Commit graph

1 commit

Author SHA1 Message Date
2e8e947adc **feat: implement Model Control Protocol (MCP) for Brainy with WebSocket and REST interfaces**
### Changes:
- **Core MCP Components**:
  - Introduced `BrainyMCPAdapter`, `BrainyMCPService`, and `MCPAugmentationToolset` for handling data access, tool execution, system information, and authentication via MCP.
  - Added asynchronous handlers to process requests for Brainy data, augmentations, and relationships.
  - Built pipelines to expose Brainy augmentation capabilities as tools.

- **Server Implementations**:
  - Added WebSocket and REST interfaces in `initializeMCPService` for external MCP requests.
  - Included rate limiting, authentication, and CORS support for REST API.

- **Type Definitions**:
  - Defined MCP-related types such as `MCPRequestType`, `MCPResponse`, and `MCPToolExecutionRequest` in `src/types/mcpTypes.ts`.
  - Incorporated augmentation-type-specific methods from `augmentationPipeline`.

- **Exports**:
  - Exposed MCP modules (`BrainyMCPAdapter`, `BrainyMCPService`, `MCPAugmentationToolset`) via `src/mcp/index.ts`.

### Purpose:
Introduced a Model Control Protocol (MCP) framework to enable seamless integration of Brainy data and augmentation tools with external models. The implementation provides structured, scalable access to data and tools through both WebSocket and REST APIs.
2025-06-20 10:56:21 -07:00