MCP server for retrieval augmented thinking and problem solving
An MCP (Model Context Protocol) server implementation that enhances AI model capabilities with structured, retrieval-augmented thinking processes. This server enables dynamic thought chains, parallel exploration paths, and recursive refinement cycles for improved reasoning and problem-solving.
npm install @modelcontextprotocol/server-retrieval-augmented-thinking
mcp-server-retrieval-augmented-thinking
import { Server } from '@modelcontextprotocol/sdk/server';
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio';
// Initialize and run the server
const server = new Server({
name: 'retrieval-augmented-thinking',
version: '0.1.0'
});
// Connect transport
const transport = new StdioServerTransport();
await server.connect(transport);
The server provides a tool with the following parameters:
thought
(string): Current reasoning stepthoughtNumber
(number): Position in reasoning chaintotalThoughts
(number): Estimated scopenextThoughtNeeded
(boolean): Chain continuation signalisRevision
(boolean, optional): Marks refinement stepsrevisesThought
(number, optional): References target thoughtbranchFromThought
(number, optional): Branch origin pointbranchId
(string, optional): Branch identifierneedsMoreThoughts
(boolean, optional): Scope expansion signalThe server tracks various metrics for thought chain quality:
Analyzes thought patterns for:
## Build
npm run build
## Watch mode
npm run watch
Contributions welcome! Please read our contributing guidelines and submit pull requests.
MIT