Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
Tiingo market data MCP server for agents
This repository packages Tiingo data as MCP tools so an agent can fetch financial information without leaving its client. The server exposes endpoints for prices, news, forex, fundamentals, dividends, and splits, and you connect it by pointing an MCP runner at the built Node entrypoint.
Builders who want their MCP client to pull Tiingo stock and forex data on demand.
You can ask your agent for market data, fundamentals, and news without wiring each Tiingo endpoint yourself.
What it does
End-of-day price tools
Fetch historical stock prices for a ticker with optional date range and resampling.
News search
Query Tiingo news by tickers, tags, sources, date range, and limit.
Forex tools
Get historical forex prices and real-time top-of-book or last data.
Fundamentals access
Retrieve definitions, statements, daily metrics, and company metadata.
Dividend and split data
Look up dividend distributions, dividend yield, and split history for a ticker.
How to get it
- 1Install dependencies
npm install
- 2Build the server
npm run build
README
Stock Trade MCP Server
A Model Context Protocol (MCP) server that exposes various Tiingo API endpoints as tools. This server allows programmatic access to financial data including stock prices, news, forex, fundamentals, and corporate actions via the MCP protocol.
Prerequisites
- Node.js (v18 or later recommended)
- npm (comes with Node.js)
- A Tiingo API Key
- MCP-compatible client or runner (e.g., VSCode extension, CLI)
Setup
-
Clone the repository or ensure you are in the project directory.
-
Install dependencies:
npm install -
Obtain Your Tiingo API Key: To use this server, you need a Tiingo API token.
- Register for a Tiingo account if you don't have one.
- Go to your Tiingo Account page and navigate to the API Token section (or directly visit: https://www.tiingo.com/account/api/token).
- Copy your API Token. You will need to provide this token to your MCP client to authenticate with the Tiingo API. Note: Programmatic registration or logins are not supported by Tiingo; the API token is the sole method for authentication.
-
Set Tiingo API Key: This server requires your Tiingo API key. You can typically provide the API key in your MCP client's configuration (see "Running the Server" below for an example).
-
Build the server:
npm run buildThis will create a
builddirectory with the compiled JavaScript code.
Running the Server
- Via MCP runner:
Configure your MCP client to run the server using stdio transport. You can provide the
TIINGO_API_TOKENin theenvblock of the configuration. Example MCP settings entry:
(Replace"mcp-tiingo": { "transportType": "stdio", "command": "node", "args": [ "/path/to/mcp-tiingo/build/index.js" ], "env": { "TIINGO_API_TOKEN": "YOUR_API_KEY_HERE" } // ... other optional settings ... }/path/to/mcp-tiingoandYOUR_API_KEY_HEREaccordingly)
Available Tools
The server exposes the following Tiingo API endpoints as tools via MCP:
get_end_of_day_prices
- Description: Fetches End-of-Day prices for a given ticker symbol with optional date range and format.
- Key Inputs:
ticker,startDate,endDate,resampleFreq
get_news
- Description: Fetches news articles from Tiingo with various filtering options.
- Key Inputs:
tickers,tags,sources,startDate,endDate,limit
get_forex_prices
- Description: Fetches historical intraday Forex prices for a given ticker symbol with optional date range and frequency.
- Key Inputs:
ticker,startDate,endDate,resampleFreq
get_forex_top_of_book
- Description: Fetches real-time Forex Top-of-Book/Last data for one or more ticker symbols.
- Key Inputs:
tickerortickers
get_fundamentals_definitions
- Description: Fetches available fundamental metrics and their definitions.
- Key Inputs: None
get_fundamentals_statements
- Description: Fetches historical fundamental statement data (Balance Sheet, Income Statement, Cash Flow, Overview) for a given ticker.
- Key Inputs:
ticker,startDate,endDate,year,quarter
get_fundamentals_daily_metrics
- Description: Fetches daily fundamental metrics for a given ticker.
- Key Inputs:
ticker,startDate,endDate,columns
get_fundamentals_meta
- Description: Fetches fundamental meta data for companies.
- Key Inputs: None
get_dividend_distributions
- Description: Fetches historical dividend and distribution data for a given ticker.
- Key Inputs:
ticker,startExDate,endExDate
get_dividend_yield
- Description: Fetches historical dividend yield data for a given ticker.
- Key Inputs:
ticker,startDate,endDate,columns
get_splits
- Description: Fetches historical split data for a given ticker.
- Key Inputs:
ticker,startExDate,endExDate
Extending
To add more Tiingo API endpoints as tools:
- Create a new TypeScript file in
src/tools/defining the tool's name, description, input schema (using Zod), and handler function to call the Tiingo API. - Import and add the tool definition object to the
tiingoToolsarray insrc/tools/index.ts. - Rebuild the server (
npm run build).
Files in the repo
- memory-bank
- src
- .clinerules
- .gitignore
- .prettierrc
- eslint.config.js
- LICENSE
- package-lock.json
- package.json
- README.md
- tsconfig.json
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More connectors
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.