Web-curl MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CX_GOOGLE_SEARCH | No | Your Custom Search Engine ID | |
| APIKEY_GOOGLE_SEARCH | No | Your Google API key for Custom Search API |
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 |
|---|---|
| fetch_webpageC | Retrieve text content from a web page |
| fetch_apiC | Make a REST API request with various methods, headers, and body. |
| google_searchC | Search the web using Google Custom Search API. Requires google_search_config resource. |
| smart_commandC | Free-form command: automatically fetch if a link is detected, automatically search if a search query is detected. |
| download_fileC | Download a file from a given URL to a specified folder. |
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
There is significant overlap between fetch_api, fetch_webpage, and download_file, as all three involve retrieving content from URLs, with fetch_api being a general-purpose tool that could subsume the others. Smart_command further blurs boundaries by automatically choosing between fetching and searching, potentially causing confusion about when to use the dedicated tools. However, google_search is clearly distinct for search operations.
The naming is inconsistent with mixed conventions: fetch_api and fetch_webpage use a verb_noun pattern, download_file uses verb_noun but with a different verb style, google_search is a compound noun, and smart_command uses an adjective_noun pattern. This lack of a predictable naming scheme makes the tool set harder to navigate and remember.
With 5 tools, the count is well-scoped for a web/curl server, covering key operations like downloading files, making API requests, fetching web content, searching, and a smart utility. Each tool appears to serve a purpose without obvious bloat or thinness, fitting the server's domain appropriately.
The tool set covers core web interaction tasks: downloading files, API requests, webpage fetching, and web searching, with smart_command adding flexibility. Minor gaps might include more advanced operations like handling cookies or sessions, but the surface is largely complete for basic web utilities, allowing agents to perform common workflows without major dead ends.