Market Eyes Live MCP Server
A free Model Context Protocol (MCP) server that gives AI agents and LLM applications MELANY stock ratings for U.S.-listed stocks and ETFs, more than 11,000 tickers on its coverage list: conviction tier, 0-100 composite score, eight factor scores, top risks, and an as-of date. Agents can also put a rating next to the public graded record for its tier, list the names currently in a tier, have a rating explained in plain words, and read the record itself. Plus U.S. mortgage-rate context. No API key, no signup. Streamable HTTP. Works with Claude, ChatGPT, Cursor, VS Code, and any MCP client.
Endpoint https://marketeyeslive.com/mcp?src=site | Transport Streamable HTTP | Auth none | Registry name io.github.marketeyeslive/market-eyes-live
Quick start
Claude Code
claude mcp add --transport http market-eyes-live "https://marketeyeslive.com/mcp?src=site"
Claude Desktop and VS Code
Add this to your MCP configuration file:
{
"mcpServers": {
"market-eyes-live": {
"type": "http",
"url": "https://marketeyeslive.com/mcp?src=site"
}
}
}
Cursor
Cursor infers a remote server from the presence of url, so it takes no type field:
{
"mcpServers": {
"market-eyes-live": {
"url": "https://marketeyeslive.com/mcp?src=site"
}
}
}
Claude.ai and the Claude desktop app, as a connector
Settings, then Connectors, then add a custom connector and paste https://marketeyeslive.com/mcp?src=site. Leave the authentication fields empty.
ChatGPT
In ChatGPT, open Plugins, choose +, then Add custom MCP server, paste https://marketeyeslive.com/mcp?src=site and set authentication to none. Custom servers are available on the Plus, Pro, Business, Enterprise and Edu plans, and some accounts need developer mode turned on first. Menu names may vary as ChatGPT updates.
Perplexity
Settings, then Connectors, then add a custom connector with https://marketeyeslive.com/mcp?src=site as a remote server over Streamable HTTP, with no authentication. Custom connectors need a Perplexity Pro plan or above. Menu names may vary.
Gemini
In the Gemini web app at gemini.google.com, open the apps settings and add a custom app with https://marketeyeslive.com/mcp?src=site as the server address. Custom apps are offered on the Google AI Pro and Ultra plans. Menu names may vary.
Grok
On Grok on the web, go to grok.com/connectors, choose New Connector, then Custom, paste https://marketeyeslive.com/mcp?src=site and add no authentication. On Grok Business and Enterprise, a team admin provisions connectors first. Menu names may vary.
Mistral Le Chat
Open Intelligence, then Connectors, then add a Custom MCP Connector, paste https://marketeyeslive.com/mcp?src=site; Le Chat detects the authentication type, and this server needs none. Adding a connector may need a workspace admin. Menu names may vary.
Set it up on a computer; once added, it also works in the phone apps of Claude and ChatGPT.
That is the whole setup. There is no key to paste and no account to create.
