MCP2Tavily
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| search_webC | Search the web for information using Tavily API |
| search_web_infoC | 从网络搜索用户查询的信息 |
| get_url_contentC | Get the content from a specific URL using Tavily API |
| get_url_content_infoC | 从指定URL获取网页内容 |
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 4 tools
The tool set has severe ambiguity issues, with two pairs of tools that appear to be exact duplicates in different languages. get_url_content and get_url_content_info seem to perform identical functions (extracting content from a URL), as do search_web and search_web_info (searching the web). An agent would have no reliable way to choose between these overlapping tools.
The naming follows a mixed convention with some consistency issues. While all tools use snake_case, the pattern is inconsistent: two tools use simple verb_noun format (get_url_content, search_web) while two others add '_info' suffix (get_url_content_info, search_web_info). This creates confusion about whether the '_info' tools are different operations or just translations.
With only 4 tools, this feels thin for a web search/content extraction server, but the real problem is that these represent only 2 distinct operations duplicated across languages. The effective tool count is just 2, which is insufficient for comprehensive web interaction capabilities that might include filtering, advanced search parameters, or content analysis.
For a web search/content extraction server, there are significant gaps in the surface. While basic URL content fetching and web search are covered, there's no support for filtering search results, specifying search parameters, handling different content types, or any advanced web interaction features. The duplication across languages doesn't add functional coverage, leaving the tool set incomplete for sophisticated web tasks.