Skip to main content
Glama

memory_recall

Retrieve stored project information and insights by searching with queries or project IDs to access previous analyses, recommendations, configurations, and interactions.

Instructions

Recall memories about a project or topic

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query or project ID
typeNoType of memory to recall
limitNoMaximum number of memories to return

Implementation Reference

  • The core handler function that implements the memory_recall tool. It initializes the memory manager, performs a search based on the query, optional type filter, and limit, then returns the matching memories with metadata.
    export async function handleMemoryRecall(args: {
      query: string;
      type?: string;
      limit?: number;
    }): Promise<any> {
      const manager = await initializeMemory();
    
      const searchOptions: any = {
        sortBy: "timestamp",
        limit: args.limit || 10,
      };
    
      if (args.type && args.type !== "all") {
        searchOptions.type = args.type;
      }
    
      const memories = await manager.search({}, searchOptions);
    
      return {
        query: args.query,
        type: args.type || "all",
        count: memories.length,
        memories: memories.map((m: any) => ({
          id: m.id,
          type: m.type,
          timestamp: m.timestamp,
          data: m.data,
          metadata: m.metadata,
        })),
      };
    }
  • The registration of the memory_recall tool within the exported memoryTools array, including name, description, and input schema.
    {
      name: "memory_recall",
      description: "Recall memories about a project or topic",
      inputSchema: {
        type: "object",
        properties: {
          query: {
            type: "string",
            description: "Search query or project ID",
          },
          type: {
            type: "string",
            enum: [
              "analysis",
              "recommendation",
              "deployment",
              "configuration",
              "interaction",
              "all",
            ],
            description: "Type of memory to recall",
          },
          limit: {
            type: "number",
            description: "Maximum number of memories to return",
            default: 10,
          },
        },
        required: ["query"],
      },
    },
  • The input schema definition for the memory_recall tool, specifying the expected parameters: query (required), type (enum), and limit.
    inputSchema: {
      type: "object",
      properties: {
        query: {
          type: "string",
          description: "Search query or project ID",
        },
        type: {
          type: "string",
          enum: [
            "analysis",
            "recommendation",
            "deployment",
            "configuration",
            "interaction",
            "all",
          ],
          description: "Type of memory to recall",
        },
        limit: {
          type: "number",
          description: "Maximum number of memories to return",
          default: 10,
        },
      },
      required: ["query"],
    },

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/tosin2013/documcp'

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