Parallax

    Product

    Insights

    MCPDocs
    Login
    Parallax
    Blog/API and MCP Integrations
    guide

    Connecting Parallax to Claude Desktop via MCP: Real-Time Factor Research Setup

    Step-by-step setup guide to connect Parallax to Claude Desktop using Model Context Protocol (MCP) for conversational factor screening and risk analytics.

    Parallax ResearchSeptember 22, 20262 min read
    Model Context ProtocolMCPClaude DesktopQuantitative ResearchAI Integrations

    Conversational Factor Research via Model Context Protocol

    The Model Context Protocol (MCP) is an open standard that enables large language model applications to interact securely with external data systems and analytical tools. By integrating Parallax's MCP server with Claude Desktop, quantitative analysts and portfolio managers can perform conversational factor screening, execute risk queries, and retrieve real-time stock scores directly within their AI research workspace.

    This integration bridges quantitative finance models with natural language interfaces, allowing research teams to analyze complex portfolio exposures without context switching between standalone tools.

    Setup Instructions for Claude Desktop

    Connecting Claude Desktop to Parallax requires adding the remote MCP endpoint to your local configuration file.

    Step 1: Open the Claude Desktop Configuration File

    Locate the claude_desktop_config.json configuration file on your operating system:

    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%\Claude\claude_desktop_config.json

    Step 2: Add the Parallax MCP Configuration Block

    Add the parallax server definition using mcp-remote to connect to the verified Parallax endpoint at mcp.chicago.global:

    {
      "mcpServers": {
        "parallax": {
          "command": "npx",
          "args": ["-y", "mcp-remote", "https://mcp.chicago.global/api/mcp"]
        }
      }
    }
    

    Step 3: Complete Authentication and Restart

    Restart Claude Desktop. On first launch, a browser window opens automatically to complete OAuth authentication with your Parallax account and authorize analytical tool access.

    Executing Conversational Factor Queries

    Once configured, Claude Desktop has direct access to Parallax's scoring engine. Analysts can submit conversational research prompts such as:

    • "Screen for US equities in the top quartile of Quality and Defensive scores with low leverage."
    • "Decompose the factor profile of Microsoft and Apple across Value, Quality, Momentum, and Size."
    • "Evaluate the risk implications of rotating 5% of portfolio weight from momentum winners into defensive dividend payers."

    To integrate Parallax analytics into automated internal scripts, consult the Parallax developer documentation and review our AI technology architecture.

    Sources

    1. 1.https://modelcontextprotocol.io/specification/2024-11-05/server/tools
    2. 2.https://mcp.chicago.global
    3. 3.https://docs.chicago.global/development
    4. 4.https://docs.anthropic.com/en/docs/agents-and-tools/mcp

    Important disclosure

    Technical integration guide for the Model Context Protocol (MCP) standard. Parallax MCP server is operated by Chicago Global; Model Context Protocol is an open standard.

    This material is educational and general in nature. It is not individualized investment advice, an offer, or a recommendation to buy, sell, or hold any security.

    Related research

    API and MCP Integrationsguide

    Asynchronous Portfolio Analysis via REST API: Polling Patterns and Job Lifecycle Management

    Architect resilient integrations with Parallax's async portfolio analysis API. Master HTTP 202 job creation, exponential backoff polling, and result retrieval.

    Sep 22, 20262 min read
    API and MCP Integrationsanalysis

    Building Thematic Equity Universes from Unstructured Briefs Using NLP and Factor Filters

    Convert unstructured thematic briefs into disciplined equity universes by pairing natural language extraction with quantitative Quality and Valuation filters.

    Sep 22, 20262 min read
    API and MCP Integrationsanalysis

    Multi-Agent Quantitative Research Desks: Grounding LLM Workflows in Deterministic Factor Engines

    Ground autonomous multi-agent research workflows in deterministic financial data using Parallax MCP servers to eliminate hallucinations in quantitative analysis.

    Sep 22, 20262 min read
    ParallaxBy Chicago Global

    Quantitative investment analytics platform for institutional and accredited investors.

    Theme:

    Product

    • Features
    • Technology
    • Pricing
    • Comparison
    • Parallax MCP
    • Docs

    Insights

    • Blog
    • Research
    • Media
    • Use Cases
    • AI Team

    Company

    • Chicago Global
    • About Us
    • Contact
    • Login
    © 2026 Chicago Global Capital Pte. Ltd.
    UEN: 201734851Z·30 Cecil Street #16-08, Singapore 049712
    TermsPrivacyDisclaimers

    Past performance does not guarantee future results. All investments involve risk of loss. See our Terms of Service for complete information.