open-webSearch
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Server port | 3000 |
| PROXY_URL | No | Proxy server URL | http://127.0.0.1:7890 |
| USE_PROXY | No | Enable HTTP proxy | false |
| CORS_ORIGIN | No | CORS origin configuration | * |
| ENABLE_CORS | No | Enable CORS | false |
| DEFAULT_SEARCH_ENGINE | No | Default search engine | bing |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| searchB | Search the web using multiple engines (e.g., Baidu, Bing, DuckDuckGo, CSDN, Exa, Brave, Juejin(掘金)) with no API key required |
| fetchLinuxDoArticleC | Fetch full article content from a linux.do post URL |
| fetchCsdnArticleB | Fetch full article content from a csdn post URL |
| fetchGithubReadmeC | Fetch README content from a GitHub repository URL |
| fetchJuejinArticleA | Fetch full article content from a Juejin(掘金) post URL |
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 5 tools
Each tool has a clearly distinct purpose: four tools fetch content from specific platforms (CSDN, GitHub, Juejin, Linux.do), while the search tool performs a general web search across multiple engines. There is no overlap in functionality, making tool selection straightforward.
The naming is mostly consistent with a 'fetchX' pattern for four tools (fetchCsdnArticle, fetchGithubReadme, fetchJuejinArticle, fetchLinuxDoArticle), but the search tool deviates by using a simple verb without a noun. All tools use camelCase, so the convention is uniform, but the pattern is not fully applied across all tools.
With 5 tools, the count is well-scoped for the server's purpose of open web search and content fetching. Each tool serves a specific, useful function without redundancy, making the set efficient and manageable for agents.
The tool surface covers fetching content from specific platforms and general web search, but there are notable gaps. For example, there is no tool to fetch content from other common sources (e.g., news sites, blogs beyond the listed ones), and no advanced search capabilities like filtering or pagination, which could limit agent effectiveness in broader web tasks.