{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"npm_npm-cap-jsmcp-server","slug":"npm-cap-jsmcp-server","name":"@cap-js/mcp-server","type":"mcp","url":"https://www.npmjs.com/package/@cap-js/mcp-server","page_url":"https://unfragile.ai/npm-cap-jsmcp-server","categories":["mcp-servers"],"tags":[],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"npm_npm-cap-jsmcp-server__cap_0","uri":"capability://tool.use.integration.cap.application.context.exposure.via.mcp.protocol","name":"cap application context exposure via mcp protocol","description":"Exposes SAP CAP (Cloud Application Programming) project structure, metadata, and configuration as MCP resources through a standardized protocol interface. The server introspects CAP project files (package.json, cds files, data models) and surfaces them as queryable resources that AI clients can discover and reference, enabling context-aware assistance without requiring the AI to parse project structure directly.","intents":["I want Claude or another AI to understand my CAP project structure and suggest code changes that respect my data models","I need an AI assistant to have access to my CDS entity definitions and service definitions so it can generate compatible code","I want to expose my CAP application metadata to multiple AI tools through a standard protocol"],"best_for":["SAP CAP developers using Claude, ChatGPT, or other MCP-compatible AI clients","Teams building enterprise applications on SAP Cloud Application Programming model","Developers integrating AI assistance into existing CAP development workflows"],"limitations":["Limited to CAP-specific project structures — will not provide useful context for non-CAP Node.js projects","Requires the AI client to support MCP protocol — not compatible with basic REST API integrations","No built-in caching of project metadata — re-introspection on each client connection may add latency for large projects"],"requires":["Node.js 14+ runtime","SAP CAP project with valid package.json and cds configuration","MCP-compatible AI client (Claude Desktop, or custom client with MCP support)","@cap-js/mcp-server npm package installed as dev dependency"],"input_types":["CAP project file system (cds files, package.json, db/srv directories)","MCP resource discovery requests from client"],"output_types":["MCP resource descriptions (JSON)","Project metadata (entity schemas, service definitions)","File content and structure information"],"categories":["tool-use-integration","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm_npm-cap-jsmcp-server__cap_1","uri":"capability://data.processing.analysis.cds.entity.and.service.schema.introspection","name":"cds entity and service schema introspection","description":"Parses and analyzes CAP's Core Data Services (CDS) definition files to extract entity schemas, relationships, service definitions, and annotations. The server reads .cds files, builds an in-memory representation of the data model, and exposes entity properties, types, associations, and service operations as queryable metadata that AI assistants can use to generate type-safe code.","intents":["I want the AI to know what fields and types are available in my CDS entities so it generates compatible queries","I need the AI to understand entity relationships and associations when suggesting data model changes","I want the AI to be aware of my service definitions and available operations when generating API calls"],"best_for":["CAP developers who want AI-assisted code generation that respects their data model constraints","Teams with complex CDS schemas who need AI to understand entity relationships and annotations","Developers building custom CAP extensions and needing AI to understand existing service contracts"],"limitations":["Only parses CDS syntax — does not execute or validate CDS logic at runtime","Annotations are exposed as metadata but not interpreted semantically (e.g., @cds.persistence.name is visible but not resolved to actual DB column names)","Does not track CDS inheritance chains or mixin composition in real-time — static analysis only"],"requires":["Valid CDS files in db/data-model.cds or srv/*.cds paths","CDS syntax must be parseable (no syntax errors in .cds files)","Node.js 14+ with file system access to project root"],"input_types":["CDS definition files (.cds)","CAP project configuration (package.json with cds section)"],"output_types":["Entity schema definitions (JSON/structured format)","Service operation signatures","Association and relationship metadata","Annotation metadata"],"categories":["data-processing-analysis","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm_npm-cap-jsmcp-server__cap_2","uri":"capability://tool.use.integration.mcp.resource.discovery.and.listing","name":"mcp resource discovery and listing","description":"Implements the MCP resource listing protocol, allowing clients to discover available resources (CDS entities, services, configuration files) without prior knowledge of the project structure. The server maintains a resource registry that maps CAP project artifacts to MCP resource URIs and provides metadata (name, description, MIME type) for each resource, enabling