locally
docker build -t wavexis-mcp .
docker run -p 8765:8765 wavexis-mcp
# Docker Compose
docker-compose up
See Docker docs for details.
Note: Playwright MCP supports WebKit (Safari) — WaveXisMCP does not (yet). See the roadmap for planned features.
Full documentation, API reference, and examples are hosted at mathiaspaulenko.github.io/wavexis-mcp.
Key sections:
All tools return structured error JSON on failure. Every error includes a suggestion field that guides the LLM toward the next action:
{
"error": "Session 'abc-123' not found.",
"tool": "wavexis_navigate",
"type": "SessionNotFoundError",
"message": "Session 'abc-123' not found.",
"suggestion": "Call wavexis_session_open first to create a browser session."
}
This enables the LLM to self-correct without human intervention — it reads the suggestion and calls the recommended tool.
WaveXisMCP sits at the top of a three-layer ecosystem:
WaveXisMCP (MCP server, 220 tools)
└─ wraps → wavexis (browser automation library)
├─ cdpwave (CDP backend, Chromium-native)
└─ bidiwave (BiDi backend, W3C cross-browser)
AbstractBackend interface.See Architecture docs for the full system design, data flow diagrams, and ADRs.
git clone https://github.com/MathiasPaulenko/wavexis-mcp.git
cd wavexis-mcp
pip install -e ".[dev]"
# Run quality checks
ruff check wavexis_mcp tests
ruff format --check
mypy wavexis_mcp
python -m bandit -r wavexis_mcp
# Run tests
pytest tests/unit -v
Contributions are welcome. Please see CONTRIBUTING.md for the development workflow, coding standards, and pull request process. For security issues, see SECURITY.md.
WaveXisMCP is built on the wavexis browser automation library and the Model Context Protocol. Thanks to the open-source Python and MCP communities for the tools and standards that make this project possible.
MIT
mcp-name: io.github.MathiasPaulenko/wavexis-mcp
220 browser automation tools for Chrome, Edge, and Firefox via CDP + BiDi. 100% Python.
{ "mcpServers": { "io.github.mathiaspaulenko-wavexis-mcp": { "command": "uvx", "args": [ "wavexis-mcp==1.6.24" ] } }}도구
아직 도구 목록이 없습니다. 원격 서버는 첫 상태 확인 후에 도구 목록이 생깁니다.
FAQ
이 페이지에서 Cursor, Claude Desktop, Claude Code 또는 VS Code용 stdio 설정을 복사합니다. PlugMCP 프록시가 아니라 게시자의 설치 방식을 사용합니다.
이 레코드에는 필수 환경 변수가 등록되어 있지 않습니다.
WaveXisMCP은(는) stdio를 통해 로컬에서 실행됩니다.
마지막 확인: 2026-11-09. 220 browser automation tools for Chrome, Edge, and Firefox via CDP + BiDi. 100% Python.