Skip to main content
Glama

memory_knowledge_graph

Query relationships and paths within a knowledge graph to analyze connections and retrieve structured information from documentation.

Instructions

Query the knowledge graph for relationships and paths

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYes

Implementation Reference

  • KnowledgeGraph.query method implements the core logic for querying the graph for nodes, edges, and paths based on the exact input schema parameters (nodeTypes, edgeTypes, startNode, maxDepth). This is the handler logic executed for the tool.
    query(query: GraphQuery): {
      nodes: GraphNode[];
      edges: GraphEdge[];
      paths?: GraphPath[];
    } {
      let nodes = Array.from(this.nodes.values());
      let edges = Array.from(this.edges.values());
    
      // Filter by node types
      if (query.nodeTypes) {
        nodes = nodes.filter((node) => query.nodeTypes!.includes(node.type));
      }
    
      // Filter by edge types
      if (query.edgeTypes) {
        edges = edges.filter((edge) => query.edgeTypes!.includes(edge.type));
      }
    
      // Filter by properties
      if (query.properties) {
        nodes = nodes.filter((node) =>
          Object.entries(query.properties!).every(
            ([key, value]) => node.properties[key] === value,
          ),
        );
      }
    
      // Filter by minimum weight
      if (query.minWeight) {
        nodes = nodes.filter((node) => node.weight >= query.minWeight!);
        edges = edges.filter((edge) => edge.weight >= query.minWeight!);
      }
    
      const result = { nodes, edges };
    
      // Find paths from start node if specified
      if (query.startNode && query.maxDepth) {
        const paths: GraphPath[] = [];
        const visited = new Set<string>();
    
        const emptyPath: GraphPath = {
          nodes: [],
          edges: [],
          totalWeight: 0,
          confidence: 1.0,
        };
        this.explorePaths(
          query.startNode,
          emptyPath,
          paths,
          visited,
          query.maxDepth,
        );
        (result as any).paths = paths;
      }
    