Tools
| Tool | Arguments | Returns |
|---|---|---|
get_stock_rating |
symbol (string, e.g. NVDA) |
MELANY's current rating for one U.S.-listed stock or ETF: conviction tier, 0-100 composite score, the eight factor scores, top flagged risks, theme context, the as-of date, the asset class (stock, ETF or REIT, which sets how the eight factors are labelled), and links to the public rating page and the method. When Market Eyes Live has a trade plan for the ticker, the rating says so; the plan values are not included (see below). |
compare_stocks |
symbols (2 to 5 tickers) |
A side-by-side comparison of tier, composite, and the valuation, quality and momentum scores across the requested tickers, drawn from the daily-refreshed set, with each ticker's rating page and a mark on any ticker that has a trade plan. A ticker outside that set returns a note; get_stock_rating can score it live. |
check_trade |
symbol (string), side (optional: buy or sell) |
The full rating for one ticker plus what the public graded record says about calls carrying that tier: the share that beat more than half of the other core stocks rated the same day, over the following week and month, with the calls behind each figure and the 50% no skill line. A REIT is looked up under its own REIT label; an ETF carries its rating without a tier figure, since funds are not graded against the same day list. The side only changes the wording; the rating and the record are the same either way. If the record cannot be read in time, the rating still comes back, with a note in place of the figures. Meant for the moment an agent is discussing a trade, so the person sees the rating, its tone and its record side by side. It reports research only; it never approves or rejects a trade and never places one. |
list_rated_by_tier |
tier (one of the nine tier words), limit (1 to 25, default 10) |
The names in the daily-refreshed set whose latest rating carries that tier, strongest composite first: symbol, company, composite, as-of date and rating page. Only ratings dated within five days of the newest in the set are listed, and the older ones are counted as left out. The list is rebuilt at most every 30 minutes (it can be older if a rebuild fails); most funds and REITs carry their own labels and are not listed under these words. |
explain_rating |
symbol (string) |
The full rating with the tier word and each of the eight factors explained in plain words: what it measures and what its score reads as (strong, leaning strong, middle, leaning weak or weak), on the label table for the asset class, plus how to read the composite and the record for the tier in one sentence. For Rising Star, Very Promising and Promising it also gives the speculative model's own score, which sets that rung, when the rating carries it. |
get_track_record |
none | The public graded record: since when, how many calls and graded outcomes, and for each published tier the share of calls that beat the same day list at one day, one week and one month. A figure is published only once it holds 20 graded outcomes across 8 tickers. The feed is cached for up to 15 minutes and rebuilt on the next read after that; an older copy, up to about a day old, may answer while a new one builds, and the record carries the date of its last capture. The public feed also grades every call against a market benchmark. |
get_mortgage_rate_context |
none | Today's U.S. mortgage-rate read: 10-year Treasury yield and direction, MBS momentum, the overall rate environment, and what moves mortgage rates. |
The eight factor scores
Every rating shows its work through eight components: Valuation (price against fundamentals), Quality (balance sheet strength and profitability), Momentum (price trend and relative strength), Earnings (growth trajectory and surprises), Sentiment (analyst and market mood), Catalyst (near-term events that could move the stock), Risk-Adjusted (return for the risk taken), and Macro Fit (fit with the current market regime and sector cycle).
The nine tier words
Every rated name carries one of nine words, or none when no tier applies; these are the same nine list_rated_by_tier accepts. The mature ladder, weakest to strongest: Unfavorable, Hold, Favorable, Highest Conviction (for a stock, a composite of about 69 or above). Names without mature fundamentals carry Promising, Very Promising or Rising Star instead; Runner! marks a momentum surge and Catalyst Watch a news-driven gap up on volume. ETFs and REITs are served on the mature ladder, read from the fund's own label in the app, so most of them are not listed by list_rated_by_tier; a leveraged or inverse fund never reads above Hold.
Questions it answers well
- "How does Market Eyes Live rate NVDA, and what does the rating rest on?"
- "Compare AAPL, MSFT and GOOGL on quality and valuation."
- "What are the flagged risks on TSLA today?"
- "How does VOO score on valuation right now?"
- "Show the rating and the record for its tier on NVDA."
- "Which names are Highest Conviction today?"
- "Explain the Market Eyes Live rating on MSFT in plain words."
- "How have Market Eyes Live's favorable ratings done against the other stocks rated the same day?"
- "What is driving mortgage rates this week?"
What this is, and what it is not
Most financial MCP servers hand a model raw inputs: prices, fundamentals, news, technicals. The model then has to do the analysis itself, in-context, with no memory of whether its last read was any good.
This server hands back a finished, graded rating: one conviction tier and one 0-100 composite, plus the eight factor scores that produced it. Two things back that number:
- The rules are stress-tested against 19 years of U.S. market history (2007 to 2026, spanning the 2008 financial crisis, the COVID crash, and the 2022 bear market), with delisted companies included so the test is not flattered by survivorship bias.
- Every published rating is forward-tested. Each one is recorded and graded daily against what the market actually did next, on a public record with a raw feed and a full validation study, including the ideas the testing program rejected. An agent can read that record directly with
get_track_record, or next to a single rating withcheck_trade.
To be explicit about the limits: Market Eyes Live does not issue buy or sell calls, this is research rather than financial advice, and the 19-year window tests the rules, not the live ratings, which are graded forward day by day. Coverage is U.S.-listed stocks and ETFs only.
