MCP server for web retrieval, search, and scraping capabilities
Three tools with clear, detailed descriptions and well-structured input schemas. Naming is verb-based and action-oriented (web_search, web_search_images, web_scrape). Descriptions are comprehensive (150-250 chars) with practical guidance on usage, operators, and limits. All parameters have types and descriptions. However, output schemas are not explicitly documented in the source code provided, and error handling guidance is minimal. Tool composition is sound, each performs one clear action, and web_scrape accepts arrays for batch processing.
Downloads pages by their links and returns the main text as markdown. Links are fetched in parallel; a single call handles up to 10 of them, so batch all links you need into one call instead of calling the tool per link. Size: the 'max_chars' limit applies to each page separately, not to the whole response — 5 links stay under the limit each and the response holds all 5 texts. The limit counts characters, not tokens. A page cut short ends with '[truncated]' and its 'truncated' field is set; the cut-off part cannot be fetched afterwards, so treat what you got as all there is for that page.
Searches the web for one or more queries and returns snippets with links. Queries run in parallel. IMPORTANT: Always write search queries in English for best results and relevance. For images use the 'web_search_images' tool; both tools can be called in the same turn when a query needs text and images. Freshness: set the 'date' field to restrict results by recency — 'd' (past day), 'w' (past week), 'm' (past month), 'y' (past year). Use it to prefer the most recent pages when the user asks about news or anything time-sensitive; leave it empty for all time. Query operators (put them inside the query string itself): 'site:example.com term' limits the search to one site; 'filetype:pdf term' restricts to a file type; double quotes "exact phrase" force an exact match; a leading '-' excludes a word (term -foo); 'intitle:term' requires the word in the page title. Operators can be combined, e.g. 'site:arxiv.org filetype:pdf transformers'.
Searches for images by one or more queries, executed in parallel. IMPORTANT: Queries must be in English ONLY. Freshness: set the 'date' field to restrict results by recency — 'd' (past day), 'w' (past week), 'm' (past month), 'y' (past year); leave it empty for all time. Query operators can be embedded in the query string: 'site:example.com term' limits to one site, double quotes "exact phrase" force an exact match, and a leading '-' excludes a word.
Output schemas not documented in source code. The handler implementations exist (app/internal/transport/mcp/web/handler.go referenced) but the actual response structure is not visible in the provided code.
Error handling guidance is minimal. Descriptions do not explain what errors the tools return or how agents should handle timeout_ms expiration, failed scrapes, or search API failures.
web_scrape 'max_chars' parameter description could clarify the per-page vs. total behavior more explicitly. The description states 'applies per page, not to total response' but does not specify whether truncation is silently lossy or if the agent should handle '[truncated]' markers programmatically.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 63 | 2025-06-18+ | v2 |