host
814fe8f7c2
- browser_click_at(x, y)：视口坐标点击（1280x800、左上角 原点），越界与非数字拒绝；live 视图里用户在截图上的 点击落点就走这个工具。 - browser_live_shot：固定文件 browser-live.png + 状态 sidecar browser-live.json（URL/标题/时间戳），watcher 轮询一个稳定路径即可；技能要求每次动作后都调一次， 保持画面最新。 - MCP 新增 browser_click_at / browser_live_shot 两个工具； 技能补 live 视图一节；测试 9 项（含 fake mouse、越界、 live 文件与状态读回）。
301 lines
11 KiB
Python
301 lines
11 KiB
Python
"""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_click_at",
|
|
"description": (
|
|
"Click at viewport coordinates (CSS pixels, origin "
|
|
"top-left of the 1280x800 viewport). This is the tool "
|
|
"a live viewer drives: the user clicks on a screenshot "
|
|
"and the coordinates arrive here. Then snapshot to see "
|
|
"the result."
|
|
),
|
|
"inputSchema": {
|
|
"type": "object",
|
|
"properties": {
|
|
"x": {"type": "number"},
|
|
"y": {"type": "number"},
|
|
},
|
|
"required": ["x", "y"],
|
|
},
|
|
},
|
|
{
|
|
"name": "browser_live_shot",
|
|
"description": (
|
|
"Screenshot to the FIXED live-view file "
|
|
"browser-live.png plus a browser-live.json status "
|
|
"sidecar (url, title, timestamp), so a watcher can "
|
|
"poll one stable path. Call after every navigate / "
|
|
"click / fill while a live view is wanted. Returns "
|
|
"path, bytes, url, title and timestamp."
|
|
),
|
|
"inputSchema": {
|
|
"type": "object",
|
|
"properties": {
|
|
"output_filename": {"type": "string",
|
|
"description": "Plain basename "
|
|
"to save as. Default: "
|
|
"browser-live.png"},
|
|
},
|
|
},
|
|
},
|
|
{
|
|
"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_click_at":
|
|
result = target.click_at(args.get("x"), args.get("y"))
|
|
elif name == "browser_live_shot":
|
|
result = target.live_shot(
|
|
args.get("output_filename"))
|
|
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()
|