Browser Use bridge for DeepSeek Harness: let your
dshagent run real web tasks — open pages, click, type, fill forms, extract data — through the Browser Use Cloud API.
English | 中文
A thin, honest bridge. It registers one model-facing tool, browser_use_run,
forwards the task to Browser Use's cloud endpoint, and returns the raw run
result. It does not reimplement Browser Use and does not claim to be a
full integration.
dsh plugin --profile web add dsh-browser-useThen set your Browser Use API key (config apiKey, or the BROWSER_USE_API_KEY
env var).
| Mode | Needs | Tools you get |
|---|---|---|
| Cloud (this plugin) | Browser Use API key | browser_use_run |
| Local (free, no key) | Python + browser-use installed |
mcp__browser_use__browser_exec, mcp__browser_use__browser_screenshot |
Browser Use also runs locally as an MCP stdio server — no cloud subscription.
DeepSeek Harness already ships @deepseek-ai/dsh-mcp-client, so you do not
need this plugin for the local path. Install Browser Use once
(pip install 'browser-use[cli]'), then add this to your profile's
cordis.yml:
- insert:
- id: browser-use-local
name: '@deepseek-ai/dsh-mcp-client'
config:
serverName: browser_use
transport: stdio
command: browser-use
args: ['--cli-mcp']
cwd: !!js process.cwd()That registers mcp__browser_use__browser_exec and
mcp__browser_use__browser_screenshot. A ready-to-copy file is in
examples/local-mcp.cordis.yml.
| Parameter | Type | Description |
|---|---|---|
task |
string | The task, e.g. "Find the stars of the browser-use repo". |
model |
string | Optional provider-prefixed model id, e.g. openai/gpt-5.5. |
Returns { result } — the raw Browser Use run result.
| Key | Type | Default | Description |
|---|---|---|---|
apiKey |
string | (env) | Browser Use API key |
baseUrl |
string | https://api.browser-use.com |
Cloud API base URL |
timeoutMs |
number | 300000 |
Request timeout |
model |
string | (none) | Default model |
pnpm typecheck·pnpm build·pnpm test(4 tests, mocked HTTP).- Tested with
@deepseek-ai/dsh-tools ^0.1.0-rc.6.
- This is a cloud-API bridge; it needs a Browser Use API key.
- Local mode is provided by DeepSeek Harness's own
mcp-client, not by this package; this README documents both so you can pick the cheaper path. - It returns the raw response; it does not stream or poll for completion.
- Community plugin, not an official Browser Use or DeepSeek product.
给 DeepSeek Harness 的 Browser Use 桥接:让
dshagent 通过 Browser Use 云 API 执行真实网页任务(打开页面、点击、输入、填表、抽取数据)。
注册一个 browser_use_run 工具:把任务转发给 Browser Use,返回原始运行结果。
这是薄桥接,不重新实现 Browser Use,也不冒充官方。
dsh plugin --profile web add dsh-browser-use需要配置 Browser Use API key(apiKey 配置项,或环境变量 BROWSER_USE_API_KEY)。
| 模式 | 需要 | 得到的工具 |
|---|---|---|
| 云端(本插件) | Browser Use API key | browser_use_run |
| 本地(免费,无需 key) | Python + browser-use 已安装 |
mcp__browser_use__browser_exec、mcp__browser_use__browser_screenshot |
Browser Use 也能以本地 MCP stdio 服务运行,无需云订阅。DeepSeek Harness 已经内置
@deepseek-ai/dsh-mcp-client,所以本地路径不需要本插件。先安装一次
Browser Use(pip install 'browser-use[cli]'),然后把你 profile 的
cordis.yml 加上:
- insert:
- id: browser-use-local
name: '@deepseek-ai/dsh-mcp-client'
config:
serverName: browser_use
transport: stdio
command: browser-use
args: ['--cli-mcp']
cwd: !!js process.cwd()这会注册 mcp__browser_use__browser_exec 和
mcp__browser_use__browser_screenshot。现成可复制的文件在
examples/local-mcp.cordis.yml。