How it compares to market-data MCP servers
These are complementary rather than competing. A raw data feed wins on breadth, history, and international coverage. This one wins when you want a scored read with a track record attached.
| Market Eyes Live | Market-data MCP servers (Alpha Vantage, EODHD, Finnhub, Tiingo) | |
|---|---|---|
| What you get | A scored, graded rating: tier, 0-100 composite, 8 factor scores, risks, and the record for its tier | Raw inputs: quotes, fundamentals, news, technicals |
| Who does the analysis | The MELANY engine, consistently, every day | The model, in-context, per request |
| Track record | Every published rating graded daily on a public record, readable by the agent itself | Not applicable, data is not a prediction |
| Coverage | U.S.-listed stocks and ETFs, 11,000+ | Often global, multi-exchange, decades of history |
| API key | None | Usually required |
| Cost | Free, rate-limited | Free tier plus paid plans |
| Best for | A scored read of a U.S. stock or ETF, with the factors and track record behind it | "Give me the numbers so I can compute something" |
A fuller side-by-side, including when a raw data feed is the better choice: financial data MCP servers compared.
Usage is governed by the API terms of use: commercial use is fine, attribution is asked for, and nothing here is financial advice.
Coverage and rate limits
- Coverage: U.S.-listed stocks and ETFs only, more than 11,000 tickers. A core set is refreshed daily and answers instantly; anything else on the coverage list is scored live on demand, by
get_stock_rating,check_tradeandexplain_ratingalike. Crypto, futures, and non-U.S. listings (for example SHOP.TO or BTC-USD) return a "not covered" result. Five U.S. tickers that share their symbol with a futures contract or a coin (CORN, GOLD, WTI, BTC and ETH) are not rated, and the result says so. Class shares work in either spelling (BRK-B or BRK.B). A ticker that is not on the coverage list, such as a very recent listing, returns a result saying exactly that. - What counts: only tool calls. Connecting, listing the tools and pings are free.
- Tool call limit: 240 calls per hour per user when the AI platform passes an anonymous user id (ChatGPT does), otherwise per network address. A platform that passes no user id, such as Claude, shares 3,000 calls per hour across all its users. Callers that do not come through ChatGPT or Claude share 3,000 calls per hour between them, so they can never use up the whole service. 6,000 calls per hour across all callers. Those are the limits in force as of 6 October 2026. They can change in either direction, and this page is the reference for what they currently are.
- Live on-demand scoring: 20 per hour per user or address, 100 per hour per platform, 150 per hour shared by callers that do not come through a platform, and 300 per hour across all callers, because those calls hit paid data vendors. Recent live scores are reused for 12 hours, and a ticker that could not be scored is not retried for 12 hours. Stating the shared caps because you can be limited by one while still under your own.
- When a limit is reached: the tool returns an error result that says which limit it was and when it resets, at the top of the hour (UTC).
- Asset-native scoring: an ETF is judged as a fund and a REIT on FFO, rather than forced through a common stock template.
- Limits are generous for normal agent use. If you are building something that needs more, email team@marketeyeslive.com.
One engine, two products
The MCP server and the Market Eyes Live app are the same company and the same engine. The MCP server is the free public data tier. It never returns trade plan values: when the app has a trade plan for a ticker, the rating says so and links the public rating page. The plan, including a suggested entry zone and a model position size, is the same for every reader and not based on anyone's account, holdings or finances, and it is part of a Market Eyes Live subscription. The app carries the full research depth: one suggested entry zone per stock, stock alerts, portfolio tools, a free paper-trading arena, and Lock Radar mortgage timing. It runs on iOS and the web.
Source, registry, and directories
- GitHub repository
- Official MCP registry:
io.github.marketeyeslive/market-eyes-live - Smithery and Glama
- llms.txt for AI crawlers
What is Market Eyes Live How MELANY is tested
Market Eyes Live is a research tool, not financial advice. Ratings are data-driven estimates of conviction, not buy or sell recommendations, and past testing does not guarantee future results.
Home | What is Market Eyes Live | How MELANY is tested | All rated stocks | Mortgage rates