clients to browse and select relevant context.","intents":["I want my AI client to automatically discover what resources are available in my CAP project","I need the AI to show me a list of entities and services it can reference when generating code","I want to browse my project structure through the AI interface without leaving the chat"],"best_for":["AI client developers building MCP-compatible interfaces for CAP projects","Teams using Claude Desktop or similar MCP clients who want resource browsing UI","Developers building custom AI workflows that need to dynamically discover CAP artifacts"],"limitations":["Resource discovery is static — does not reflect runtime changes to project structure without server restart","No filtering or search capabilities in the protocol layer — clients must implement their own filtering logic","Resource descriptions are auto-generated from metadata — may lack semantic context for complex services"],"requires":["MCP client that supports resource listing (listResources RPC method)","CAP project with discoverable CDS files and configuration","Server running and accessible to MCP client"],"input_types":["MCP listResources request (no parameters required)"],"output_types":["MCP resource list (array of resource objects with uri, name, description, mimeType)"],"categories":["tool-use-integration","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm_npm-cap-jsmcp-server__cap_3","uri":"capability://tool.use.integration.mcp.resource.content.retrieval.with.caching","name":"mcp resource content retrieval with caching","description":"Handles MCP readResource requests by retrieving and serving CAP project file contents (CDS definitions, configuration, documentation) through the MCP protocol. The server reads files from disk, applies optional caching to reduce I/O for frequently accessed resources, and returns content in appropriate formats (text, JSON) with metadata about the resource type and encoding.","intents":["I want the AI to read my CDS entity definitions when I reference them in a prompt","I need the AI to fetch my service definitions and annotations without me copy-pasting them","I want the AI to access my CAP configuration files to understand project settings"],"best_for":["MCP clients that need to fetch full resource content for context injection","CAP developers who want AI to reference actual project files rather than descriptions","Teams with large CDS files who benefit from caching to reduce latency"],"limitations":["No built-in file watching — changes to files are not reflected until server restart or cache invalidation","Large files (>1MB) may cause performance issues if cached in memory","No access control — all resources readable by MCP client are exposed without authentication","Binary files not supported — only text-based content (CDS, JSON, YAML, markdown)"],"requires":["File system read access to CAP project directory","MCP client that supports readResource RPC method","Server running with project root directory configured"],"input_types":["MCP readResource request with resource URI"],"output_types":["File content as text (CDS, JSON, YAML, markdown)","Resource metadata (mimeType, size, encoding)"],"categories":["tool-use-integration","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm_npm-cap-jsmcp-server__cap_4","uri":"capability://tool.use.integration.tool.calling.interface.for.cap.development.tasks","name":"tool calling interface for cap development tasks","description":"Exposes CAP development operations as MCP tools that AI clients can invoke, such as generating boilerplate code, validating CDS syntax, or scaffolding new services. The server implements tool definitions with input schemas (JSON Schema) that describe parameters, and executes the corresponding CAP operations, returning structured results that the AI can interpret and present to the user.","intents":["I want the AI to generate a new CDS entity with proper syntax and annotations","I need the AI to validate my CDS file and report errors before I save it","I want the AI to scaffold a new service with CRUD operations matching my entity"],"best_for":["CAP developers using AI assistants to accelerate boilerplate generation","Teams with code generation standards who want AI to follow CAP best practices","Developers building custom CAP scaffolding tools that integrate with AI workflows"],"limitations":["Tool execution is synchronous — long-running operations (e.g., large code generation) may timeout","No built-in rollback — generated code is written directly to disk without transaction support","Tool definitions are static — cannot dynamically register new tools at runtime","Limited to development tasks — no production data operations or deployment tools"],"requires":["MCP client that supports tool calling (callTool RPC method)","CAP project with write access to file system","Node.js 14+ with CAP CLI or SDK available"],"input_types":["MCP tool call request with tool name and parameters (JSON)","Parameters validated against JSON Schema defined in tool definition"],"output_types":["Tool execution result (success/failure status)","Generated code or validation output","Error