web-tool-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BROWSER_TYPES | No | Inherited environment setting for browser types. | |
| DEFAULT_TIMEOUT | No | Inherited environment setting for default timeout behavior. | |
| BROWSER_HEADLESS | No | Inherited environment setting controlling browser headless mode. | |
| WEB_EXTRACT_SAVE_DIR | No | Overrides the OS temporary directory where full extracted page text is saved. | |
| ENABLE_RELEVANCE_CHECKING | No | Inherited environment setting to enable relevance checking. | |
| FORCE_MULTI_ENGINE_SEARCH | No | Inherited environment setting to force multi-engine search. | |
| BROWSER_FALLBACK_THRESHOLD | No | Inherited environment setting for browser fallback threshold. |
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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| web_searchA | Search the web and return concise results with titles, URLs, and search snippets (5 by default). Use web_extract to read a result in detail. The query is passed through to the configured search backend, so operators such as site:domain, filetype:pdf, intitle:word, -term, and quoted phrases may work when supported by the backend. |
| web_extractA | Extract readable page content from one or more web page URLs. Returns cleaned Markdown/text directly without LLM summarization. Pages within the character budget (15,000 by default) are returned whole; longer pages return a head-and-tail window and save the complete text to a local file, with a path and read_file instructions for paging through the omitted middle. PDF URLs are accepted as inputs, but PDF text extraction requires a PDF reader dependency not included in this build. Inline images are represented as [IMAGE: alt] and linked image URLs are preserved. If a page fails, times out, or requires JavaScript, login, or clicks, use a browser tool instead. |
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 2 tools
web_search and web_extract have clearly distinct roles: discovery vs. full-page reading. The descriptions explicitly cross-reference each other, telling the agent to use web_search first and web_extract for detail.
Both tools follow a strict web_verb pattern (web_search, web_extract) with snake_case throughout. The convention is predictable and easy to extend.
Two tools form a coherent minimal pair but feel thin for a web utility server, lacking follow-up operations like opening/crawling many links or handling JS-heavy pages. It is borderline under-scoped rather than inappropriate.
The core search-then-extract workflow is complete, including pagination guidance for long pages. Minor gaps exist around JavaScript/login-protected pages and PDF extraction, though the descriptions explicitly point to external browser tools for those cases.