Vybsly MCP
Provides tools for extracting full content from arXiv articles and searching for research papers, with support for strict-mode filters to enforce research domains.
Hosts the MCP server source code repository, providing access to documentation, issues, and contributions for the Vybsly MCP integration.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Vybsly MCP what's the current price of Bitcoin and recent crypto news?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Works with Claude Desktop, Cursor, Windsurf, or any MCP-compatible client.
Why Vybsly
Other search APIs return snippets. Vybsly returns up to 30,000 characters of clean, extracted content per result — the full page, ready for RAG and agent context. No scraping, no follow-up fetches.
29M+ web pages indexed with full content
25M+ encyclopedia articles (federated search via
/knowledge)Strict mode: enforce research/news/educational domains with allowlists
Real-time data: stocks, crypto, weather, news, sports odds, maps
8× cheaper than Tavily, $9/mo for 10,000 queries
Related MCP server: Gemini Google Web Search MCP
Install
npm install -g vybsly-mcpOr use directly with npx:
npx vybsly-mcpGet an API key
Sign up free at vybsly.ai/developers.html — 1,000 free queries/month, no credit card required.
Claude Desktop setup
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"vybsly": {
"command": "npx",
"args": ["-y", "vybsly-mcp"],
"env": {
"VYBSLY_API_KEY": "your_api_key_here"
}
}
}
}Restart Claude Desktop. Vybsly tools will appear in the tool picker.
Cursor / Windsurf setup
Add to your .cursor/mcp.json or equivalent:
{
"mcpServers": {
"vybsly": {
"command": "npx",
"args": ["-y", "vybsly-mcp"],
"env": { "VYBSLY_API_KEY": "your_api_key_here" }
}
}
}Available tools
Tool | Purpose |
| Full-content web search with strict-mode filters |
| Federated web + encyclopedia search |
| Extract full content from any URL (JS-rendered) |
| Ask a question, get a sourced AI answer |
| Live stock prices |
| Live cryptocurrency data |
| Current weather + 5-day forecast |
| Recent news articles |
| Live sports betting lines |
| Address → coordinates |
| Turn-by-turn driving directions |
Examples (natural language in Claude)
"Search for recent CRISPR research papers only" → uses
vybsly_searchwithresearch=true, strict=true
"What's Einstein's most famous equation?" → uses
vybsly_knowledge— gets encyclopedia + web results
"Extract the article at https://arxiv.org/abs/2501.00001" → uses
vybsly_extract— returns full markdown
"What's AAPL trading at and how's the weather in NYC?" → uses
vybsly_stocks+vybsly_weatherin parallel
Environment variables
Variable | Description | Default |
| Your API key (optional for free tier) | (none) |
| API base URL |
|
Free vs paid
Free: 1,000 queries/month, 50/day
Starter ($9/mo): 10,000/month
Pro ($29/mo): 50,000/month
Business ($99/mo): 250,000/month
Enterprise: Contact sales
Upgrade anytime at vybsly.ai/developers.html.
Links
Website: vybsly.ai
API docs: vybsly.ai/docs.html
Developer portal: vybsly.ai/developers.html
License
MIT © Blue Fusion Labs
Available Tools
11 toolsvybsly_askB
Ask a question, get a sourced AI answer (like Perplexity). Returns a synthesized answer plus the source URLs used.
Inputs: question (required), max_sources.
vybsly_cryptoC
Live cryptocurrency prices and market data.
Inputs: symbol (required).
vybsly_directionsC
Get turn-by-turn driving directions between two places.
Inputs: from (required), to (required).
vybsly_extractA
Extract full content from any URL with JavaScript rendering. Returns clean markdown/text, title, description, images, and links. Works on React/Vue SPAs. Use when you need content from a specific URL.
Inputs: url (required), format.
vybsly_geocodeB
Convert a street address or place name into latitude/longitude coordinates.
Inputs: address (required).
vybsly_knowledgeA
Federated search: web index + structured encyclopedia in one call. Returns results tagged by source (vybsly/vybpedia). Best for factual questions needing both breadth (web) and authority (encyclopedia).
Inputs: query (required), limit, strict, research.
vybsly_newsA
Recent news articles with publish dates. Use for time-sensitive queries.
Inputs: query (required), hours.
vybsly_oddsA
Live sports betting odds from multiple bookmakers (FanDuel, DraftKings, BetMGM). Useful for sports analysis.
Inputs: sport, team.
vybsly_searchA
Full-content web search across 29M+ pages. Returns up to 30K chars per result — perfect for RAG and agent context. Supports strict-mode filters (research/news/educational) and federation with encyclopedia.
Inputs: query (required), limit, mode, strict, +6 more.
vybsly_stocksA
Live stock prices for one or more ticker symbols. Auto-saves to historical almanac for trend lookups.
Inputs: symbols (required).
vybsly_weatherA
Current weather and 5-day forecast for a city.
Inputs: city (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 11 tools
Each tool has a unique and distinct purpose, clearly differentiated by name and description. No two tools overlap in functionality, making it easy for an agent to select the right tool.
All tools follow a consistent 'vybsly_<noun>' pattern in snake_case, with verbs implicit in the noun (e.g., 'ask', 'search'). This provides a predictable and uniform naming convention.
With 11 tools, the server offers a broad range of capabilities without being overwhelming. However, the scope is quite broad (crypto, directions, weather, etc.), which might feel slightly unfocused, but the count itself is appropriate.
The server covers many common user needs (search, news, weather, stocks, etc.), but lacks some typical assistant features like email or calendar integration. Nonetheless, it provides a solid set for general queries.
Maintenance
Related MCP Connectors
Web search API and MCP server for developers building AI agents.
One MCP server for all web data. Scrape, search, crawl, and AI research in one install.
Live AI-native web search with citations. One tool for every MCP client. Flat per-request pricing.
Free web search for AI agents. No API key required. Hosted MCP in active development.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides comprehensive search capabilities including web search, content extraction, news search, academic search, and AI-powered multi-source research. Enables natural language access to web content and research through a production-ready MCP server.MIT
- AlicenseBqualityDmaintenanceAn MCP server that enables AI models to perform Google Web searches using the Gemini API, complete with citations and grounding metadata for accurate information retrieval. It is compatible with Claude Desktop and other MCP clients for real-time web access.13Apache 2.0
- AlicenseBqualityDmaintenanceMCP server providing search, extract, map, and crawl tools powered by Tavily for real-time web data access.4MIT
- AlicenseAqualityDmaintenanceMCP server for web search powered by Google AI Mode (Gemini). Enables any AI agent to search the web in real-time for free and without rate limits.2189MIT