Skip to main content
Glama

MarketMind MCP

A financial research MCP server built with FastMCP, Pydantic v2, and LangGraph.

Exposes 4 tools over the Model Context Protocol that any MCP-compatible client (Claude Desktop, Cursor, etc.) can call. Includes a LangGraph workflow that chains the tools into a multi-step research pipeline.

Tools

Tool

Description

get_stock_quote

Latest price, change %, and volume for a ticker

get_historical_prices

OHLC price history for a given period

compute_rsi

RSI indicator with overbought/oversold classification

generate_research_report

Streams an AI analyst report token-by-token via MCP progress notifications

Related MCP server: Finance MCP Server

Prerequisites

  • Python 3.11+

  • uv

  • OpenAI API key (for generate_research_report)

Setup

git clone https://github.com/your-username/marketmind-mcp
cd marketmind-mcp
uv sync
cp .env.example .env
# Add your OPENAI_API_KEY to .env

Usage

Run as MCP server (connect to Claude Desktop)

uv run marketmind

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "marketmind": {
      "command": "uv",
      "args": ["run", "marketmind"],
      "cwd": "/path/to/marketmind-mcp"
    }
  }
}

Once connected, Claude Desktop can call all 4 tools. generate_research_report streams the analyst report token-by-token via MCP progress notifications — the report appears in real-time as it is written.

Run the LangGraph workflow directly (CLI)

uv run python -m marketmind.workflow NVDA

Example output:

Researching NVDA...

[market_node]  NVDA  $924.18  (+2.51%)
[market_node]  RSI(14): 55.61  → neutral
[news_node]    5 headlines fetched

========================================================
  RESEARCH REPORT: NVDA
  Generated: 2026-03-16 05:57 UTC
========================================================

Summary
  NVIDIA continues to exhibit strong bullish momentum, driven by accelerating
  data centre GPU demand and positive earnings revisions.

Price Action
  NVDA is up 2.51% today at $924.18, breaking above the 20-day moving average
  on above-average volume.

Momentum
  RSI(14) at 55.6 signals healthy momentum without approaching overbought territory.

News Context
  Recent headlines highlight record Blackwell GPU shipments and expanded
  hyperscaler contracts.

Outlook: BULLISH

For informational purposes only. Not financial advice.

Inspect tools interactively

uv run fastmcp inspect src/marketmind/server.py

Opens the FastMCP inspector in your browser — lets you call any tool manually and inspect inputs, outputs, and schemas.

Run Tests

uv run pytest -v

45 tests covering business correctness, input security, and workflow resilience.

Stack

Layer

Technology

MCP server

fastmcp 3.x

Schema validation

pydantic v2

Orchestration

langgraph

LLM

openai (GPT-4o)

Market data

yfinance

News

Yahoo Finance RSS via feedparser + httpx

Available Tools

4 tools
compute_rsiA

Compute the Relative Strength Index (RSI) for a stock.

Returns the RSI value (0–100) and a signal:

  • overbought: RSI ≥ 70 (potential sell pressure)

  • oversold: RSI ≤ 30 (potential buy opportunity)

  • neutral: RSI between 30 and 70

Inputs: symbol (required), period. Returns: rsi, period, signal, symbol

generate_research_reportA

Generate a streaming AI research report for a stock.

Fetches the latest quote, RSI(14), price history, and recent news concurrently, then streams a narrative analyst report token-by-token via MCP progress notifications — so the client sees output as it is written rather than waiting for the full response.

Returns the complete report text when finished.

Inputs: symbol (required). Returns: result

get_historical_pricesA

Retrieve OHLC price history for a stock over a given period.

Inputs: symbol (required), period, interval. Returns: bars, period, symbol, interval

get_stock_quoteB

Get the latest price, daily change %, and trading volume for a stock.

Inputs: symbol (required). Returns: price, symbol, volume, timestamp, +1 more

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool targets a distinct aspect of stock research: current quote, historical prices, RSI indicator, and a comprehensive research report. No overlapping functionality.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern in snake_case (compute_rsi, generate_research_report, get_historical_prices, get_stock_quote), making the set predictable and easy to navigate.

    Tool Count4/5

    With 4 tools, the server is focused and each tool serves a clear purpose. While slightly lean for a research domain, the number is appropriate for the stated scope.

    Completeness4/5

    The tool set covers core stock research needs: quote, history, RSI, and a report that aggregates data and news. Missing standalone news or fundamental data, but the report compensates, so only minor gaps exist.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      B
      quality
      D
      maintenance
      Provides tools to get financial data (stock prices, company information) and generate financial visualizations through the Model Context Protocol.
      10
      11
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides real-time financial data from Yahoo Finance to Large Language Models through the Model Context Protocol, enabling AI models to access stock prices, historical data, and company information.
      1
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that provides stock technical analysis tools (moving averages, RSI, trade recommendations) for AI assistants to analyze stocks and offer trading signals.
      -
    • A
      license
      A
      quality
      C
      maintenance
      Provides access to real-time stock prices, financial statements, news, and options data via the Model Context Protocol. It enables AI assistants to retrieve comprehensive market data, including historical prices and analyst recommendations, through a standardized interface.
      9
      62 PyPI
      2
      MIT