{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"smithery_vezlo-src-to-kb","slug":"vezlo-src-to-kb","name":"vezlo/src-to-kb","type":"mcp","url":"https://github.com/vezlo/src-to-kb","page_url":"https://unfragile.ai/vezlo-src-to-kb","categories":["mcp-servers","rag-knowledge","app-builders"],"tags":["mcp","model-context-protocol","smithery:vezlo/src-to-kb"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"smithery_vezlo-src-to-kb__cap_0","uri":"capability://data.processing.analysis.automated.source.code.chunking","name":"automated source code chunking","description":"This capability employs a systematic approach to break down source code repositories into manageable chunks, utilizing static analysis techniques to identify logical code segments. By analyzing the code structure and dependencies, it ensures that each chunk maintains context, which is crucial for effective embedding generation and search functionality. This method allows for a more nuanced understanding of code relationships compared to simple line-based splitting.","intents":["How can I convert my codebase into smaller, context-aware segments for better searchability?","I need to break down a large repository into logical parts for embedding generation.","What is the best way to prepare my source code for integration into a knowledge base?"],"best_for":["developers looking to enhance code discoverability in large repositories"],"limitations":["May struggle with highly dynamic languages where context is less predictable","Chunking process may introduce overhead for very large codebases"],"requires":["Node.js 14+","Access to the source code repository"],"input_types":["source code"],"output_types":["structured data"],"categories":["data-processing-analysis","code-organization"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_vezlo-src-to-kb__cap_1","uri":"capability://data.processing.analysis.embedding.generation.for.code","name":"embedding generation for code","description":"This capability generates embeddings for each code chunk using advanced neural network models, specifically designed for programming languages. By leveraging contextual information from the chunking process, it creates high-dimensional vector representations that capture semantic meaning, enabling efficient similarity searches and retrieval. The integration with MCP allows for seamless embedding generation tailored for Claude Code and Cursor.","intents":["How can I generate embeddings for my codebase to support intelligent search?","I want to create a searchable knowledge base from my source code using embeddings.","What is the best way to represent my code semantically for retrieval purposes?"],"best_for":["data scientists and developers building intelligent code search systems"],"limitations":["Embedding quality may vary based on the complexity of the code and the model used","Requires significant computational resources for large repositories"],"requires":["Python 3.8+","Pre-trained embedding model access"],"input_types":["structured data"],"output_types":["embeddings"],"categories":["data-processing-analysis","machine-learning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_vezlo-src-to-kb__cap_2","uri":"capability://search.retrieval.intelligent.search.capabilities","name":"intelligent search capabilities","description":"This capability implements a sophisticated search mechanism that leverages the generated embeddings to perform semantic searches across the knowledge base. It uses vector similarity metrics to retrieve relevant code chunks based on user queries, allowing for natural language search inputs. The integration with Claude Code and Cursor enhances the search experience by providing contextual results tailored to the user's intent.","intents":["How can I search my codebase using natural language queries?","I need to retrieve specific code snippets based on semantic meaning rather than exact matches.","What is the best way to find relevant code examples in my knowledge base?"],"best_for":["developers and researchers needing advanced code search functionalities"],"limitations":["Search results may be less effective for very niche queries with limited context","Performance can degrade with extremely large datasets without proper indexing"],"requires":["Node.js 14+","Access to the knowledge base with embeddings"],"input_types":["natural language queries"],"output_types":["search results"],"categories":["search-retrieval","knowledge-discovery"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_vezlo-src-to-kb__cap_3","uri":"capability://tool.use.integration.mcp.integration.for.enhanced.functionality","name":"mcp integration for enhanced functionality","description":"This capability allows for seamless integration with the Model Context Protocol (MCP), enabling the artifact to communicate effectively with other MCP-compliant tools like Claude Code and Cursor. It supports function calling and context sharing, facilitating a more cohesive workflow for developers. This integration is designed to enhance the overall user experience by allowing for dynamic context adjustments based on the user's interactions.","intents":["How can I integrate my knowledge base with other tools using MCP?","I want to enable function calling in my code search application.","What are the benefits of using MCP for my development workflow?"],"best_for":["developers using multiple tools in their workflow"],"limitations":["Dependency on MCP compliance from other tools may limit integration options","Requires understanding of MCP for effective use"],"requires":["MCP-compliant tools","Node.js 14+"],"input_types":["function calls","context data"],"output_types":["contextual responses","function results"],"categories":["tool-use-integration","workflow-automation"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":33,"verified":false,"data_access_risk":"moderate","permissions":["Node.js 14+","Access to the source code repository","Python 3.8+","Pre-trained embedding model access","Access to the knowledge base with embeddings","MCP-compliant tools"],"failure_modes":["May struggle with highly dynamic languages where context is less predictable","Chunking process may introduce overhead for very large codebases","Embedding quality may vary based on the complexity of the code and the model used","Requires significant computational resources for large repositories","Search results may be less effective for very niche queries with limited context","Performance can degrade with extremely large datasets without proper indexing","Dependency on MCP compliance from other tools may limit integration options","Requires understanding of MCP for effective use","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.05,"quality":0.33,"ecosystem":0.6900000000000001,"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":"2026-05-24T12:16:28.693Z","last_scraped_at":"2026-05-03T15:19:48.006Z","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=vezlo-src-to-kb","compare_url":"https://unfragile.ai/compare?artifact=vezlo-src-to-kb"}},"signature":"TtmzuvjZ21mNc2C4DkgyE9RQoi4a0A7d6+5PA595s2HhI2CZ1Nzvu+PzuqT3zIy3Mt/zRf6EDAmcBTZWSOWyDg==","signedAt":"2026-06-19T22:11:36.897Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/vezlo-src-to-kb","artifact":"https://unfragile.ai/vezlo-src-to-kb","verify":"https://unfragile.ai/api/v1/verify?slug=vezlo-src-to-kb","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"}}