feat: 浏览器自动化 MCP（Playwright）+ browser-automation 技能
- playwright_browser.Browser：单页 Chromium，navigate / snapshot（正文 8000 字截断标记）/ click / fill / evaluate / screenshot（工作区内）/ close；启动参数 --no-sandbox + --disable-dev-shm-usage（runsc + 1003 用户实测必需）， 代理显式传给 launch（Chromium 在 Linux 下不稳定地读 env 代理），浏览器路径 PLAYWRIGHT_BROWSERS_PATH=/opt/ms-playwright。 - playwright_mcp：stdio MCP，7 个 browser_* 工具，同一进程 单 Browser 实例；测试用 fake browser / fake factory。 - worker：--playwright-mcp flag，_tenant_dirs 播种两个脚本 + [mcp_servers.playwright]，_prepare_tenant 写 env（代理 + 浏览器路径，MCP 子进程不继承 Codex 进程 env，镜像 ENV 在此必须重写，缺了会报 Executable doesn't exist）。 - 技能 browser-automation：JS 页、翻页、表单、截图时用， 静态页优先 web_fetch / web_search；截图须 PIL 读回验证。 - 镜像（层构建，非本 PR）：FROM latest + fonts-noto-cjk + playwright + chromium（npmmirror）+ install-deps，3.77GB； runsc + 1003 + docker-codex 条件下 JS 执行、example.com 标题、截图均已实测通过。
This commit is contained in:
host committed
1 parent
872b23a296
commit
c9a483282d
5 files changed
+821
-2
No files matched your search
@@ -0,0 +1,257 @@
|
||||
"""Stdio MCP server exposing headless Chromium to codex.
|
||||
|
||||
Protocol: JSON-RPC 2.0 over stdio, one JSON object per line.
|
||||
Logs go to stderr only -- anything on stdout would corrupt the
|
||||
JSON-RPC stream.
|
||||
|
||||
This file is deliberately thin: all browser logic lives in
|
||||
``playwright_browser.py``. It can run two ways:
|
||||
- inside the repo: ``python3 -m cloud.playwright_mcp`` (imports
|
||||
``cloud.playwright_browser``);
|
||||
- copied flat into a tenant codex-home next to
|
||||
``playwright_browser.py`` (imports plain ``playwright_browser``
|
||||
from its own directory).
|
||||
The ``ensure_codex_home_playwright`` helper does the copying;
|
||||
proxy vars and PLAYWRIGHT_BROWSERS_PATH arrive via the MCP env
|
||||
block in config.toml, never via tool arguments.
|
||||
|
||||
One Browser instance lives for the whole MCP process: navigate
|
||||
once, then snapshot/click/fill/screenshot against the same page.
|
||||
"""
|
||||
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
|
||||
try:
|
||||
from cloud.playwright_browser import Browser, BrowserError
|
||||
except ImportError: # flat copy in a tenant codex-home
|
||||
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
|
||||
from playwright_browser import Browser, BrowserError # noqa: E402
|
||||
|
||||
SERVER_NAME = "playwright"
|
||||
SERVER_VERSION = "0.1.0"
|
||||
|
||||
_TOOLS = [
|
||||
{
|
||||
"name": "browser_navigate",
|
||||
"description": (
|
||||
"Open a URL in headless Chromium and return its final "
|
||||
"URL and title. Use for pages that need JavaScript to "
|
||||
"render, which web_fetch cannot see. Network goes "
|
||||
"through the egress proxy, so domains outside the "
|
||||
"Tinyproxy whitelist fail with a proxy 403 -- report "
|
||||
"that plainly, do not bypass it."
|
||||
),
|
||||
"inputSchema": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"url": {"type": "string",
|
||||
"description": "http(s) URL, or file:// URL "
|
||||
"for a page already in the worktree"},
|
||||
},
|
||||
"required": ["url"],
|
||||
},
|
||||
},
|
||||
{
|
||||
"name": "browser_snapshot",
|
||||
"description": (
|
||||
"Return the current page's title, URL and body text "
|
||||
"(truncated at 8000 characters with a flag). Call "
|
||||
"after navigate, and after click/fill, to see what "
|
||||
"actually rendered."
|
||||
),
|
||||
"inputSchema": {"type": "object", "properties": {}},
|
||||
},
|
||||
{
|
||||
"name": "browser_click",
|
||||
"description": (
|
||||
"Click an element by CSS selector or Playwright "
|
||||
"selector (e.g. 'button.submit', 'text=Next'). "
|
||||
"Then snapshot to see the result."
|
||||
),
|
||||
"inputSchema": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"selector": {"type": "string"},
|
||||
},
|
||||
"required": ["selector"],
|
||||
},
|
||||
},
|
||||
{
|
||||
"name": "browser_fill",
|
||||
"description": (
|
||||
"Fill an input/textarea by CSS selector with text. "
|
||||
"Then snapshot or click to submit."
|
||||
),
|
||||
"inputSchema": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"selector": {"type": "string"},
|
||||
"text": {"type": "string"},
|
||||
},
|
||||
"required": ["selector", "text"],
|
||||
},
|
||||
},
|
||||
{
|
||||
"name": "browser_evaluate",
|
||||
"description": (
|
||||
"Run a JavaScript expression in the page and return "
|
||||
"its string value (truncated at 4000 characters). "
|
||||
"Same sandbox privilege as the shell tool; prefer "
|
||||
"snapshot/click/fill for ordinary reads and actions."
