Skip to main content
Glama

get_memory_relationships

Retrieve connections between stored memories to analyze how data points relate within the AGI MCP Server's persistent memory system.

Instructions

Get relationships for a specific memory

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
memory_idYesUUID of the memory
directionNoDirection of relationships to retrieveboth
relationship_typeNoFilter by relationship type (optional)

Implementation Reference

  • Main handler implementation that executes the get_memory_relationships tool logic. Queries the memory_relationships table with optional filters for direction (incoming/outgoing/both) and relationship_type. Returns results sorted by strength and creation date.
    async getMemoryRelationships(memoryId, direction = 'both', relationshipType = null) {
      try {
        let query = this.db
          .select({
            id: schema.memoryRelationships.id,
            fromMemoryId: schema.memoryRelationships.fromMemoryId,
            toMemoryId: schema.memoryRelationships.toMemoryId,
            relationshipType: schema.memoryRelationships.relationshipType,
            strength: schema.memoryRelationships.strength,
            properties: schema.memoryRelationships.properties,
            createdAt: schema.memoryRelationships.createdAt,
            direction: sql`CASE 
              WHEN ${schema.memoryRelationships.fromMemoryId} = ${memoryId} THEN 'outgoing'
              ELSE 'incoming'
            END`.as('direction'),
            relatedMemoryId: sql`CASE 
              WHEN ${schema.memoryRelationships.fromMemoryId} = ${memoryId} THEN ${schema.memoryRelationships.toMemoryId}
              ELSE ${schema.memoryRelationships.fromMemoryId}
            END`.as('related_memory_id')
          })
          .from(schema.memoryRelationships);
    
        if (direction === 'outgoing') {
          query = query.where(eq(schema.memoryRelationships.fromMemoryId, memoryId));
        } else if (direction === 'incoming') {
          query = query.where(eq(schema.memoryRelationships.toMemoryId, memoryId));
        } else {
          query = query.where(
            or(
              eq(schema.memoryRelationships.fromMemoryId, memoryId),
              eq(schema.memoryRelationships.toMemoryId, memoryId)
            )
          );
        }
    
        if (relationshipType) {
          query = query.where(eq(schema.memoryRelationships.relationshipType, relationshipType));
        }
    
        const results = await query
          .orderBy(desc(schema.memoryRelationships.strength), desc(schema.memoryRelationships.createdAt));
        
        return results;
      } catch (error) {
        console.warn('Memory relationships query failed:', error.message);
        return [];
      }
    }
  • mcp.js:610-616 (registration)
    Tool handler invocation in the MCP server's request router that calls the memoryManager.getMemoryRelationships method with arguments from the MCP request.
    case "get_memory_relationships":
      const relationships = await memoryManager.getMemoryRelationships(
        args.memory_id,
        args.direction || 'both',
        args.relationship_type || null
      );
      return { content: [{ type: "text", text: JSON.stringify(relationships, null, 2) }] };
  • mcp.js:248-270 (registration)
    Tool registration in the MCP server defining the input schema for get_memory_relationships including memory_id (required), direction (enum: incoming/outgoing/both, default: both), and relationship_type (optional).
    {
      name: "get_memory_relationships",
      description: "Get relationships for a specific memory",
      inputSchema: {
        type: "object",
        properties: {
          memory_id: {
            type: "string",
            description: "UUID of the memory"
          },
          direction: {
            type: "string",
            enum: ["incoming", "outgoing", "both"],
            description: "Direction of relationships to retrieve",
            default: "both"
          },
          relationship_type: {
            type: "string",
            description: "Filter by relationship type (optional)"
          }
        },
        required: ["memory_id"]
      }
  • Database schema definition for memory_relationships table that stores relationships between memories, including id, fromMemoryId, toMemoryId, relationshipType, strength, properties, and createdAt fields with indexes and foreign key constraints.
    export const memoryRelationships = pgTable("memory_relationships", {
    	id: uuid().defaultRandom().primaryKey().notNull(),
    	fromMemoryId: uuid("from_memory_id").notNull(),
    	toMemoryId: uuid("to_memory_id").notNull(),
    	relationshipType: text("relationship_type").notNull(),
    	strength: doublePrecision().default(0.5),
    	properties: jsonb(),
    	createdAt: timestamp("created_at", { withTimezone: true, mode: 'string' }).default(sql`CURRENT_TIMESTAMP`),
    }, (table) => [
    	index("memory_relationships_from_memory_id_idx").using("btree", table.fromMemoryId.asc().nullsLast().op("uuid_ops")),
    	index("memory_relationships_to_memory_id_idx").using("btree", table.toMemoryId.asc().nullsLast().op("uuid_ops")),
    	index("memory_relationships_type_strength_idx").using("btree", table.relationshipType.asc().nullsLast().op("text_ops"), table.strength.desc().nullsFirst().op("float8_ops")),
    	foreignKey({
    			columns: [table.fromMemoryId],
    			foreignColumns: [memories.id],
    			name: "memory_relationships_from_memory_id_fkey"
    		}).onDelete("cascade"),
    	foreignKey({
    			columns: [table.toMemoryId],
    			foreignColumns: [memories.id],
    			name: "memory_relationships_to_memory_id_fkey"
    		}).onDelete("cascade"),
    ]);

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the action but doesn't describe what 'relationships' entail (e.g., structure, format), whether it's a read-only operation, potential rate limits, or error conditions. This leaves significant gaps for an agent to understand the tool's behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded, making it easy to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of annotations and output schema, the description is incomplete. It doesn't explain what 'relationships' are returned, their format, or any behavioral traits like pagination or error handling. For a retrieval tool with three parameters, this minimal description leaves too much undefined for effective agent use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, providing clear documentation for all three parameters. The description adds no additional semantic context beyond implying that 'memory_id' identifies the target memory, which is already covered by the schema. This meets the baseline for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Get') and resource ('relationships for a specific memory'), making the purpose understandable. However, it doesn't distinguish this tool from sibling tools like 'find_related_memories' or 'create_memory_relationship', which appear to handle related functionality but with different operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. With sibling tools like 'find_related_memories' and 'search_memories_advanced' available, there's no indication of context, prerequisites, or exclusions for selecting this specific retrieval tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.