{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"smithery_irresi-bl-view-mcp","slug":"irresi-bl-view-mcp","name":"Finance Portfolio Optimizer","type":"mcp","url":"https://github.com/irresi/bl-view-mcp","page_url":"https://unfragile.ai/irresi-bl-view-mcp","categories":["mcp-servers","testing-quality"],"tags":["mcp","model-context-protocol","smithery:irresi/bl-view-mcp"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"smithery_irresi-bl-view-mcp__cap_0","uri":"capability://data.processing.analysis.black.litterman.portfolio.optimization","name":"black-litterman portfolio optimization","description":"Utilizes the Black-Litterman model to optimize finance portfolios by integrating user-defined return views and confidence levels. This capability employs a mathematical framework that combines market equilibrium returns with user insights, allowing for dynamic adjustments based on individual risk tolerance and market conditions. The implementation leverages matrix algebra for efficient calculations and integrates seamlessly with various financial data sources to provide real-time optimization.","intents":["How can I optimize my investment portfolio using my own market views?","What is the best way to incorporate my confidence levels into portfolio decisions?","Can I adjust my portfolio based on real-time market data?"],"best_for":["financial analysts looking to customize investment strategies"],"limitations":["Requires accurate input data for effective optimization; poor data quality can lead to suboptimal results."],"requires":["Python 3.8+","NumPy library for matrix operations"],"input_types":["structured data (returns, confidence levels)"],"output_types":["structured data (optimized portfolio allocations)"],"categories":["data-processing-analysis","financial-tools"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_irresi-bl-view-mcp__cap_1","uri":"capability://data.processing.analysis.backtesting.investment.strategies","name":"backtesting investment strategies","description":"Enables users to backtest their investment strategies by simulating portfolio performance over historical data. This capability employs time-series analysis to evaluate how the portfolio would have performed under various market conditions, using metrics like drawdowns and Value at Risk (VaR) to assess risk. The implementation uses efficient data handling techniques to process large datasets quickly, providing insights into potential future performance based on past trends.","intents":["How can I test my investment strategy against historical data?","What metrics can I use to evaluate the risk of my portfolio?","Can I see how my portfolio would have performed in past market conditions?"],"best_for":["quantitative analysts testing investment hypotheses"],"limitations":["Backtesting results may not predict future performance due to changing market conditions."],"requires":["Python 3.8+","pandas library for data manipulation"],"input_types":["structured data (historical prices, portfolio allocations)"],"output_types":["structured data (performance metrics, visualizations)"],"categories":["data-processing-analysis","financial-tools"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_irresi-bl-view-mcp__cap_2","uri":"capability://data.processing.analysis.risk.analysis.and.visualization","name":"risk analysis and visualization","description":"Analyzes portfolio risk by calculating correlations, drawdowns, and Value at Risk (VaR) and presents this information through interactive dashboards. This capability utilizes advanced statistical methods to assess how different assets interact and the potential impact of market fluctuations on overall portfolio risk. The visualization component is built using modern web technologies to create user-friendly dashboards that allow for real-time monitoring and analysis.","intents":["How can I visualize the risk associated with my investment portfolio?","What are the correlations between different assets in my portfolio?","Can I track drawdowns and VaR in real-time?"],"best_for":["portfolio managers needing to monitor risk dynamically"],"limitations":["Visualizations may become cluttered with large datasets, making it harder to interpret."],"requires":["Python 3.8+","Dash or similar library for dashboard creation"],"input_types":["structured data (asset prices, portfolio allocations)"],"output_types":["visual data (interactive dashboards, charts)"],"categories":["data-processing-analysis","visualization-tools"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_irresi-bl-view-mcp__cap_3","uri":"capability://tool.use.integration.custom.asset.upload.and.integration","name":"custom asset upload and integration","description":"Allows users to upload custom asset data for analysis, enabling the optimization of portfolios that include non-standard investments such as alternative assets or private equity. This capability uses a flexible data ingestion pipeline that can handle various data formats and integrates seamlessly with existing datasets. The architecture supports both structured and unstructured data, ensuring a comprehensive approach to portfolio optimization.","intents":["How can I include my own assets in the portfolio optimization process?","What formats can I use to upload custom asset data?","Can I analyze alternative investments alongside traditional assets?"],"best_for":["investors with unique or non-traditional asset classes"],"limitations":["Custom data must be formatted correctly; otherwise, integration may fail."],"requires":["Python 3.8+","API access for data integration"],"input_types":["structured data (custom asset prices)"],"output_types":["structured data (optimized portfolio including custom assets)"],"categories":["tool-use-integration","financial-tools"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":31,"verified":false,"data_access_risk":"moderate","permissions":["Python 3.8+","NumPy library for matrix operations","pandas library for data manipulation","Dash or similar library for dashboard creation","API access for data integration"],"failure_modes":["Requires accurate input data for effective optimization; poor data quality can lead to suboptimal results.","Backtesting results may not predict future performance due to changing market conditions.","Visualizations may become cluttered with large datasets, making it harder to interpret.","Custom data must be formatted correctly; otherwise, integration may fail.","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.05,"quality":0.33,"ecosystem":0.5900000000000001,"match_graph":0.25,"freshness":0.6,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.15,"match_graph":0.23,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:26.914Z","last_scraped_at":"2026-05-03T15:19:33.056Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=irresi-bl-view-mcp","compare_url":"https://unfragile.ai/compare?artifact=irresi-bl-view-mcp"}},"signature":"5lBSCx6n41Lh4pgFFdrx0nU3UH+CxLgkWeKYV+//FHNPJ3k5i26JcsWATnLCW6FzrYlgLzvBpyAt8v2phRzdBg==","signedAt":"2026-06-21T01:47:07.872Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/irresi-bl-view-mcp","artifact":"https://unfragile.ai/irresi-bl-view-mcp","verify":"https://unfragile.ai/api/v1/verify?slug=irresi-bl-view-mcp","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}