Skip to main content
Glama
mixelpixx

meMCP - Memory-Enhanced Model Context Protocol

memory_optimize

Optimizes memory usage in LLMs to enable continuous learning and knowledge retention across sessions through the Model Context Protocol.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • Main handler logic for the 'memory_optimize' tool. Parses input arguments and orchestrates the optimization process by calling optimizeSystem.
    async handleOptimize(args) {
      try {
        const { rebuildIndexes = true, compactStorage = true, rebuildSemantic = true } = args;
        
        const optimizeResult = await this.optimizeSystem({
          rebuildIndexes,
          compactStorage,
          rebuildSemantic,
        });
        
        return {
          content: [
            {
              type: 'text',
              text: `⚡ **Optimization Complete**\n\n**Rebuilt Indexes:** ${rebuildIndexes ? 'Yes' : 'No'}\n**Compacted Storage:** ${compactStorage ? 'Yes' : 'No'}\n**Rebuilt Semantic Index:** ${rebuildSemantic ? 'Yes' : 'No'}\n**Duration:** ${optimizeResult.duration}ms\n**Storage Saved:** ${optimizeResult.spaceSaved || 'N/A'}`,
            },
          ],
        };
      } catch (error) {
        return {
          content: [
            {
              type: 'text',
              text: `Error optimizing system: ${error.message}`,
            },
          ],
          isError: true,
        };
      }
    }
  • Input schema defining parameters for the memory_optimize tool.
      type: 'object',
      properties: {
        rebuildIndexes: {
          type: 'boolean',
          description: 'Rebuild all search indexes',
          default: true,
        },
        compactStorage: {
          type: 'boolean',
          description: 'Compact storage files',
          default: true,
        },
        rebuildSemantic: {
          type: 'boolean',
          description: 'Rebuild semantic search index',
          default: true,
        },
      },
    },
  • Registers the 'memory_optimize' tool on the server with name, description, schema, and handler function.
    server.registerTool(
      'memory_optimize',
      'Optimize the memory system performance and storage',
      {
        type: 'object',
        properties: {
          rebuildIndexes: {
            type: 'boolean',
            description: 'Rebuild all search indexes',
            default: true,
          },
          compactStorage: {
            type: 'boolean',
            description: 'Compact storage files',
            default: true,
          },
          rebuildSemantic: {
            type: 'boolean',
            description: 'Rebuild semantic search index',
            default: true,
          },
        },
      },
      async (args) => {
        return await this.handleOptimize(args);
      }
    );
  • Core helper method that performs the actual optimization tasks like rebuilding indexes and measures performance.
    async optimizeSystem(options = {}) {
      try {
        const startTime = Date.now();
        const { rebuildIndexes, compactStorage, rebuildSemantic } = options;
        
        if (rebuildIndexes) {
          await this.factStore.rebuildIndexes();
        }
        
        if (rebuildSemantic) {
          this.factStore.rebuildSemanticIndex();
        }
        
        const duration = Date.now() - startTime;
        
        return {
          duration,
          spaceSaved: null,
          indexesRebuilt: rebuildIndexes,
          semanticRebuilt: rebuildSemantic,
          storageCompacted: compactStorage,
        };
      } catch (error) {
        throw new Error(`Failed to optimize system: ${error.message}`);
      }
  • Top-level registration in MemoryTools that invokes MemoryManagement.registerTools, indirectly registering memory_optimize.
    async registerTools(server) {
      // Register tools from modular components
      this.operations.registerTools(server);
      this.queryHandler.registerTools(server);
      this.streamingTools.registerTools(server);
      this.management.registerTools(server);
    }

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/mixelpixx/meMCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server