web-search-agent
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CHROME_PATH | No | Chrome for Testing 可执行文件路径 | D:/app/chrome-win64/chrome.exe |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| web_search_bingA | 使用 Bing 搜索引擎执行网络搜索。输入：query（搜索关键词）和 num（返回结果数量，默认10）。返回：包含标题、URL和摘要的搜索结果列表。 |
| read_webpageA | 访问指定 URL，提取并清洗页面正文内容，返回干净的 Markdown 格式文本。输入：url（网页地址）。返回：包含标题和 Markdown 内容的对象。 |
| get_current_timeA | 获取当前时间信息，包括当前年份、去年年份、前年年份等。用于搜索最新动态时动态获取年份信息。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: fetching current time, reading a webpage, and performing a web search. There is no functional overlap.
All tools use snake_case and a verb_noun pattern. However, 'web_search_bing' includes the search engine name, which deviates slightly from the simpler 'get_' and 'read_' patterns.
Three tools is on the lower end but appropriate for a focused web search agent. The core functionalities of search and page reading are covered, with an extra time utility.
The tool set covers basic web search and content retrieval, but lacks options like filtering by date, searching multiple engines, or managing search history. The time tool is a niche addition.