parallel-search

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

parallel-search

Use this skill when you need to work with search-mcp through its generated async Python app, call its MCP-backed functions from code, or inspect available functions with the mcp-skill CLI.

当你需要通过生成的异步Python应用操作search-mcp、从代码中调用其基于MCP的函数，或使用mcp-skill CLI查看可用函数时，可使用此技能。

Authentication

身份验证

This app can use the MCP client's built-in OAuth flow when the server requires it. In most cases, the default constructor is enough. Tokens are persisted to

~/.mcp-skill/auth/

so subsequent runs reuse the same credentials automatically.

python

app = ParallelsearchApp()

If you need a custom OAuth provider, pass it via the

auth

argument:

python

app = ParallelsearchApp(auth=my_oauth_provider)

此应用在服务器要求时可使用MCP客户端内置的OAuth流程。大多数情况下，默认构造函数即可满足需求。令牌会持久化到

~/.mcp-skill/auth/

目录，因此后续运行会自动复用相同的凭据。

python

app = ParallelsearchApp()

若需要自定义OAuth提供商，可通过

auth

参数传入：

python

app = ParallelsearchApp(auth=my_oauth_provider)

Dependencies

依赖项

This skill requires the following Python packages:

```
mcp-skill
```

Install with uv:

bash

uv pip install mcp-skill

Or with pip:

bash

pip install mcp-skill

此技能需要以下Python包：

```
mcp-skill
```

使用uv安装：

bash

uv pip install mcp-skill

或使用pip安装：

bash

pip install mcp-skill

Python Usage

Python 使用方法

Use the generated app directly in async Python code:

python

import asyncio
from parallel_search.app import ParallelsearchApp


async def main():
    app = ParallelsearchApp()
    result = await app.web_search_preview(objective="example", search_queries="value")
    print(result)


asyncio.run(main())

在异步Python代码中直接使用生成的应用：

python

import asyncio
from parallel_search.app import ParallelsearchApp


async def main():
    app = ParallelsearchApp()
    result = await app.web_search_preview(objective="example", search_queries="value")
    print(result)


asyncio.run(main())

Async Usage Notes

异步使用注意事项

Every generated tool method is
```
async
```
, so call it with
```
await
```
.
Use these apps inside an async function, then run that function with
```
asyncio.run(...)
```
if you are in a script.
If you forget
```
await
```
, you will get a coroutine object instead of the actual tool result.
Be careful when mixing this with other event-loop environments such as notebooks, web servers, or async frameworks.

每个生成的工具方法都是
```
async
```
，因此需使用
```
await
```
调用。
在异步函数内使用这些应用，若在脚本中运行，则通过
```
asyncio.run(...)
```
执行该函数。
若忘记添加
```
await
```
，你将获得一个协程对象而非实际的工具结果。
在混合使用其他事件循环环境（如笔记本、Web服务器或异步框架）时需谨慎。

Discover Functions with the CLI

使用CLI发现函数

Use the CLI to find available apps, list functions on an app, and inspect a function before calling it:

bash

uvx mcp-skill list-apps
uvx mcp-skill list-functions parallel_search
uvx mcp-skill inspect parallel_search web_search_preview

Important: Add

.agents/skills

to your Python path so imports resolve correctly:

python

import sys
sys.path.insert(0, ".agents/skills")
from parallel_search.app import ParallelsearchApp

Or set the

PYTHONPATH

environment variable:

bash

export PYTHONPATH=".agents/skills:$PYTHONPATH"

Preferred: use
uv run
(handles dependencies automatically):

bash

PYTHONPATH=.agents/skills uv run --with mcp-skill python -c "
import asyncio
from parallel_search.app import ParallelsearchApp

async def main():
    app = ParallelsearchApp()
    result = await app.web_search_preview(objective="example", search_queries="value")
    print(result)

asyncio.run(main())
"

Alternative: use
python
directly (install dependencies first):

bash

pip install mcp-skill
PYTHONPATH=.agents/skills python -c "
import asyncio
from parallel_search.app import ParallelsearchApp

async def main():
    app = ParallelsearchApp()
    result = await app.web_search_preview(objective="example", search_queries="value")
    print(result)

asyncio.run(main())
"

使用CLI查找可用应用、列出某个应用的函数，以及在调用函数前查看其详情：

bash

uvx mcp-skill list-apps
uvx mcp-skill list-functions parallel_search
uvx mcp-skill inspect parallel_search web_search_preview

重要提示： 将

.agents/skills

添加到Python路径中，以便正确解析导入：

python

import sys
sys.path.insert(0, ".agents/skills")
from parallel_search.app import ParallelsearchApp

或设置

PYTHONPATH

环境变量：

bash

export PYTHONPATH=".agents/skills:$PYTHONPATH"

推荐方案：使用
uv run
（自动处理依赖项）：

bash

PYTHONPATH=.agents/skills uv run --with mcp-skill python -c "
import asyncio
from parallel_search.app import ParallelsearchApp

async def main():
    app = ParallelsearchApp()
    result = await app.web_search_preview(objective="example", search_queries="value")
    print(result)

asyncio.run(main())
"

替代方案：直接使用
python
（需先安装依赖项）：

bash

pip install mcp-skill
PYTHONPATH=.agents/skills python -c "
import asyncio
from parallel_search.app import ParallelsearchApp

async def main():
    app = ParallelsearchApp()
    result = await app.web_search_preview(objective="example", search_queries="value")
    print(result)

asyncio.run(main())
"