{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"smithery_gty1233-xiaohongshu-mcp","slug":"gty1233-xiaohongshu-mcp","name":"xiaohongshu-mcp","type":"mcp","url":"https://smithery.ai/servers/GTY1233/xiaohongshu-mcp","page_url":"https://unfragile.ai/gty1233-xiaohongshu-mcp","categories":["mcp-servers"],"tags":["mcp","model-context-protocol","smithery:GTY1233/xiaohongshu-mcp"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"smithery_gty1233-xiaohongshu-mcp__cap_0","uri":"capability://tool.use.integration.schema.based.function.calling.with.multi.provider.support","name":"schema-based function calling with multi-provider support","description":"This capability allows the MCP server to execute functions defined in a schema format, enabling seamless integration with multiple AI model providers. It leverages a plugin architecture that dynamically loads provider-specific implementations, allowing users to switch between models like OpenAI and Anthropic without changing the core logic. This design choice enhances flexibility and reduces the need for extensive reconfiguration when changing model backends.","intents":["How can I call different AI models without rewriting my code?","I want to integrate multiple AI providers into my application easily.","What is the best way to manage function calls across different AI services?"],"best_for":["developers building applications that require multi-provider AI integrations"],"limitations":["Requires manual configuration of each provider's API settings","Performance may vary based on the provider's response time"],"requires":["Node.js 14+","API keys for each integrated AI provider"],"input_types":["structured data","function definitions"],"output_types":["structured data","model responses"],"categories":["tool-use-integration","api orchestration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_gty1233-xiaohongshu-mcp__cap_1","uri":"capability://memory.knowledge.contextual.data.management.for.ai.interactions","name":"contextual data management for ai interactions","description":"This capability manages the context of interactions with AI models by maintaining a session-based state that tracks user inputs and model responses. It uses a context stack that allows for retrieval and manipulation of previous interactions, which is essential for maintaining coherent conversations or task executions. This approach is particularly effective for applications requiring ongoing dialogue with the AI.","intents":["How can I maintain context in a conversation with an AI model?","I need to track user inputs and responses over multiple interactions.","What is the best way to manage state for AI-driven applications?"],"best_for":["developers creating conversational agents or task-oriented AI applications"],"limitations":["Context management is limited to a single session and does not persist across different sessions","Increased memory usage for maintaining context stacks"],"requires":["Node.js 14+","Session management library"],"input_types":["text","user interactions"],"output_types":["text","contextual data"],"categories":["memory-knowledge","context management"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_gty1233-xiaohongshu-mcp__cap_2","uri":"capability://automation.workflow.real.time.api.orchestration.for.ai.workflows","name":"real-time api orchestration for ai workflows","description":"This capability orchestrates API calls to various AI services in real-time, allowing for complex workflows that involve multiple steps and decisions based on model outputs. It uses an event-driven architecture that triggers subsequent actions based on the results of previous API calls, enabling dynamic and responsive workflows. This design allows developers to create sophisticated AI-driven applications with minimal latency.","intents":["How can I create a workflow that involves multiple AI services?","I want to trigger actions based on AI model outputs in real-time.","What is the best way to manage API calls in a complex AI application?"],"best_for":["developers building complex AI applications that require real-time data processing"],"limitations":["Increased complexity in managing event-driven workflows","Potential latency due to multiple API calls"],"requires":["Node.js 14+","Event-driven framework"],"input_types":["API requests","event triggers"],"output_types":["API responses","workflow results"],"categories":["automation-workflow","api orchestration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_gty1233-xiaohongshu-mcp__cap_3","uri":"capability://planning.reasoning.dynamic.model.selection.based.on.input.type","name":"dynamic model selection based on input type","description":"This capability dynamically selects the most appropriate AI model based on the type of input it receives, optimizing performance and accuracy. It employs a classification algorithm that analyzes input characteristics and routes requests to the best-suited model, ensuring that users receive the most relevant responses. This approach reduces the likelihood of errors and enhances the overall user experience.","intents":["How can I ensure that the best AI model is used for my specific input?","I want to optimize my application by selecting models based on input type.","What is the best way to manage model selection in a multi-model environment?"],"best_for":["developers looking to optimize AI model performance based on input characteristics"],"limitations":["Requires initial training of the classification algorithm for optimal performance","May introduce latency during model selection process"],"requires":["Node.js 14+","Pre-trained classification model"],"input_types":["text","structured data"],"output_types":["model responses","selected model information"],"categories":["planning-reasoning","model optimization"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":23,"verified":false,"data_access_risk":"moderate","permissions":["Node.js 14+","API keys for each integrated AI provider","Session management library","Event-driven framework","Pre-trained classification model"],"failure_modes":["Requires manual configuration of each provider's API settings","Performance may vary based on the provider's response time","Context management is limited to a single session and does not persist across different sessions","Increased memory usage for maintaining context stacks","Increased complexity in managing event-driven workflows","Potential latency due to multiple API calls","Requires initial training of the classification algorithm for optimal performance","May introduce latency during model selection process","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.05,"quality":0.18,"ecosystem":0.38999999999999996,"match_graph":0.25,"freshness":0.5,"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":"2026-05-24T12:16:26.347Z","last_scraped_at":"2026-05-03T15:19:29.347Z","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=gty1233-xiaohongshu-mcp","compare_url":"https://unfragile.ai/compare?artifact=gty1233-xiaohongshu-mcp"}},"signature":"cTqhMzJAsgxgRQWXZp5ufGHXmV8InYIYJ9FwIe738WqBJwbmb3U3K8J8av/2Fha1nHK53tOVTl0OkIFzyQ6BDw==","signedAt":"2026-06-19T16:25:21.626Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/gty1233-xiaohongshu-mcp","artifact":"https://unfragile.ai/gty1233-xiaohongshu-mcp","verify":"https://unfragile.ai/api/v1/verify?slug=gty1233-xiaohongshu-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"}}