What can you do with this server?

Fetch real-time market data, news, earnings, watchlist scans, composite analysis, and Alpaca paper positions through MCP tools. * Quotes: market_quote returns real-time price, % change, day high/low, and previous close for a symbol. * News: market_news returns top 5 company-specific or general market headlines. * Earnings: market_calendar lists upcoming earnings for 1–30 days with EPS/revenue estimates when available. * Scanner: market_scan ranks up to 25 tickers by absolute % change. * Analysis: market_analyze combines quote momentum, news catalyst, and earnings proximity into a -100 to +100 score with confidence. * Broker: broker_positions reads open Alpaca paper positions if API keys are set; otherwise degrades gracefully. * Output: Every tool returns Markdown by default or JSON on demand, with uniform graceful no-data/error handling.

How do I use market-data-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@market-data-mcp get quote for AAPL" 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.

market-data-mcp

by cstamigo-droid

Overview Schema Source Related Servers Discussions Admin

Python

Remote

market-data-mcp

market-data-mcp - quote + verdict demo

Real-time market data: quotes, news, earnings calendar, and a watchlist scanner for AI agents — backed by Finnhub.

Gives any MCP client (Claude Desktop, Claude Code, agents) clean, uniform market data tools that fail gracefully. A missing or premium-gated source returns "no data", never a fabricated value. Markdown output by default, JSON on demand.

Tools

Tool	What it does	Source	Free tier
`market_quote`	Real-time price, % change, high/low/open/prev-close	Finnhub `/quote`	Yes
`market_news`	Top 5 headlines — company-specific or general market	Finnhub `/company-news`, `/news`	Yes
`market_calendar`	Earnings calendar for the next N days (with EPS/revenue estimates)	Finnhub `/calendar/earnings`	Yes*
`market_scan`	Watchlist scanner: rank up to 25 tickers by absolute % change	Finnhub `/quote` x N	Yes
`market_analyze`	Composite: momentum score + news catalyst + earnings proximity	All of the above	Yes
`broker_positions`	Read open positions from Alpaca paper account	Alpaca Paper API	Optional**

*Calendar tested live on 2026-06-14: accessible on Finnhub free tier.
**broker_positions requires ALPACA_API_KEY + ALPACA_SECRET_KEY in .env. Degrades gracefully without them.

Every tool returns Markdown (human-readable, default) or JSON (response_format="json") for programmatic use.

Related MCP server: MonteWalk

Live demo output (2026-06-14)

market_quote AAPL:
  AAPL: $291.13  (-1.52%  -$4.50)  prev close $295.63

market_scan AAPL,MSFT,NVDA,TSLA:
  Scanned 4/4 symbols. Top mover: TSLA +1.82%

market_calendar days=7:
  20 earnings events in the next 7 days: ACN, KR, MEI ...

market_analyze AAPL:
  Signal: Lean negative  [......##|........] -30/100  confidence 60%
  AAPL: $291.13  -1.52%  → Lean negative [TRIM]
  Catalyst: Apple's iOS 27 surprise could change the AI narrative

Quick start

Note: the market-data-mcp package on PyPI is a different, unrelated project by another author. Install this one from source:

git clone https://github.com/cstamigo-droid/market-data-mcp.git
cd market-data-mcp
python -m venv .venv
.venv\Scripts\activate        # Windows
pip install -r requirements.txt

copy .env.example .env        # edit: add FINNHUB_API_KEY
python tests/test_smoke.py    # live test all 6 tools

Get a free Finnhub key at: https://finnhub.io/register

Claude Desktop config

Add this to claude_desktop_config.json (%APPDATA%\Claude\ on Windows, ~/Library/Application Support/Claude/ on macOS), then restart Claude Desktop:

{
  "mcpServers": {
    "market-data-mcp": {
      "command": "python",
      "args": ["-m", "market_data_mcp"],
      "cwd": "C:/path/to/market-data-mcp"
    }
  }
}

Use the system Python path if you are not using a venv:

{
  "mcpServers": {
    "market-data-mcp": {
      "command": "C:/Users/YourName/AppData/Local/Python/pythoncore-3.14-64/python.exe",
      "args": ["-m", "market_data_mcp"],
      "cwd": "C:/path/to/market-data-mcp",
      "env": { "PYTHONUTF8": "1" }
    }
  }
}

Optional: Alpaca broker source

The broker_positions tool reads your Alpaca paper account. To enable it:

Go to https://app.alpaca.markets/ → Paper Trading → API Keys

Add to .env:

ALPACA_API_KEY=your-key-here
ALPACA_SECRET_KEY=your-secret-here

Restart the server.

