TipRanks
Live TipRanks financial data & analyst research for AI agents - analyst ratings, Smart Score, technicals, options, and your portfolios.
README
TipRanks MCP Server
Live financial data and analyst research for AI agents — over the Model Context Protocol.
Plug Claude, ChatGPT, Cursor, or any MCP-compatible client into live TipRanks data: analyst ratings, Smart Score, price targets, technicals, options, insider and hedge-fund activity, congressional trading, ETFs, commodities, forex, crypto, earnings, news — plus read access to your own TipRanks portfolios.
- Endpoint:
https://mcp.tipranks.com/mcp/ - Transport: Streamable HTTP
- Auth: OAuth 2.1 (PKCE + Dynamic Client Registration) or API key
- Official MCP Registry:
com.tipranks/tipranks - Docs: https://mcp.tipranks.com/ · Privacy: https://mcp.tipranks.com/privacy · Terms: https://mcp.tipranks.com/terms
Informational only. TipRanks provides market data and analyst research for informational purposes — not investment, financial, legal, or tax advice. Quotes and other data may be delayed. All tools are read-only; the connector never places trades or modifies your account.
Connect
Claude.ai / Claude Desktop / Claude Code
Add a custom connector pointing at https://mcp.tipranks.com/mcp/ and complete the OAuth sign-in with your TipRanks account.
ChatGPT
Available as a ChatGPT app — search the app directory for TipRanks.
Cursor / VS Code / other MCP clients
Add a remote (streamable-HTTP) MCP server with URL https://mcp.tipranks.com/mcp/. Clients that support OAuth will discover the flow automatically via the server's /.well-known/oauth-protected-resource metadata.
Full per-client setup instructions: https://mcp.tipranks.com/
Authentication & scopes
Authenticated services use OAuth 2.1 (PKCE S256, Dynamic Client Registration). Two scopes:
| Scope | Default | Grants |
|---|---|---|
tipranks:read |
✔ | Market data: analyst ratings, Smart Score, technicals, news, screening, ETFs, commodities, forex, crypto |
tipranks:portfolio |
— | Read your TipRanks portfolios (holdings, performance, allocation) — limited to portfolios you own at authorization time |
Developers can alternatively use an API key — see the developer portal.
Rate limits
| Plan | Tool calls / month |
|---|---|
| Free | 10 |
| Premium | 100 |
| Ultimate | 200 |
Resets on the 1st of each month (UTC). API-key tiers (free / smart / advanced / professional) carry their own per-minute and monthly limits.
Tools
70+ read-only tools, grouped by domain:
- Stocks & research — quotes, prices, analyst ratings & consensus, price targets, Smart Score, bull/bear summary, peers, catalysts
- Fundamentals — financials, earnings history & estimates, earnings-call summaries, dividends, KPIs, buybacks, stock splits
- Ownership & sentiment — insider transactions, hedge-fund holdings & activity, congressional (politician) trading, blogger & investor sentiment, top experts
- Discovery & screening — trending stocks, top-rated & top Smart-Score stocks, market movers, sector & market performance, ETF screener
- ETFs — analysis, forecast, holdings, exposures, top stocks
- Options — expirations, chains, contracts, unusual trades
- Calendars & events — earnings, IPO, economic, clinical-trial/FDA calendars, market commentary, news & articles
- Cross-asset — commodities, forex, crypto, indices (quotes + historical)
- Your portfolios — list, holdings, overview, performance, analysis (requires
tipranks:portfolio)
The connector is read-only end to end — every tool is annotated readOnlyHint: true, destructiveHint: false.
Examples
Runnable sample agents that build on the connector live in examples/:
- due-diligence-agent — turns a ticker into a structured research memo (analyst consensus, Smart Score, financials, technicals, bull/bear case, smart-money signals).
- earnings-companion — turns a ticker into an earnings brief (next report & expectations, beat/miss track record, last-call recap, analyst posture into the print).
- smart-money-screener — surfaces a ranked shortlist of ideas the smart money is favoring (top Smart-Score names, trending stocks, hedge-fund/insider buying).
Each is compact Python; the model calls the TipRanks tools autonomously through the MCP connector. Get an API key at mcp.tipranks.com/dev/signup to run them.
Privacy Policy
See https://mcp.tipranks.com/privacy. In brief: OAuth tokens and API keys are stored only as SHA-256 hashes (no plaintext credentials at rest); the connector reads TipRanks and market data on your behalf and does not sell personal data. Contact: support@tipranks.com.
Support
- Docs: https://mcp.tipranks.com/
- Developer portal: https://mcp.tipranks.com/dev
- Email: support@tipranks.com
© TipRanks. This repository contains the public connector descriptor, documentation, and example code for the hosted TipRanks MCP service. It does not contain the server implementation.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.