Skip to main content
Get $10 free credits for the Valyu API when you sign up at Valyu!
Valyu MCP Server enables AI assistants like Claude to perform real-time searches through the Valyu Deepsearch API, allowing them to access up-to-date information from the web, academic journals and textbooks, and financial data. It is open-source, checkout GitHub.

Remote Valyu MCP

Connect directly to Valyu’s hosted MCP server (instead of running it locally).

Remote Valyu MCP URL

https://mcp.valyu.ai/mcp?valyuApiKey=your-valyu-api-key
Get your API key from platform.valyu.ai/user/account/apikeys.

Configuration

Claude Desktop Configuration

Add this to your Claude Desktop configuration file:
{
  "mcpServers": {
    "valyu": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.valyu.ai/mcp?valyuApiKey=your-valyu-api-key"
      ]
    }
  }
}

Claude Code Configuration

Add the Valyu MCP server to Claude Code using the CLI:
claude mcp add --transport http valyuMcp "https://mcp.valyu.ai/mcp?valyuApiKey=YOUR_API_KEY"

OpenAI Responses API

This is how to try out the Valyu MCP server in the OpenAI playground. Easily hook up the Valyu MCP server to the OpenAI Responses API:
from openai import OpenAI
client = OpenAI()

response = client.responses.create(
  model="gpt-5",
  input=[],
  text={
    "format": {
      "type": "text"
    }
  },
  reasoning={},
  tools=[
    {
      "type": "mcp",
      "server_label": "Valyu",
      "server_url": "https://mcp.valyu.ai/mcp?valyuApiKey=VALYU_API_KEY",
      "allowed_tools": [
        "valyu_search",
        "valyu_academic_search",
        "valyu_financial_search",
        "valyu_contents"
      ],
      "require_approval": "always"
    }
  ],
  temperature=1,
  max_output_tokens=2048,
  top_p=1,
  store=True
)

Available Tools

Valyu MCP provides 6 specialized tools for comprehensive information retrieval across multiple domains:
ToolDescription
valyu_searchThe world’s most powerful web search that returns full page content. Perfect for current events, technical documentation, and any web-accessible information.
valyu_academic_searchFull-text academic search across ArXiv, PubMed, and scholarly databases. Returns peer-reviewed papers with complete metadata including authors, citations, DOI, and references.
valyu_financial_searchReal-time financial intelligence covering stocks (NASDAQ/NYSE), crypto, forex, earnings reports, balance sheets, insider transactions, and market movers.
valyu_sec_searchSearch SEC filings (10-K, 10-Q, 8-K) using natural language queries. Find specific sections like MD&A, risk factors, or business strategy from any public company’s regulatory filings.
valyu_company_researchNEW! Comprehensive company intelligence reports in ~10 seconds. Automatically gathers and synthesizes information across business overview, leadership, products, funding, competitors, financials, and recent news. Uses parallel execution to deliver complete reports 4x faster than sequential searches.
valyu_contentsExtract clean, structured content from any URL. Returns full page content in markdown format with metadata extraction.

Tool Details

When to use: General knowledge, current events, news, technical documentation Parameters:
  • query (string, required): Your search query
    • Example: "who won the superbowl this year"
    • Example: "latest developments in quantum computing"
  • max_num_results (number, optional): 1-20 results (default: 10)
Returns: Full web page content with publication dates and source information

valyu_academic_search - Academic Papers

When to use: Literature reviews, research validation, academic citations Parameters:
  • query (string, required): Academic research query
    • Example: "transformer architecture improvements"
    • Example: "recent papers on AI in healthcare"
  • max_num_results (number, optional): 1-20 results (default: 10)
Returns: Papers with enhanced metadata:
  • Authors and citations
  • Publication dates and DOI
  • Citation counts
  • References
  • Full paper content
Data sources: ArXiv, PubMed, scholarly journals, research databases

valyu_financial_search - Market Data

When to use: Investment research, portfolio management, market monitoring Parameters:
  • query (string, required): Financial data query
    • Example: "AAPL stock price and recent performance"
    • Example: "Tesla latest quarterly earnings"
    • Example: "Bitcoin volatility trends"
  • max_num_results (number, optional): 1-20 results (default: 10)
Returns: Real-time financial data including:
  • Live stock prices (NASDAQ, NYSE)
  • Cryptocurrency rates
  • Forex data
  • Earnings reports (quarterly/annual)
  • Balance sheets & income statements
  • Cash flow statements
  • Insider transactions
  • Market movers (gainers/losers)
  • Dividend information

valyu_sec_search - SEC Filings

When to use: Due diligence, compliance monitoring, competitive analysis, investment research Parameters:
  • query (string, required): Natural language query about SEC filings
    • Example: "Tesla's latest 10-K MD&A section"
    • Example: "Apple risk factors from FY2023"
    • Example: "Microsoft's business strategy from annual report"
  • max_num_results (number, optional): 1-20 results (default: 5)
  • response_length (string, optional): Content length control
    • "short": ~25,000 characters
    • "medium": ~50,000 characters (default)
    • "large": ~100,000 characters
    • "max": Up to 400,000 characters (complete filings)
Filing types supported: 10-K (annual), 10-Q (quarterly), 8-K (current events) Searchable sections: MD&A, risk factors, business strategy, financial condition, legal proceedings, executive compensation, and more

