TA
Search

TAM MCP Server: TAM/SAM Market Research Insights

Analyze TAM/SAM market insights with the MCP server using integrated data from Alpha Vantage, BLS, Census, FRED, IMF, Nasdaq, OECD, and World Bank.

View on GitHub
Quick Install
npx -y @gvaibhav/TAM-MCP-Server

Overview

The TAM MCP Server is an implementation of a Model Context Protocol (MCP) server tailored for Total Addressable Market (TAM) and Serviceable Available Market (SAM) research. It aggregates and normalizes economic, company, and macro datasets from sources such as Alpha Vantage, BLS, Census, FRED, IMF, Nasdaq, OECD, and the World Bank. By exposing a unified MCP-compatible HTTP API, the server lets analytics clients and LLM agents query, search, and retrieve contextual market data without having to manage multiple APIs and formats.

This server is useful for analysts, product managers, and developers who need reproducible market sizing, trend analysis, and competitive research. Instead of stitching together disparate data downloads, you can request domain-specific context (time series, indicators, company fundamentals, demographic tables), apply semantic search over combined data, and supply that context directly to models or downstream applications.

Features

  • Unified MCP-compatible API for market and macroeconomic context
  • Aggregation of public data sources: Alpha Vantage, BLS, Census, FRED, IMF, Nasdaq, OECD, World Bank
  • Normalized datasets: consistent naming, units, and time-series formats
  • Text and numeric semantic search across datasets (vector-backed)
  • Endpoint for fetching raw source data and curated context bundles
  • Configurable fetch schedules and caching to reduce API usage
  • Simple developer onboarding with environment-driven configuration and Docker support

Installation / Configuration

Clone the repository and install dependencies. The example assumes a Python-based server, but the steps are similar for other runtimes.

git clone https://github.com/gvaibhav/TAM-MCP-Server.git
cd TAM-MCP-Server

# create a virtualenv (Python)
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

Set required API keys and basic configuration via environment variables or a .env file. Typical variables:

  • ALPHA_VANTAGE_KEY
  • BLS_API_KEY
  • FRED_API_KEY
  • IMF_API_KEY
  • NASDAQ_API_KEY (if available)
  • WORLD_BANK_KEY (optional)
  • OECD_KEY (optional)
  • MCP_SERVER_PORT (default: 8080)
  • CACHE_DIR (local cache path)

Example .env:

ALPHA_VANTAGE_KEY=your_alpha_key
BLS_API_KEY=your_bls_key
FRED_API_KEY=your_fred_key
IMF_API_KEY=your_imf_key
MCP_SERVER_PORT=8080
CACHE_DIR=./cache

Start the server locally:

# with environment variables sourced
export $(cat .env | xargs)

# start (example)
python server.py
# or, if node-based: node index.js

Docker (optional):

docker build -t tam-mcp-server .
docker run -p 8080:8080 \
  -e ALPHA_VANTAGE_KEY=your_alpha_key \
  -e BLS_API_KEY=your_bls_key \
  -e FRED_API_KEY=your_fred_key \
  tam-mcp-server

Available Tools / Resources

The server provides endpoints and resources that clients can call:

  • /mcp/sources — list available data sources and metadata
  • /mcp/search — semantic search across datasets (query -> ranked contexts)
  • /mcp/query — fetch structured data bundles (time series, tables)
  • /mcp/raw/{source} — raw API proxy to an upstream source
  • /mcp/health — server status and cache metrics

Data sources and primary contents:

SourceTypical content
Alpha VantageStock prices, fundamentals, company time series
BLSEmployment, wages, occupation data
CensusDemographics, population, business counts
FREDMacroeconomic time series (GDP, CPI, interest rates)
IMFCountry-level economic indicators
NasdaqMarket data, company listings (where available)
OECDEconomic indicators, standardized country metrics
World BankDevelopment indicators, global time series

The server can return pre-composed “context bundles” (e.g., TAM_bundle_US_EV) that combine multiple sources into a single MCP response suitable for model prompts.

Use Cases

  • Estimating TAM for an industry: retrieve population, household income (Census), related macro trends (FRED/GDP, CPI), and public company revenues (Alpha Vantage / Nasdaq) to triangulate market size.
    • Example: query semantic search for “electric vehicle charging infrastructure market — United States 2019-2024” and request a time-series bundle.
  • Deriving SAM from occupational and industry employment: combine BLS employment counts and Census business counts to estimate serviceable workforce and addressable firms in a region.
  • Competitive / financial context: fetch recent revenue, market cap, and stock trends for public competitors from Alpha Vantage and Nasdaq, then feed the combined context to an LLM for comparative analysis.
  • Trend detection: aggregate FRED, IMF, and World Bank indicators to surface macro trends that could expand or contract TAM over a multi-year horizon.

Example API usage (curl):

Search for context related to “renewable energy demand — India”:

curl -X POST "http://localhost:8080/mcp/search" \
  -H "Content-Type: application/json" \
  -d '{"query":"renewable energy demand India 2010-2024", "top_k":5}'

Fetch a prebuilt TAM bundle for US EV market:

curl "http://localhost:8080/mcp/query?bundle=TAM_US_EV_2024"

Tips for Developers

  • Configure caching to avoid hitting upstream API rate limits during iterative development.
  • Use the /mcp/sources endpoint to discover which datasets are available and their refresh cadence.
  • When integrating with LLMs, prefer the precomputed context bundles to reduce prompt tokens and ensure reproducibility.

This MCP server is intended as a practical bridge between public economic/company data and model-driven workflows for market research. Use it to centralize data access, standardize context, and accelerate TAM/SAM analyses.

Tags:search