Skip to main content
Glama
geraldo96

finwatch-mcp

by geraldo96

πŸ“Š finwatch-mcp

A custom MCP Server for financial portfolio monitoring, risk analysis, and compliance β€” powered by LangGraph + Claude.

Turn natural language into actionable financial intelligence. Ask your portfolio questions like "What's my risk exposure to tech stocks?" or "Flag any anomalous movements in the last 24h" and get data-driven answers in seconds.

Python 3.11+ MCP Protocol LangGraph License: MIT


Architecture

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚                   CLIENT LAYER                          β”‚
β”‚   Claude Desktop  β”‚  Gradio UI  β”‚  CLI  β”‚  Telegram     β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                         β”‚ MCP Protocol (JSON-RPC)
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β–Όβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚              LANGGRAPH AGENT (Orchestrator)              β”‚
β”‚  Multi-step reasoning Β· Report generation Β· Triage      β”‚
β”‚  Claude API Β· StateGraph Β· Human-in-the-loop            β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                         β”‚ MCP Tool Calls
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β–Όβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚              FINWATCH MCP SERVER                        β”‚
β”‚                                                         β”‚
β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”‚
β”‚  β”‚ get_portfolio β”‚ β”‚ analyze_risk β”‚ β”‚ detect_anomaly β”‚  β”‚
β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β”‚
β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”‚
β”‚  β”‚search_filingsβ”‚ β”‚get_market_kpiβ”‚ β”‚compliance_checkβ”‚  β”‚
β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                         β”‚
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β–Όβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚                    DATA LAYER                            β”‚
β”‚  SQLite (prices, KPIs)  β”‚  ChromaDB (SEC filings, RAG)  β”‚
β”‚  Alpha Vantage Β· Finnhub Β· FRED Β· SEC EDGAR             β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

Related MCP server: Financial Modeling Prep MCP Server

Features

MCP Server Tools

Tool

Description

get_portfolio

Real-time portfolio status: holdings, P&L, sector allocation

analyze_risk

Risk metrics: VaR, Sharpe ratio, Beta, max drawdown

detect_anomaly

Flag unusual price movements, volume spikes, correlation breaks

search_filings

RAG-powered semantic search over SEC filings and earnings reports

get_market_kpi

Macro indicators: interest rates, inflation, sector performance

compliance_check

Validate portfolio against exposure limits and concentration rules

LangGraph Agent

  • Multi-step reasoning: chains tool calls to answer complex questions

  • Report generation: automated daily/weekly portfolio summaries

  • Anomaly triage: investigates detected anomalies with root cause analysis

  • Human-in-the-loop: asks for confirmation before high-impact actions

Quick Start

Prerequisites

  • Python 3.11+

  • uv (recommended) or pip

  • API keys: Alpha Vantage (free), Finnhub (free), Anthropic (for agent)

Installation

# Clone the repo
git clone https://github.com/geraldo96/finwatch-mcp.git
cd finwatch-mcp

# Install with uv (recommended)
uv sync

# Or with pip
pip install -e ".[dev]"

# Copy environment template
cp .env.example .env
# Edit .env with your API keys

Run the MCP Server

# Start the MCP server (Streamable HTTP)
uv run python -m src.mcp_server.server

# The server runs on http://localhost:8080/mcp

Connect to Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "finwatch": {
      "type": "http",
      "url": "http://localhost:8080/mcp"
    }
  }
}

Run the LangGraph Agent (standalone)

# Interactive CLI mode
uv run python -m src.agent.cli

# Example queries:
# > What's my current portfolio allocation?
# > Is my tech exposure within compliance limits?
# > Show me anomalies from the last week and explain them

Run with Docker

docker compose up
# MCP server: http://localhost:8080/mcp
# Gradio UI:  http://localhost:7860

Data Sources

Source

Data

API Key

Rate Limit (free)

Alpha Vantage

Stock prices, fundamentals

Free

25 req/day

Finnhub

Real-time quotes, news, sentiment

Free

60 req/min

FRED

Macro indicators, interest rates

Free

120 req/min

SEC EDGAR

10-K, 10-Q filings

None

10 req/sec

Yahoo Finance

Historical prices (backup)