valyu_company_research - Company Intelligence

When to use: Comprehensive company analysis, competitive intelligence, due diligence Why it’s fast: Queries all 9 sections in parallel simultaneously, delivering complete reports in ~10-15 seconds instead of 45-60 seconds with sequential searches Parameters:
  • company (string, required): Company identifier
    • Company name: "Apple"
    • Ticker symbol: "AAPL"
    • Domain: "apple.com"
  • sections (array, optional): Specific sections to include
    • Options: ["summary", "leadership", "products", "funding", "competitors", "filings", "financials", "news", "insiders"]
    • Default: All applicable sections
Available sections:
  • summary: Business overview, industry, headquarters, key products
  • leadership: CEO, executives, board members with backgrounds
  • products: Main offerings, target markets, product strategy
  • news: Recent developments from last 30 days
  • funding: Funding rounds, investors, valuation (for private companies)
  • competitors: Direct competitors and market positioning
  • filings: SEC filing highlights (public companies only)
  • financials: Stock performance, market cap, revenue, P/E ratio
  • insiders: Insider trading activity from last 90 days
Returns: Comprehensive markdown report with citations and structured data Features:
  • Blazing fast: Full 9-section report in ~10-15 seconds (4x faster than sequential)
  • 🛡️ Smart filtering: Automatically excludes unavailable data
  • 📊 Structured reports: Markdown format with source citations
  • 🔄 Adaptive: Works for both public and private companies
  • 🎯 Comprehensive: Single request covers all company dimensions

valyu_contents - URL Extraction

When to use: Content extraction, article parsing, documentation scraping Parameters:
  • urls (array, required): URLs to process (max 10 per request)
    • Example: ["https://example.com/article", "https://docs.example.com/guide"]
Returns: Clean markdown content with metadata (author, publish date, etc.) Features:
  • Automatic content cleaning
  • Markdown formatting
  • Metadata extraction
  • Support for paywalled content (where accessible)

Usage Examples

Once configured, you can ask your AI assistant to perform various types of searches using natural language:

Web Search Examples

  • “Who won the superbowl this year?”
  • “Latest developments in quantum computing”
  • “Best practices for React server components”

Academic Research Examples

  • “Find recent papers on transformer architecture improvements”
  • “CRISPR gene editing therapeutic applications”
  • “Climate change mitigation strategies peer-reviewed studies”

Financial Analysis Examples

  • “AAPL stock price and recent performance”
  • “Tesla latest quarterly earnings and revenue trends”
  • “Bitcoin price trends this week”

SEC Filings Examples

  • “Tesla’s latest 10-K MD&A section”
  • “Apple risk factors from FY2023 annual report”
  • “Microsoft’s business strategy from recent 10-K”

Company Research Examples

  • “Research the company Anthropic - give me everything you can find”
  • “Analyze Apple’s competitive position and recent financials”
  • “Get me a full company profile for Stripe including funding and leadership”

Content Extraction Examples

  • “Extract and summarize this article: https://techcrunch.com/…”
  • “Get the full content from these documentation pages: [URLs]“

Features

  • 6 Specialized Tools: Web search, academic papers, financial data, SEC filings, company research, and content extraction
  • ⚡ Lightning Fast: Company research tool uses parallel execution for 4x faster results
  • 🛡️ Smart Filtering: Automatically excludes insufficient or unavailable data
  • 📊 Rich Metadata: Academic citations, financial metrics, filing dates, and source tracking
  • 🔍 Natural Language Queries: Search SEC filings and company data using plain English
  • 💰 Real-time Data: Live stock prices, crypto rates, market movers, and insider trading
  • 📚 Full-text Search: Complete academic papers, web pages, and SEC documents
  • 🎯 Comprehensive Reports: Auto-generated company intelligence with citations
  • OpenAI Compatible: Direct integration with OpenAI’s Responses API

Transport Protocol

Uses HTTP/SSE transport (JSON-RPC over HTTP with Server-Sent Events) for:
  • ✅ Direct OpenAI Responses API compatibility
  • ✅ Real-time streaming responses
  • ✅ Stateless authentication via URL parameters
  • ✅ Standard MCP protocol compliance

Pricing

Valyu MCP operates on a usage-based pricing model through Valyu’s Deepsearch API. You can control costs by setting the maxPrice parameter in the URL.

Cost Control

Set the maxPrice parameter to limit spending per search operation:
https://mcp.valyu.ai/mcp?valyuApiKey=your-key&maxPrice=50
  • Default: 100 CPM ($0.10) maximum cost per search
  • Minimum: 1 CPM ($0.01) minimum cost per search
  • Recommended: 30-100 CPM (0.030.03-0.10) for most use cases
Visit Valyu Pricing for detailed cost information.

Additional Resources

Support

I