@cap-js/mcp-server

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.

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.

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.

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.

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.

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.

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).

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.

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).