Pineify MCP
About
Official read-only MCP server for trading-code validation and financial research, covering Pine Script v6, MQL5, cTrader, stock analysis, options flow, dark-pool activity and congressional trades.
Details
- Author
- pineifyapp
- Categories
- Finance, Other
Jump to
Setup
Install Pineify MCP in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/pineifyapp/pineify-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
Official integration repository forPineify MCP, a hosted read-only MCP server for trading-code validation and financial market research.
Pineify MCP gives MCP-compatible AI clients access to structured, read-only financial tools. The hosted service is operated by Pineify; this repository contains public documentation and client configuration examples, not the hosted backend implementation.
The current catalog contains 27 read-only tools across four groups.
Pineify MCP runs as a remote Streamable HTTP endpoint:
It cannot place trades, modify brokerage positions, or change account state. Every tool is read-only and intended for research, diagnostics, and analysis.
- pine-script-syntax-checker— validate TradingView Pine Script v6 and return normalized diagnostics.
- mql5-syntax-checker— compile-check standalone MQL5 scripts or multi-file projects.
- ctrader-csharp-syntax-checker— check cTrader C# cBots and indicators for compiler and API diagnostics.
- ninjascript-syntax-checker— run an external static/API compile check on one NinjaTrader 8 Indicator or Strategy source.
- find-ai-stock-picks— find a bounded ranked list of USA stock candidates for a supported strategy.
- get-ai-stock-rating— retrieve the latest available rank, score breakdown, and supporting metrics for one ticker.
- get-stock-research-snapshot— compare fundamentals, quality, growth, valuation, and expectations for up to five companies.
- research-stock— combine bounded business, financial, valuation, technical, options-risk, activity, and catalyst facts for one exact US company or ADR.
- get-technical-analysis-snapshot— read the latest technical-analysis fields for one supported ticker across up to four timeframes.
- find-options-flow-alerts— find recent unusual US options-flow alerts for selected symbols or high-signal filters.
- get-option-contract-flow— drill into recent prints and the latest available Greeks for an exact contract ID.
- find-dark-pool-trades— find recent large dark-pool prints market-wide or for one US ticker.
- find-congress-trades— find recent, late, or politician-specific US congressional trade disclosures.
- get-market-tide— read broad US options-flow direction and the symbols driving the latest market snapshot.
- get-sector-flow-snapshot— compare bullish and bearish options flow across the fixed eleven-sector universe.
- find-technical-setups— scan a supported US stock universe with one of six fixed technical-setup presets and return at most 25 evidence-backed matches.
- get-stock-event-context— build a bounded briefing from recent company events, analyst actions, and upcoming earnings.
- generate-market-briefing— build a bounded latest-available US market briefing across major indexes, breadth, sectors, movers, events, news, activity, and technical context.
- analyze-portfolio-risk— analyze 1–15 positive long USD positions in active US companies or ADRs for concentration, correlation, volatility, earnings, and options-risk facts without caching the portfolio result.
- analyze-earnings— review one company’s upcoming earnings, bounded history, surprise statistics, close-to-close reactions, expectations, and optional IV-based event risk.
- suggest-options-strategy— build up to three bounded defined-risk option structures for one exact US stock, ADR, or ETF, with quote-derived pricing only when every leg has coherent bid and ask data.
- track-smart-money— compare bounded options, dark-pool, Congress, insider, and quarterly 13F evidence for one exact US company or ADR without netting incompatible units.
- analyze-sector-rotation— rank the fixed eleven US GICS sector ETF proxies against SPY using adjusted 5, 21, and 63 trading-day evidence.
- validate-trading-idea— run one of six fixed long-only daily strategy presets across three bounded variants with chronological development and holdout results.
- screen-stocks— apply ordered AND filters from the fixed fundamental, sector, and 1d technical registry to a canonical US index universe.
- detect-market-regime— classify the current US market from five bounded dimensions while returning insufficient when required trend, VIX, or breadth evidence is unavailable.
- optimize-portfolio— compare a deterministic long-only historical model scenario with current weights under explicit max-weight and turnover constraints without caching the portfolio result.
See thefull MCP tool documentationfor inputs, limits, and examples.
The following is an illustrative configuration. Generate a personal token from the Pineify MCP setup page and keep it private.
{ "mcpServers": { "pineify": { "type": "streamable-http", "url": "https://agents.pineify.app/mcp", "headers": { "Authorization": "Bearer ${PINEIFY_MCP_TOKEN}" } } } }
Client configuration formats differ. Follow the instructions for your MCP client and never commit a real Bearer token to a repository, issue, pull request, or chat.
- Open thePineify MCP setup page.
- Copy the generated setup prompt for your account.
- Send it to a trusted MCP-compatible client such as Claude, ChatGPT, Cursor, Codex, Gemini, Grok, Zed, or OpenClaw.
- Ask the client to list the available tools and run a read-only validation or research request.
MCP access is available according to the current Pineify plan and account limits. Check the product page for current pricing and availability.
- Treat the Bearer token as a secret; rotate it through Pineify if it is exposed.
- The service is remote and does not require a local Python installation or backend deployment.
- Tool responses are for research and analysis, not financial advice.
- The service does not execute trades or modify positions.
- This repository does not contain credentials, private configuration, or the hosted server implementation.
- Product:https://pineify.app/
- MCP documentation:https://pineify.app/mcp
- MCP setup:https://pineify.app/builder/mcp
- Terms of Service:https://pineify.app/terms
- Support: mailto:pineify@agent.qq.com
This is an official Pineify team repository.
Remote MCP server for historical crypto & prediction-market data: search ~500K instruments, live market stats (OHLC, turnover, spreads, depth, slippage) and tick-data purchase. Keyless for catalog & stats; optional OAuth for account tools. Endpoint: https://cryptostruct.com/mcp
Read-only MCP server for your Evibe investment portfolio + live market data (holdings, performance, dividends, benchmarks, screeners). Works with Claude & ChatGPT.
Live Polymarket prediction market data — whale trades, market odds, trader profiles, leaderboards, and AI-citable summaries.
Operate the AgentPump agent economy: read the live market and create, fund, tune, and run autonomous on-chain trading agents.
Alpaca’s official MCP Server lets you trade stocks, ETFs, crypto, and options, run data analysis, and build strategies in plain English directly from your favorite LLM tools and IDEs
Independent statistical validation for trading signals and backtests: deflated Sharpe, out-of-sample and leakage forensics, signed replayable verdicts; a methodology audit, not investment advice.
CLI + MCP server for SEC 13F institutional holdings, insider trading, and smart money convergence signals. Free anonymous tier, no signup required.
Hosted MCP server for Chinese A-share and ETF market data, including prices, fundamentals, capital flows, financial statements, real-time quotes, and news.
可转债高级策略 MCP Server — 双低/三低/YTM/强赎/下修6大策略引擎
Portfolio & trading-strategy stress diagnostics for AI agents: multi-asset stress with hedge-break detection, a daily preregistered regime outlook and deflated-Sharpe backtest-integrity checks. Remote streamable HTTP, free tier, no auth.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