None

Unofficial

Project Structure

finwatch-mcp/
β”œβ”€β”€ src/
β”‚   β”œβ”€β”€ mcp_server/
β”‚   β”‚   β”œβ”€β”€ server.py          # MCP server entrypoint (Streamable HTTP)
β”‚   β”‚   β”œβ”€β”€ tools/
β”‚   β”‚   β”‚   β”œβ”€β”€ portfolio.py   # get_portfolio tool
β”‚   β”‚   β”‚   β”œβ”€β”€ risk.py        # analyze_risk tool
β”‚   β”‚   β”‚   β”œβ”€β”€ anomaly.py     # detect_anomaly tool
β”‚   β”‚   β”‚   β”œβ”€β”€ filings.py     # search_filings tool (RAG)
β”‚   β”‚   β”‚   β”œβ”€β”€ market_kpi.py  # get_market_kpi tool
β”‚   β”‚   β”‚   └── compliance.py  # compliance_check tool
β”‚   β”‚   └── config.py          # Server configuration
β”‚   β”œβ”€β”€ agent/
β”‚   β”‚   β”œβ”€β”€ graph.py           # LangGraph StateGraph definition
β”‚   β”‚   β”œβ”€β”€ nodes.py           # Agent nodes (reason, act, report)
β”‚   β”‚   β”œβ”€β”€ state.py           # Agent state schema
β”‚   β”‚   └── cli.py             # Interactive CLI client
β”‚   β”œβ”€β”€ data/
β”‚   β”‚   β”œβ”€β”€ ingester.py        # Data fetching & sync logic
β”‚   β”‚   β”œβ”€β”€ models.py          # SQLAlchemy / Pydantic models
β”‚   β”‚   └── db.py              # Database connection & queries
β”‚   └── rag/
β”‚       β”œβ”€β”€ embeddings.py      # BAAI embedding pipeline
β”‚       β”œβ”€β”€ indexer.py         # SEC filing indexer
β”‚       └── retriever.py       # ChromaDB retrieval
β”œβ”€β”€ tests/
β”‚   β”œβ”€β”€ test_tools.py          # Unit tests for MCP tools
β”‚   β”œβ”€β”€ test_agent.py          # Agent integration tests
β”‚   └── test_data.py           # Data layer tests
β”œβ”€β”€ scripts/
β”‚   β”œβ”€β”€ seed_data.py           # Seed DB with sample portfolio
β”‚   β”œβ”€β”€ ingest_filings.py      # Download & index SEC filings
β”‚   └── demo.py                # Full demo walkthrough
β”œβ”€β”€ docs/
β”‚   β”œβ”€β”€ ARCHITECTURE.md        # Detailed architecture docs
β”‚   └── TOOLS.md               # MCP tool specifications
β”œβ”€β”€ docker-compose.yml
β”œβ”€β”€ Dockerfile
β”œβ”€β”€ pyproject.toml
β”œβ”€β”€ .env.example
└── README.md

Development Roadmap

Week 1 β€” Foundation

  • Project scaffold & CI setup

  • MCP server with get_portfolio and analyze_risk tools

  • SQLite data layer + Alpha Vantage / yfinance ingestion

  • Sample portfolio seeding script

Week 2 β€” RAG & Anomaly Detection

  • ChromaDB setup + SEC EDGAR filing indexer

  • search_filings tool with BAAI embeddings

  • detect_anomaly tool (z-score + rolling stats)

  • get_market_kpi tool (FRED integration)

Week 3 β€” Agent & Orchestration

  • LangGraph StateGraph with Claude API

  • Multi-step reasoning chains

  • compliance_check tool

  • Interactive CLI client

Week 4 β€” Polish & Deploy

  • Docker Compose (server + agent + Gradio UI)

  • Comprehensive tests

  • Demo video / GIF

  • Hugging Face Space (optional)

Tech Stack

Layer

Technology

MCP Server

Python mcp SDK, Streamable HTTP

Agent

LangGraph, Claude API (Anthropic SDK)

Structured Data

SQLite + SQLAlchemy

Vector Store

ChromaDB + BAAI/bge-small-en-v1.5

Data Sources

Alpha Vantage, Finnhub, FRED, SEC EDGAR, yfinance

UI

Gradio (demo), Claude Desktop (production)

Deploy

Docker Compose

Testing

pytest, pytest-asyncio

Contributing

Contributions are welcome! Please read the contributing guidelines first.

License

MIT License β€” see LICENSE for details.


Built by Geraldo Margjini as a portfolio project demonstrating MCP Server development, LangGraph agent orchestration, and financial data engineering.

A
license - permissive license
-
quality - not tested
D
maintenance

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/geraldo96/finwatch-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server