Without these keys, broker_positions returns a graceful "keys not set" message.

Why it's built this way

Uniform result contract. Every source returns the same Result shape (source, ok, summary, data, score, confidence, error). An LLM can reason across all tools without parsing N formats.
Graceful degradation. A source with no data, a premium-gated endpoint, or a missing key returns Result.failed(...) — never a fabricated value. Zero-price from Finnhub for unknown symbols is treated as "no data", not a quote.
Scored analysis. The composite market_analyze tool emits a -100..+100 directional score with confidence, so an agent can triage without reading prose.
TTL cache. Per-source in-process cache avoids hammering rate-limited APIs when an agent calls several tools in one turn (e.g. scan + analyze in sequence).

Disclaimer

For research and educational use only. Data comes from Finnhub and Alpaca and may be delayed or incomplete. Never use automated market data for financial decisions without independent verification.

License

MIT

Available Tools

6 tools

broker_positionsA

Read-only

Read open positions from an Alpaca paper trading account.

OPTIONAL — requires ALPACA_API_KEY and ALPACA_SECRET_KEY in .env. If keys are absent, returns a graceful 'no data' message with setup instructions. Read-only: never places orders or moves money.

Args: params: response_format ('markdown'|'json').

Examples: - "What positions do I have open in my paper account?" -> (no ticker needed) - "Show me my paper portfolio" -> (no ticker needed)

Inputs: params (required). Returns: result

market_analyzeA

Read-only

Composite market analysis: momentum score, news catalyst, and earnings proximity.

Combines real-time quote (momentum), latest news headline (catalyst), and earnings calendar (risk flag) into a single scored verdict. Each component degrades gracefully — if news or calendar are unavailable, only quote is used. Score: -100 (strong selling pressure) to +100 (strong upward momentum).

Args: params: symbol (str) and response_format ('markdown'|'json').

Examples: - "Give me a full read on Apple" -> symbol='AAPL' - "What's the momentum on NVIDIA right now?" -> symbol='NVDA' - "Analyze Tesla for me" -> symbol='TSLA'

Inputs: params (required). Returns: result

market_calendarA

Read-onlyIdempotent

Fetch the earnings calendar for the next N days.

Returns upcoming earnings reports with estimated EPS and revenue where available. NOTE: This endpoint may be premium-gated on the Finnhub free tier. If so, it degrades gracefully with an honest 'no data' message rather than fabricating events.

Args: params: days (int, 1-30, default 7) and response_format.

Examples: - "Which companies report earnings this week?" -> days=7 - "Show me earnings for the next 2 weeks" -> days=14 - "What's reporting tomorrow?" -> days=1

Inputs: params (required). Returns: result

market_newsA

Read-only

Fetch the latest market news — company-specific or general market headlines.

With a symbol: returns top 5 news items for that ticker from the past 7 days. Without a symbol: returns top 5 general market headlines. Backed by Finnhub free tier.

Args: params: symbol (optional ticker) and response_format ('markdown'|'json').

Examples: - "What's the latest news about Microsoft?" -> symbol='MSFT' - "Give me today's market news" -> (no symbol) - "Any news on Amazon this week?" -> symbol='AMZN'

Inputs: params (required). Returns: result

market_quoteA

Read-onlyIdempotent

Get a real-time stock quote: price, % change, day high/low, and previous close.

Backed by Finnhub free tier. Returns 'no data' for unknown/delisted symbols (Finnhub returns zeros for unknowns — we treat that as no data, never fabricate).

Args: params: symbol (str) and response_format ('markdown'|'json').

Examples: - "What is Apple's current stock price?" -> symbol='AAPL' - "How much is NVIDIA up today?" -> symbol='NVDA' - "Get me a quote for Tesla" -> symbol='TSLA'

Inputs: params (required). Returns: result

market_scanA

Read-onlyIdempotent

Scan a watchlist of stocks and rank them by absolute % change (biggest movers first).

