Ref
by ref-tools · Web & Browser · mcp-server, npm
Integrates with Ref.tools documentation search service to provide curated technical documentation access, web search fallback, and URL-to-markdown conversion for efficient developer reference during coding workflows.
This MCP server provides AI assistants with access to technical documentation through Ref.tools, a specialized documentation search service that indexes APIs, frameworks, libraries, and other technical resources. Built with TypeScript using the Model Context Protocol SDK and axios, it offers three core tools: documentation search that queries curated technical docs with contextual relevance, web search as a fallback for broader queries, and URL reading that converts web pages to markdown for easy consumption. The implementation supports both legacy stdio transport and experimental streamable HTTP modes, requires a Ref API key for authentication, and can be configured to disable web search if users prefer alternative search providers, making it valuable for developers and AI coding assistants that need up-to-date, token-efficient access to technical documentation during development workflows.
Source: https://github.com/ref-tools/ref-tools-mcp
Install
npx -y ref-tools-mcpTags: mcp-server, npm
⭐ 1,026 GitHub stars · Source: pulsemcp
About Web & Browser MCP servers and Claude skills
Web & Browser MCP servers extend what AI agents can do inside Claude Code, Cursor, Copilot, Codex, and Windsurf. The Skiln directory indexes 16,000+ such integrations across 22 categories.
Ref is one of hundreds of Web & Browser entries indexed on Skiln. Browse the full Web & Browser category or the complete directory of Claude skills, MCP servers, agents, commands, and hooks.
Related Web & Browser MCPs and skills
- OpenAI o3 Search by yoshiko-pg
Provides web search capabilities using OpenAI's o3 model with configurable reasoning effort levels for finding current information and solving complex problems beyond traditional search engines.
- Omnisearch by spences10
Unifies search and content processing by dynamically selecting optimal providers like Tavily, Brave, and Perplexity to enable flexible information retrieval and enhancement across multiple domains.
- Web Research by mzxrai
Research topics using Google search and web scraping.
- EVM Blockchain by mcpdotdirect
Integrates with EVM-compatible blockchains to enable querying data, transferring tokens, reading smart contracts, and resolving ENS names across Ethereum, Optimism, Arbitrum, and Base networks.
- Claude Talk to Figma by arinspunk
Enables direct control over Figma designs through WebSocket communication for document inspection, element creation and modification, text manipulation, component management, and export capabilities for automated design workflows and content localization.
- Hyperbrowser by hyperbrowserai
Enables web browsing capabilities through tools for content extraction, link following, and browser automation with customizable parameters for scraping, data collection, and web crawling tasks.
- Web Fetcher by jae-jae
Fetches and extracts web content using Playwright's headless browser capabilities, delivering clean, readable content from JavaScript-heavy websites in HTML or Markdown format for research and information gathering.
- DeepWiki Markdown Converter by regenrek
Converts DeepWiki repositories into well-formatted Markdown, maintaining links between pages while removing headers, footers, navigation elements, and ads for clean documentation extraction.
Frequently asked questions
How do I install Ref?
Add the install command above to your Claude Code, Cursor, or Windsurf MCP configuration. Most servers register via npx, a local command, or a Docker image. Refer to the source repository for environment variables and credential requirements.
Which clients support Ref?
Any MCP-compatible client works: Claude Desktop, Claude Code CLI, Cursor, Windsurf, Zed, and VS Code with the official MCP extension. OpenAI Codex and GitHub Copilot increasingly support MCP via adapter bridges.
Is Ref free?
The server itself is typically open source. Any upstream service (API keys, paid tiers, hosted infrastructure) may have its own pricing. Check the source repository for details.