Sortefi
Server Details
Plain-English market screens and quant answers on live US, India, ETF, forex and crypto data.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
Each tool has a clearly distinct role: ask_quant answers numeric questions on named symbols, run_screen lists symbols matching conditions, and the two get_*_result tools retrieve async results by reference. The descriptions explicitly cross-reference ask_quant vs run_screen, and the retrieval tools are tied to the corresponding reference, leaving little chance of misselection.
All names follow a readable verb_noun pattern (ask_quant, run_screen, get_quant_result, get_screen_result). The verbs vary between ask/run/get, but the pattern is predictable and the paired quant/screen naming is coherent.
Four tools is a lean but reasonable surface: two primary actions (ask_quant, run_screen) plus two async retrieval counterparts. There is no redundancy, though the small set relies heavily on ask_quant's breadth.
The core lifecycle of asking a quant question, running a screen, and retrieving deferred results is covered, including charging behavior and cross-tool guidance. Minor gaps remain around account/credit inspection or listing available symbols, but agents can work around them via the primary tools.
Available Tools
4 toolsask_quantAsk a quant questionAIdempotentInspect
Answers a question about the numbers of named symbols, computed on Sortefi's market data, and shows how it was worked out. Covers US stocks, Indian NSE stocks, ETFs, forex pairs and crypto perpetual futures, on candles from 1 minute to monthly: total and yearly returns over any window; a lump sum or a monthly investment plan, with dividends; volatility, Sharpe, Sortino and Calmar ratios and value at risk; drawdowns, every crash and its recovery; beta, alpha and correlation against an index or another symbol; how often something happened and what followed, streaks, gaps and event studies; seasonality by weekday, month, hour or trading session; technical indicators, candlestick patterns and Renko bricks inside any statistic; statistical tests (stationarity, autocorrelation, cointegration, fitted distributions); backtests of a stated trading rule with costs, slippage, stops and targets, long or short, with a settings search and a look-ahead check; portfolios with stated or fitted weights; current fundamentals, US debt and cash history, ownership and US short interest; and options figures for Indian and crypto markets (implied volatility, put-call ratio, max pain, skew, and the payoff and Greeks of a stated strategy). Up to 8 symbols per question, or an index or group. Sortefi reads the question with its own rules and returns the answer, the tables behind it, the method, and a link to the saved answer. It reports what happened in the data — requests for advice, forecasts or trade setups are declined. For a list of symbols that match conditions, use run_screen instead. Runs on the user's Sortefi account: each completed answer is charged — a free prompt if the account has one left, otherwise wallet credits, at least 10 (1 credit = $0.01, or ₹1 on accounts topped up in rupees). The result states what was charged and the balance left. Follow-up questions and declines are free.
Inputs: market (required), question (required).
get_quant_resultGet a running quant answerARead-onlyIdempotentInspect
Returns a Sortefi quant answer that was still being worked out when ask_quant replied, using the reference ask_quant gave. Never charges again.
Inputs: ref (required).
get_screen_resultGet a running screen's resultARead-onlyIdempotentInspect
Returns the result of a Sortefi screen that was still running when run_screen answered, using the reference run_screen gave. Never charges again.
Inputs: ref (required).
run_screenRun a market screenAIdempotentInspect
Runs a market screen on Sortefi and returns the symbols that match now. Sortefi screens US stocks, Indian NSE stocks, ETFs, forex pairs and crypto perpetual futures, on timeframes from 1 minute to monthly, with technical indicators, candlestick and chart patterns, price maths and fundamentals. Sortefi reads the request with its own rules and returns what it screened in plain English, the matching symbols and a link to the saved result. Requests that are not screens (advice, forecasts, trade setups) are declined. Runs on the user's Sortefi account: each completed screen is charged — a free screen if the account has one left, otherwise wallet credits, about 20 credits on average (1 credit = $0.01, or ₹1 on accounts topped up in rupees). The result states what was charged and the balance left. Follow-up questions and declines are free. For numbers about named symbols (returns, risk, backtests), Sortefi's ask_quant tool answers instead.
Inputs: market (required), screen_request (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Screen global stocks, options, ETFs and crypto in plain English, and set email alerts on any screen.
Analytical engine for US-listed equities: screens, rankings, and event studies in plain English.
Plain-English US stock market news and daily market analysis. Free, no login.
Market analysis from live data: stocks, ETFs, commodities, crypto, reports and options levels.
Related MCP Servers
- AlicenseAqualityAmaintenanceDaily stock screens, RS ratings, market breadth and group rankings for 12 markets. No API keys.9423Apache 2.0
- AlicenseAqualityBmaintenancePoint-in-time market data for AI agents: stocks, ETFs and crypto as named bands plus raw values.105MIT
- AlicenseNot gradedqualityBmaintenanceEnables natural language quantitative analysis for US and Indian equities, including trade plans, portfolio optimization, backtests, and price alerts using real market data.4MIT
- FlicenseNot gradedqualityCmaintenanceEnables NSE stock market research with screening, quotes, peer comparison, watchlists, alerts, and strategies using natural language.-
Glama MCP Gateway
Add one secure layer between your agents and this server.