S&P 500 MCP Server
MCP server for querying S\&P 500 company data from Supabase, providing tools for company info, financials, price data, news, officers, and SEC filings.
README
S&P 500 MCP Server
An MCP (Model Context Protocol) server and Next.js web app for querying S&P 500 company data from Supabase. It exposes MCP tools for company fundamentals, annual financial metrics, historical price data, news sentiment, officers, and SEC filings, plus a web UI and embedded MCP App resources for browsing and testing those tools.
Tools
| Tool | Description |
|---|---|
get_company_info |
Company basics, financials, leadership, address, and business summary |
get_company_financials |
Annual financial metrics with chart-ready trends and matrix output |
get_company_price_data |
Historical daily OHLCV price rows with date filters |
get_company_news |
Recent company news with sentiment filtering |
get_company_officers |
Executive officers and compensation |
get_company_filings |
SEC filings history, with filing type and date filters |
search_companies is an internal symbol resolver, not an exposed MCP tool. User queries are resolved through getCompanySymbol.
Tech Stack
- Workspace: pnpm 10.33.3 + Turborepo
- Runtime: Node 22 (
.nvmrc) - Web app: Next.js 16 App Router, React 19, TypeScript strict mode (
apps/web) - MCP Apps: Vite single-file React pages built from
apps/web-appand served as tool UI resources - MCP:
mcp-handleratapps/web/app/[transport]/route.ts;/sseis the public SSE endpoint - Database: Supabase client at
apps/web/app/[transport]/utils/supabase.ts - UI: shared shadcn/Tailwind primitives in
packages/ui
Getting Started
Prerequisites
- Node.js 22
- pnpm 10
- Supabase project with the S&P 500 data tables used by the tools
Local Development
- Install dependencies:
pnpm install
- Create a local env file with Supabase credentials:
SUPABASE_URL=your_supabase_url
SUPABASE_ANON_KEY=your_supabase_anon_key
MCP_MAX_DURATION=60
REDIS_URL=your_redis_url
LOGO_DEV_TOKEN=your_logo_dev_publishable_key
SUPABASE_URL and SUPABASE_ANON_KEY are required. REDIS_URL is only needed for production SSE. LOGO_DEV_TOKEN is required for the /api/logo/* proxy.
- Build the embedded MCP App HTML resources:
pnpm --filter @apps/web-app build
- Start the apps:
pnpm dev
The Next.js web app runs on http://localhost:3000; the MCP endpoint is http://localhost:3000/sse. The apps/web-app dev server proxies /sse to port 3000 when run separately.
Commands
pnpm dev # Start apps/* dev tasks via Turbo
pnpm build # Build apps/web and apps/web-app via Turbo
pnpm start # Start production server for apps/web
pnpm type-check # Type-check apps/web and apps/web-app
pnpm lint # ESLint + Prettier rule checks
Focused commands:
pnpm --filter @apps/web dev
pnpm --filter @apps/web-app dev
pnpm --filter @apps/web-app build
pnpm exec tsc -p apps/web/tsconfig.json --noEmit
pnpm exec tsc -p apps/web-app/tsconfig.json --noEmit
pnpm exec tsc -p packages/ui/tsconfig.json --noEmit
Testing
Tests are integration tests that connect a real MCP client to http://localhost:3000/sse, so start the dev server first:
pnpm --filter @apps/web-app build
pnpm dev
pnpm test
Run a single tool test:
pnpm vitest run apps/web/tests/tools/get-company-info-tool.test.ts
Generate coverage:
pnpm coverage
Project Layout
apps/web/
app/[transport]/route.ts MCP GET/POST/DELETE handler
app/[transport]/tools/ MCP tool registrations
app/[transport]/utils/ Supabase, symbol resolution, summaries
app/api/tools/call/route.ts HTTP proxy for the web tool tester
app/tools/ Tool catalog page
components/ App-specific UI
tests/tools/ MCP integration tests
apps/web-app/
src/pages/ Embedded MCP App pages, one per tool
src/components/ MCP App UI components
scripts/build-pages.js Builds each page into dist/*.html
dist/ Generated single-file HTML resources
packages/ui/
src/components/ Shared shadcn UI primitives
src/styles/globals.css Shared Tailwind CSS
apps/web/app/[transport]/tools/app-resource.ts reads generated HTML from apps/web-app/dist, so rebuild apps/web-app after changing embedded MCP App pages.
Vercel Deployment
- Requires Fluid compute
MCP_MAX_DURATIONdefaults to60; set a higher duration for long-running production calls when your Vercel plan supports it- SSE is enabled (
disableSse: false); production SSE requires Redis viaREDIS_URL
Docs
Full guides and examples: https://sp500-mcp.vercel.app/
Contributing
Feel free to dive in! Open an issue or submit PRs.
Standard Readme follows the Contributor Covenant Code of Conduct.
Contributors
This project exists thanks to all the people who contribute.
<a href="https://github.com/zhensherlock/sp500-mcp-server/graphs/contributors"> <img src="https://contrib.rocks/image?repo=zhensherlock/sp500-mcp-server" /> </a>
License
GNU Affero General Public License v3.0 © MichaelSun
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.