AGI MCP Server

Instructions

Implementation Reference

• src/memory-manager.js:813-855 (handler)

  Core handler function in MemoryManager that executes the pruning logic: updates old, low-importance, rarely-accessed archived memories to 'deleted' status and logs the changes.

  async pruneMemories(criteria = {}) {
    try {
      const {
        maxAge = 1095, // 3 years
        minImportance = 0.1,
        maxAccessCount = 2,
        status = 'archived'
      } = criteria;
  
      const cutoffDate = new Date(Date.now() - maxAge * 24 * 60 * 60 * 1000);
  
      const prunedMemories = await this.db
        .update(schema.memories)
        .set({ status: 'deleted' })
        .where(
          and(
            eq(schema.memories.status, status),
            lt(schema.memories.createdAt, cutoffDate),
            lt(schema.memories.importance, minImportance),
            lte(schema.memories.accessCount, maxAccessCount)
          )
        )
        .returning({
          id: schema.memories.id,
          content: schema.memories.content,
          type: schema.memories.type
        });
  
      // Record deletion events
      for (const memory of prunedMemories) {
        await this.db.insert(schema.memoryChanges).values({
          memoryId: memory.id,
          changeType: 'deletion',
          newValue: { reason: 'Pruned based on criteria', criteria }
        });
      }
  
      return prunedMemories;
    } catch (error) {
      console.warn('Memory pruning failed:', error.message);
      return [];
    }
  }

• src/tools/memory-tools.js:314-346 (schema)

  Input schema definition for the prune_memories tool, defining the criteria object structure with defaults for age, importance, access count, and status.

    name: "prune_memories",
    description: "Permanently delete memories based on criteria",
    inputSchema: {
      type: "object",
      properties: {
        criteria: {
          type: "object",
          properties: {
            max_age: {
              type: "integer",
              description: "Maximum age in days",
              default: 1095
            },
            min_importance: {
              type: "number",
              description: "Minimum importance threshold",
              default: 0.1
            },
            max_access_count: {
              type: "integer",
              description: "Maximum access count",
              default: 2
            },
            status: {
              type: "string",
              description: "Memory status to prune",
              default: "archived"
            }
          }
        }
      }
    }
  },

• mcp.js:641-643 (registration)

  Tool dispatch registration in MCP server's CallToolRequestSchema handler: maps tool calls to memoryManager.pruneMemories and formats response.

  case "prune_memories":
    const prunedMemories = await memoryManager.pruneMemories(args.criteria || {});
    return { content: [{ type: "text", text: JSON.stringify(prunedMemories, null, 2) }] };

• mcp.js:340-372 (registration)

  Tool registration in MCP server's ListToolsRequestSchema response, including name, description, and input schema.

    name: "prune_memories",
    description: "Permanently delete memories based on criteria",
    inputSchema: {
      type: "object",
      properties: {
        criteria: {
          type: "object",
          properties: {
            max_age: {
              type: "integer",
              description: "Maximum age in days",
              default: 1095
            },
            min_importance: {
              type: "number",
              description: "Minimum importance threshold",
              default: 0.1
            },
            max_access_count: {
              type: "integer",
              description: "Maximum access count",
              default: 2
            },
            status: {
              type: "string",
              description: "Memory status to prune",
              default: "archived"
            }
          }
        }
      }
    }
  },