messages with diagnostic information"],"categories":["tool-use-integration","code-generation-editing"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm_npm-cap-jsmcp-server__cap_5","uri":"capability://data.processing.analysis.project.configuration.and.metadata.exposure","name":"project configuration and metadata exposure","description":"Reads and exposes CAP project configuration from package.json (cds section), .cdsrc.json, and other configuration files as MCP resources. The server parses configuration to extract project settings (database type, build profiles, middleware configuration) and makes this metadata available to AI clients, enabling context-aware suggestions that respect project-specific settings.","intents":["I want the AI to know my database type (SQLite, PostgreSQL, HANA) when suggesting queries","I need the AI to understand my build profiles and suggest code that works with my deployment target","I want the AI to be aware of my middleware configuration when suggesting service implementations"],"best_for":["CAP developers with non-standard configurations who need AI to respect their setup","Teams with multiple deployment targets who want AI to generate database-agnostic code","Developers building AI-assisted CAP tools that need to understand project configuration"],"limitations":["Only reads static configuration files — does not resolve environment variables or runtime configuration","Does not validate configuration correctness — exposes raw config even if invalid","Limited to standard CAP configuration locations — custom config files not discovered automatically","No support for configuration inheritance or profile merging — exposes only the primary config file"],"requires":["Valid package.json with cds section or .cdsrc.json file","File system read access to project root","Node.js 14+ with JSON parsing capability"],"input_types":["package.json (cds section)",".cdsrc.json","CAP configuration files"],"output_types":["Parsed configuration object (JSON)","Configuration metadata (database type, profiles, middleware list)"],"categories":["data-processing-analysis","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm_npm-cap-jsmcp-server__cap_6","uri":"capability://tool.use.integration.multi.client.mcp.server.lifecycle.management","name":"multi-client mcp server lifecycle management","description":"Manages the MCP server lifecycle, handling client connections, protocol negotiation, and request routing. The server implements the MCP protocol specification, manages concurrent client connections, handles protocol versioning, and ensures proper cleanup of resources when clients disconnect. Built on Node.js with support for stdio-based transport (standard for local AI clients like Claude Desktop).","intents":["I want to run an MCP server that Claude Desktop can connect to for CAP development assistance","I need the server to handle multiple concurrent AI client connections without conflicts","I want the server to properly initialize and shut down without leaving orphaned processes"],"best_for":["CAP developers using Claude Desktop or other MCP-compatible AI clients","Teams deploying MCP servers for local development environments","Developers building custom MCP client integrations with CAP projects"],"limitations":["Stdio-based transport only — no HTTP or WebSocket support for remote clients","Single-threaded Node.js event loop — high concurrency may cause request queuing","No built-in authentication or authorization — all connected clients have equal access","No persistence of server state — configuration and cache lost on restart"],"requires":["Node.js 14+ runtime","MCP client that supports stdio transport (Claude Desktop, custom client)","CAP project directory accessible to server process"],"input_types":["MCP protocol messages via stdin (JSON-RPC 2.0)"],"output_types":["MCP protocol responses via stdout (JSON-RPC 2.0)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm_npm-cap-jsmcp-server__cap_7","uri":"capability://code.generation.editing.cap.aware.code.generation.with.template.support","name":"cap-aware code generation with template support","description":"Generates CAP-compliant code (CDS entities, services, handlers) using templates that respect CAP conventions and patterns. The server maintains a library of code templates for common CAP structures (entity definitions, service implementations, event handlers) and uses these templates to generate boilerplate code that integrates with the existing project structure and follows best practices.","intents":["I want the AI to generate a new CDS entity with proper syntax and common annotations","I need the AI to create a service implementation that follows my project's patterns","I want the AI to generate event handlers that integrate with my existing services"],"best_for":["CAP developers who want AI-assisted code generation that follows project conventions","Teams with established CAP patterns who want AI to maintain consistency","Developers building custom CAP scaffolding tools with AI assistance"],"limitations":["Templates are predefined — cannot dynamically learn new patterns from existing code","Generated code