|
||||
),
|
||||
"inputSchema": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"expression": {"type": "string"},
|
||||
},
|
||||
"required": ["expression"],
|
||||
},
|
||||
},
|
||||
{
|
||||
"name": "browser_screenshot",
|
||||
"description": (
|
||||
"Save a PNG screenshot of the current page into the "
|
||||
"working directory and return its absolute path and "
|
||||
"byte size. Verify the returned path with shell/PIL "
|
||||
"before reporting success."
|
||||
),
|
||||
"inputSchema": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"output_filename": {"type": "string",
|
||||
"description": "Plain basename "
|
||||
"to save as, e.g. 'shot.png'. "
|
||||
"Default: shot-<epoch>.png"},
|
||||
},
|
||||
},
|
||||
},
|
||||
{
|
||||
"name": "browser_close",
|
||||
"description": "Close the browser page. Safe to call twice.",
|
||||
"inputSchema": {"type": "object", "properties": {}},
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
def _err(code, message):
|
||||
return {"code": code, "message": message}
|
||||
|
||||
|
||||
_BROWSER = None
|
||||
|
||||
|
||||
def _get_browser(browser=None):
|
||||
global _BROWSER
|
||||
if browser is not None:
|
||||
return browser
|
||||
if _BROWSER is None:
|
||||
_BROWSER = Browser()
|
||||
return _BROWSER
|
||||
|
||||
|
||||
def handle_request(request, browser=None):
|
||||
"""Handle one JSON-RPC request dict. Returns a response dict or
|
||||
None for notifications (no id). Tests pass a fake browser."""
|
||||
if not isinstance(request, dict):
|
||||
return {"jsonrpc": "2.0", "id": None,
|
||||
"error": _err(-32700, "request is not an object")}
|
||||
method = request.get("method")
|
||||
req_id = request.get("id")
|
||||
is_notification = "id" not in request
|
||||
|
||||
if method == "initialize":
|
||||
if is_notification:
|
||||
return None
|
||||
return {"jsonrpc": "2.0", "id": req_id,
|
||||
"result": {
|
||||
"protocolVersion": request.get("params", {}).get(
|
||||
"protocolVersion", "2024-11-05"),
|
||||
"capabilities": {"tools": {}},
|
||||
"serverInfo": {"name": SERVER_NAME,
|
||||
"version": SERVER_VERSION}}}
|
||||
if method in ("notifications/initialized", "notifications/cancelled"):
|
||||
return None
|
||||
if method == "ping":
|
||||
if is_notification:
|
||||
return None
|
||||
return {"jsonrpc": "2.0", "id": req_id, "result": {}}
|
||||
if method == "tools/list":
|
||||
if is_notification:
|
||||
return None
|
||||
return {"jsonrpc": "2.0", "id": req_id,
|
||||
"result": {"tools": _TOOLS}}
|
||||
if method == "tools/call":
|
||||
if is_notification:
|
||||
return None
|
||||
params = request.get("params") or {}
|
||||
name = params.get("name")
|
||||
args = params.get("arguments") or {}
|
||||
target = _get_browser(browser)
|
||||
try:
|
||||
if name == "browser_navigate":
|
||||
result = target.navigate(args.get("url"))
|
||||
elif name == "browser_snapshot":
|
||||
result = target.snapshot()
|
||||
elif name == "browser_click":
|
||||
result = target.click(args.get("selector"))
|
||||
elif name == "browser_fill":
|
||||
result = target.fill(args.get("selector"),
|
||||
args.get("text"))
|
||||
elif name == "browser_evaluate":
|
||||
result = target.evaluate(args.get("expression"))
|
||||
elif name == "browser_screenshot":
|
||||
result = target.screenshot(
|
||||
args.get("output_filename"))
|
||||
elif name == "browser_close":
|
||||
result = target.close()
|
||||
else:
|
||||
return {"jsonrpc": "2.0", "id": req_id,
|
||||
"error": _err(-32602, "unknown tool: %r" % name)}
|
||||
except Exception as exc: # noqa: BLE001 - tool errors are data
|
||||
return {"jsonrpc": "2.0", "id": req_id,
|
||||
"result": {"content": [{"type": "text",
|
||||
"text": "error: %s" % exc}],
|
||||
"isError": True}}
|
||||
return {"jsonrpc": "2.0", "id": req_id,
|
||||
"result": {"content": [{"type": "text",
|
||||
"text": json.dumps(
|
||||
result, ensure_ascii=False)}],
|
||||
"isError": False}}
|
||||
if is_notification:
|
||||
return None
|
||||
return {"jsonrpc": "2.0", "id": req_id,
|
||||
"error": _err(-32601, "method not found: %r" % method)}
|
||||
|
||||
|
||||
def main():
|
||||
for line in sys.stdin:
|
||||
line = line.strip()
|
||||
if not line:
|
||||
continue
|
||||
try:
|
||||
request = json.loads(line)
|
||||
except json.JSONDecodeError as exc:
|
||||
sys.stdout.write(json.dumps(
|
||||
{"jsonrpc": "2.0", "id": None,
|
||||
"error": _err(-32700, "parse error: %s" % exc)}) + "\n")
|
||||
sys.stdout.flush()
|
||||
continue
|
||||
try:
|
||||
response = handle_request(request)
|
||||
except Exception as exc: # noqa: BLE001 - server must not die
|
||||
print("playwright_mcp: handler error: %s" % exc,
|
||||
file=sys.stderr)
|
||||
if "id" in request:
|
||||
response = {"jsonrpc": "2.0", "id": request["id"],
|
||||
"error": _err(-32603, "internal error")}
|
||||
else:
|
||||
response = None
|
||||
if response is not None:
|
||||
sys.stdout.write(json.dumps(response) + "\n")
|
||||
sys.stdout.flush()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in new issue
Block a user