xby-web-research-assistant
一个提供网络研究和发现功能的综合模型上下文协议（MCP）服务器，包含13种工具用于搜索、爬取和分析网络内容。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:xby-skill/xby-web-research-assistant#4b51b928b8289a81e6c2954469b75cded2e5858dXby Web Research Assistant 以 xby-web-research-assistant 发布，当前版本为 1.0.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
DeepSeek Harness (DSH) 的插件：网络研究助手
一个提供网络研究和发现功能的综合模型上下文协议（MCP）服务器，包含13种工具用于搜索、爬取和分析网络内容。
Returns version, downloads, license, dependencies, security status, and repository links. Use this to quickly evaluate libraries before adding them to your project.
Examples:
package_info("express", reasoning="Need web framework", registry="npm")
package_info("requests", reasoning="HTTP client for API", registry="pypi")
package_info("serde", reasoning="JSON serialization", registry="crates")
search_examples — Search for code examples, tutorials, and technical articles.
Optimized for finding practical examples and learning resources. Can optionally filter by time range for the most recent content. Perfect for learning new APIs, finding usage patterns, or discovering how others solve specific technical problems.
Content Types:
Time Ranges:
Examples:
search_examples("FastAPI dependency injection examples", content_type="code")
search_examples("React hooks tutorial", content_type="articles", time_range="year")
search_examples("Rust lifetime examples", content_type="both")
search_images — Search for high-quality stock images using Pixabay.
Returns royalty-free images that are safe to use. Perfect for finding photos, illustrations, and vector graphics for projects, presentations, or design work.
Image Types:
Examples:
search_images("mountain landscape", image_type="photo")
search_images("business icons", image_type="vector")
search_images("technology background", orientation="horizontal")
package_search — Search for packages by keywords or description across registries.
Use this to find packages that solve a specific problem or provide certain functionality. Perfect for discovering libraries when you know what you need but not the package name.
Examples:
package_search("web framework", reasoning="Need backend framework", registry="npm")
package_search("json parsing", reasoning="Data processing", registry="pypi")
github_repo — Fetch GitHub repository information and health metrics.
Returns stars, forks, issues, recent activity, language, license, and description. Use this to evaluate open source projects before using them.
Examples:
github_repo("microsoft/vscode", reasoning="Evaluate editor project")
github_repo("https://github.com/facebook/react", reasoning="Research UI framework")
translate_error — Find solutions for error messages and stack traces from Stack Overflow and GitHub.
Takes an error message or stack trace and finds relevant solutions with code examples. Automatically detects language and framework, extracts key error information, and searches for the best solutions ranked by votes and relevance.
Perfect for:
Examples:
translate_error("TypeError: Cannot read property 'map' of undefined", reasoning="Debugging React app crash")
translate_error("CORS policy: No 'Access-Control-Allow-Origin' header", reasoning="Fixing API integration", framework="FastAPI")
translate_error("error[E0382]: borrow of moved value", reasoning="Learning Rust ownership", language="rust")
api_docs — Search and fetch official API documentation with examples and explanations.
Documentation-first approach: fetches human-written docs with context, examples, and best practices. Much more useful than OpenAPI specs alone.
Discovery strategy:
No hardcoded URLs - works for ANY API by discovering docs dynamically.
Examples:
api_docs("stripe", "create customer", reasoning="Setting up payments")
api_docs("github", "create repository", reasoning="Automating repo creation")
api_docs("spartan", "button component", reasoning="Learning UI library")
extract_data — Extract structured data from web pages.
Extracts tables, lists, or specific fields from HTML pages and returns structured data. Much more efficient than parsing full page text.
Extract Types:
Examples:
extract_data("https://pypi.org/project/fastapi/", reasoning="Get package info")
extract_data("https://github.com/user/repo/releases", reasoning="Get releases", extract_type="list")
extract_data( "https://example.com/product", reasoning="Extract product details", extract_type="fields", selectors={"price": ".price", "title": "h1.product-name"} )
compare_tech — Compare multiple technologies, frameworks, or libraries side-by-side.
Automatically gathers information about each technology and presents a structured comparison to help make informed decisions.
Categories:
Examples:
compare_tech(["React", "Vue", "Svelte"], reasoning="Choose framework for new project")
compare_tech(["PostgreSQL", "MongoDB"], category="database", reasoning="Database for user data")
compare_tech(["FastAPI", "Flask"], aspects=["performance", "learning_curve"], reasoning="Python web framework")
get_changelog — Get changelog and release notes for a package.
check_service_status — Check if an API service or platform is experiencing issues.
# 格式: dsh plugin --profile <profile> add github:<owner>/<repo>
dsh plugin --profile web add github:xby_skill/xby-web-research-assistant
# 仅用于本地开发调试
dsh plugin --profile web add /absolute/path/to/xby-web-research-assistant
dsh web --profile web --patch /absolute/path/to/dsh-ocr-plugin/cordis.patch.yml
前往 小笨羊官网 注册并获取 API 密钥。