requires manual review and integration — not production-ready without validation","Limited to common CAP patterns — complex custom logic requires manual implementation","No support for custom annotations or domain-specific extensions beyond standard CAP"],"requires":["CAP project with valid structure (db/, srv/ directories)","MCP tool calling support in client","Write access to project file system"],"input_types":["Code generation parameters (entity name, properties, service type)","Optional: existing code samples for pattern learning"],"output_types":["Generated CDS code (entity definitions, service definitions)","Generated JavaScript/TypeScript code (service implementations, handlers)","Integration instructions or warnings"],"categories":["code-generation-editing","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"npm_npm-cap-jsmcp-server__cap_8","uri":"capability://code.generation.editing.cds.syntax.validation.and.error.reporting","name":"cds syntax validation and error reporting","description":"Validates CDS file syntax and reports errors with diagnostic information (line numbers, error messages, suggestions). The server parses CDS files, checks for syntax errors, and provides structured error output that AI clients can use to guide users toward fixes. Validation includes checking for common mistakes (missing semicolons, invalid type references, malformed associations).","intents":["I want the AI to check my CDS file for syntax errors before I save it","I need the AI to explain what's wrong with my entity definition and suggest fixes","I want the AI to validate my service definition and report any issues"],"best_for":["CAP developers who want real-time syntax validation through AI assistance","Teams building custom CAP development tools with validation feedback","Developers using AI to learn CAP syntax and best practices"],"limitations":["Validates syntax only — does not check semantic correctness (e.g., entity references, type compatibility)","Error messages are generic — may not provide actionable suggestions for complex issues","Does not validate against runtime constraints (e.g., database column name limits)","No support for custom CDS extensions or domain-specific syntax"],"requires":["CDS file content (text)","MCP tool calling support in client","CDS parser library (built into @cap-js/mcp-server)"],"input_types":["CDS file content (text)","Optional: file path for context"],"output_types":["Validation result (valid/invalid status)","Error list with line numbers and messages","Suggested fixes or corrections"],"categories":["code-generation-editing","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":26,"verified":false,"data_access_risk":"high","permissions":["Node.js 14+ runtime","SAP CAP project with valid package.json and cds configuration","MCP-compatible AI client (Claude Desktop, or custom client with MCP support)","@cap-js/mcp-server npm package installed as dev dependency","Valid CDS files in db/data-model.cds or srv/*.cds paths","CDS syntax must be parseable (no syntax errors in .cds files)","Node.js 14+ with file system access to project root","MCP client that supports resource listing (listResources RPC method)","CAP project with discoverable CDS files and configuration","Server running and accessible to MCP client"],"failure_modes":["Limited to CAP-specific project structures — will not provide useful context for non-CAP Node.js projects","Requires the AI client to support MCP protocol — not compatible with basic REST API integrations","No built-in caching of project metadata — re-introspection on each client connection may add latency for large projects","Only parses CDS syntax — does not execute or validate CDS logic at runtime","Annotations are exposed as metadata but not interpreted semantically (e.g., @cds.persistence.name is visible but not resolved to actual DB column names)","Does not track CDS inheritance chains or mixin composition in real-time — static analysis only","Resource discovery is static — does not reflect runtime changes to project structure without server restart","No filtering or search capabilities in the protocol layer — clients must implement their own filtering logic","Resource descriptions are auto-generated from metadata — may lack semantic context for complex services","No built-in file watching — changes to files are not reflected until server restart or cache invalidation","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.05,"quality":0.28,"ecosystem":0.3,"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":"2026-05-24T12:16:23.903Z","last_scraped_at":"2026-05-03T14:23:34.579Z","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=npm-cap-jsmcp-server","compare_url":"https://unfragile.ai/compare?artifact=npm-cap-jsmcp-server"}},"signature":"VhadMIgrk3Byzaote8IsE6z9xyKxeUNoUzIDCB0BPBFx18xRORfyT79bKAWu/CRJ2dxZfQEsXmTSHGVGxXM7BA==","signedAt":"2026-06-21T06:34:00.491Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/npm-cap-jsmcp-server","artifact":"https://unfragile.ai/npm-cap-jsmcp-server","verify":"https://unfragile.ai/api/v1/verify?slug=npm-cap-jsmcp-server","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"}}