Accepts up to 25 symbols. Unknown or delisted tickers are skipped gracefully. Useful for monitoring a portfolio or sector basket for unusual activity.

Args: params: symbols (comma-separated string, max 25) and response_format.

Examples: - "Which of AAPL, MSFT, GOOGL, AMZN, META is moving most today?" -> symbols='AAPL,MSFT,GOOGL,AMZN,META' - "Scan my tech watchlist: NVDA,AMD,INTC,TSM,AVGO" -> symbols='NVDA,AMD,INTC,TSM,AVGO' - "Show biggest movers in AAPL TSLA MSFT today" -> symbols='AAPL,TSLA,MSFT'

Inputs: params (required). Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.2/5.0

Scored 2026-07-12 22:40 across 6 tools

Disambiguation5/5

Each tool targets a distinct aspect of market data: positions, analysis, calendar, news, quote, and scan. No two tools have overlapping purposes, making it easy for an agent to select the correct one.

Naming Consistency4/5

All tools use lowercase and underscores, and five out of six start with 'market_'. The outlier 'broker_positions' breaks the prefix pattern, but the naming style is otherwise consistent.

Tool Count5/5

6 tools is well-scoped for a market data server. Each tool serves a clear purpose without being excessive or insufficient.

Completeness4/5

The server covers core market data needs: quotes, news, earnings, scan, and composite analysis. A minor gap is historical price data, but the surface is sufficient for most real-time queries.

Maintenance

ActivitySlowing

ResponsivenessOutdated data

Resources

Related MCP Connectors

finance-mcp-serverA
com.thenextgennexus
Live stock quotes, a stock screener, crypto prices and FX rates as agent tools.
Finance Cryptocurrency
2
https://nexgendata-mcp-proxy.steve-corbeil.workers.dev/finance-mcp-server/mcp
xfinlabA
io.github.lnanology
Financial intelligence for AI agents: market events, sentiment, technicals, news feed.
Finance AI & Machine Learning
611
https://api.xfinlab.com/api/mcp
GogiA
ai.gogi.api
Unified financial infrastructure connecting AI agents directly to trade live/demo brokerage accounts, Web3 non-custodial wallets, real-time market data across equities, ETFs, crypto, forex, options, DeFi swaps, and prediction markets, institutional research feeds, and algorithmic strategy backtesters.
Agent Orchestration AI & Machine Learning Finance
391
https://api.gogi.ai/api/mcp/stream
Gloom
io.github.gloom-sh
Stocks, options flow, SEC filings, earnings, GPU prices, supply chain and macro data for agents
Finance Open Data
1
https://api.gloom.sh/mcp

Related MCP Servers

MCP Finnhub Server
Finance Search
NimbleBrainInc
A
license
Not graded
quality
C
maintenance
Provides comprehensive financial market data and news through the Finnhub API. Enables real-time stock quotes, company profiles, financial metrics, analyst recommendations, and market news access.
Updated 4 months ago (2026-07-22 03:24 UTC)
1
MIT
MonteWalk
Finance RAG Systems Autonomous Agents
N-lia
A
license
C
quality
D
maintenance
Provides AI agents with institutional-grade quantitative finance tools including real-time market data, paper trading via Alpaca, risk analysis with Monte Carlo simulations, backtesting, and multi-source news sentiment analysis for portfolio management and trading strategy development.
Updated 10 months ago (2026-01-18 08:53 UTC)
31
5
MIT
Stock Market MCP Server
Finance Research & Data
sverze
F
license
A
quality
D
maintenance
Provides stock market data and analysis tools using the Finnhub API, including stock prices, financial metrics, news, and historical data.
Updated 2 years ago (2025-05-01 07:20 UTC)
6
7
-
FinSage MCP
Finance Data Visualization
robbintech2019
F
license
Not graded
quality
D
maintenance
Connects AI agents to the Finnhub API for real-time stock quotes, market news, earnings reports, and financial metrics.
Updated 9 months ago (2026-02-14 15:34 UTC)
-

market-data-mcp

Tools

Live demo output (2026-06-14)

Quick start

Claude Desktop config

Optional: Alpaca broker source

Why it's built this way

Disclaimer

License

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

MCP Finnhub Server

MonteWalk

Stock Market MCP Server

FinSage MCP