      return result;
    }
  • Input schema definition for the memory_knowledge_graph tool, defining the expected query parameters.
    {
      name: "memory_knowledge_graph",
      description: "Query the knowledge graph for relationships and paths",
      inputSchema: {
        type: "object",
        properties: {
          query: {
            type: "object",
            properties: {
              nodeTypes: {
                type: "array",
                items: { type: "string" },
                description: "Filter by node types",
              },
              edgeTypes: {
                type: "array",
                items: { type: "string" },
                description: "Filter by edge types",
              },
              startNode: {
                type: "string",
                description: "Starting node for path queries",
              },
              maxDepth: {
                type: "number",
                description: "Maximum path depth",
                default: 3,
              },
            },
          },
        },
        required: ["query"],
      },
    },
  • The memoryTools array exports all memory-related MCP tools including memory_knowledge_graph, which gets incorporated into the main TOOLS registry.
    export const memoryTools = [
      {
        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"],
        },
      },
      {
        name: "memory_intelligent_analysis",
        description:
          "Get intelligent analysis with patterns, predictions, and recommendations",
        inputSchema: {
          type: "object",
          properties: {
            projectPath: {
              type: "string",
              description: "Path to the project for analysis",
            },
            baseAnalysis: {
              type: "object",
              description: "Base analysis data to enhance",
            },
          },
          required: ["projectPath", "baseAnalysis"],
        },
      },
      {
        name: "memory_enhanced_recommendation",
        description:
          "Get enhanced recommendations using learning and knowledge graph",
        inputSchema: {
          type: "object",
          properties: {
            projectPath: {
              type: "string",
              description: "Path to the project",
            },
            baseRecommendation: {
              type: "object",
              description: "Base recommendation to enhance",
            },
            projectFeatures: {
              type: "object",
              properties: {
                language: { type: "string" },
                framework: { type: "string" },
                size: { type: "string", enum: ["small", "medium", "large"] },
                complexity: {
                  type: "string",
                  enum: ["simple", "moderate", "complex"],
                },
                hasTests: { type: "boolean" },
                hasCI: { type: "boolean" },
                hasDocs: { type: "boolean" },
                isOpenSource: { type: "boolean" },
              },
              required: ["language"],
            },
          },
          required: ["projectPath", "baseRecommendation", "projectFeatures"],
        },
      },
      {
        name: "memory_learning_stats",
        description: "Get comprehensive learning and knowledge graph statistics",
        inputSchema: {
          type: "object",
          properties: {
            includeDetails: {
              type: "boolean",
              description: "Include detailed statistics",
              default: true,
            },
          },
        },
      },
      {
        name: "memory_knowledge_graph",
        description: "Query the knowledge graph for relationships and paths",
        inputSchema: {
          type: "object",
          properties: {
            query: {
              type: "object",
              properties: {
                nodeTypes: {
                  type: "array",
                  items: { type: "string" },
                  description: "Filter by node types",
                },
                edgeTypes: {
                  type: "array",
                  items: { type: "string" },
                  description: "Filter by edge types",
                },
                startNode: {
                  type: "string",
                  description: "Starting node for path queries",
                },
                maxDepth: {
                  type: "number",
                  description: "Maximum path depth",
                  default: 3,
                },
              },
            },
          },
          required: ["query"],
        },
      },
      {
        name: "memory_contextual_search",
        description: "Perform contextual memory retrieval with intelligent ranking",
        inputSchema: {
          type: "object",
          properties: {
            query: {
              type: "string",
              description: "Search query",
            },
            context: {
              type: "object",
              properties: {
                currentProject: {
                  type: "object",
                  properties: {
                    path: { type: "string" },
                    language: { type: "string" },
                    framework: { type: "string" },
                    size: { type: "string", enum: ["small", "medium", "large"] },
                  },
                },
                userIntent: {
                  type: "object",
                  properties: {
                    action: {
                      type: "string",
                      enum: [
                        "analyze",
                        "recommend",
                        "deploy",
                        "troubleshoot",
                        "learn",
                      ],
                    },
                    urgency: { type: "string", enum: ["low", "medium", "high"] },
                    experience: {
                      type: "string",
                      enum: ["novice", "intermediate", "expert"],
                    },
                  },
                },
                temporalContext: {
                  type: "object",
                  properties: {
                    recency: {
                      type: "string",
                      enum: ["recent", "all", "historical"],
                    },
                    timeRange: {
                      type: "object",
                      properties: {
                        start: { type: "string" },
                        end: { type: "string" },
                      },
                    },
                  },
                },
              },
            },
            options: {
              type: "object",
              properties: {
                maxResults: { type: "number", default: 10 },
                minRelevance: { type: "number", default: 0.3 },
                includeReasoning: { type: "boolean", default: true },
              },
            },
          },
          required: ["query", "context"],
        },
      },
      {
        name: "memory_agent_network",
        description: "Manage multi-agent memory sharing and collaboration",
        inputSchema: {
          type: "object",
          properties: {
            action: {
              type: "string",
              enum: [
                "register_agent",
                "share_memory",
                "sync_request",
                "get_insights",
                "network_status",
              ],
              description: "Action to perform",
            },
            agentInfo: {
              type: "object",
              properties: {
                name: { type: "string" },
                capabilities: { type: "array", items: { type: "string" } },
                specializations: { type: "array", items: { type: "string" } },
                trustLevel: {
                  type: "string",
                  enum: ["low", "medium", "high", "trusted"],
                },
              },
            },
            memoryId: {
              type: "string",
              description: "Memory ID for sharing operations",
            },
            targetAgent: {
              type: "string",
              description: "Target agent for sync operations",
            },
            options: {
              type: "object",
              properties: {
                anonymize: { type: "boolean", default: false },
                requireValidation: { type: "boolean", default: false },
              },
            },
          },
          required: ["action"],
        },
      },
      {
        name: "memory_insights",
        description: "Get insights and patterns from memory",
        inputSchema: {
          type: "object",
          properties: {
            projectId: {
              type: "string",
              description: "Project ID to analyze",
            },
            timeRange: {
              type: "object",
              properties: {
                start: { type: "string", format: "date-time" },
                end: { type: "string", format: "date-time" },
              },
              description: "Time range for analysis",
            },
          },
        },
      },
      {
        name: "memory_similar",
        description: "Find similar projects from memory",
        inputSchema: {
          type: "object",
          properties: {
            analysisId: {
              type: "string",
              description: "Analysis ID to find similar projects for",
            },
            limit: {
              type: "number",
              description: "Maximum number of similar projects",
              default: 5,
            },
          },
          required: ["analysisId"],
        },
      },
      {
        name: "memory_export",
        description: "Export memories to JSON or CSV",
        inputSchema: {
          type: "object",
          properties: {
            format: {
              type: "string",
              enum: ["json", "csv"],
              description: "Export format",
              default: "json",
            },
            filter: {
              type: "object",
              properties: {
                type: { type: "string" },
                projectId: { type: "string" },
                startDate: { type: "string", format: "date-time" },
                endDate: { type: "string", format: "date-time" },
              },
              description: "Filter memories to export",
            },
          },
        },
      },
      {
        name: "memory_cleanup",
        description: "Clean up old memories",
        inputSchema: {
          type: "object",
          properties: {
            daysToKeep: {
              type: "number",
              description: "Number of days of memories to keep",
              default: 30,
            },
            dryRun: {
              type: "boolean",
              description:
                "Preview what would be deleted without actually deleting",
              default: false,
            },
          },
        },
      },
      {
        name: "memory_pruning",
        description: "Intelligent memory pruning and optimization",
        inputSchema: {
          type: "object",
          properties: {
            policy: {
              type: "object",
              properties: {
                maxAge: {
                  type: "number",
                  description: "Maximum age in days",
                  default: 180,
                },
                maxSize: {
                  type: "number",
                  description: "Maximum storage size in MB",
                  default: 500,
                },
                maxEntries: {
                  type: "number",
                  description: "Maximum number of entries",
                  default: 50000,
                },
                preservePatterns: {
                  type: "array",
                  items: { type: "string" },
                  description: "Pattern types to preserve",
                },
                compressionThreshold: {
                  type: "number",
                  description: "Compress entries older than X days",
                  default: 30,
                },
                redundancyThreshold: {
                  type: "number",
                  description: "Remove similar entries with similarity > X",
                  default: 0.85,
                },
              },
            },
            dryRun: {
              type: "boolean",
              description: "Preview pruning without executing",
              default: false,
            },
          },
        },
      },
      {
        name: "memory_temporal_analysis",
        description: "Analyze temporal patterns and trends in memory data",
        inputSchema: {
          type: "object",
          properties: {
            query: {
              type: "object",
              properties: {
                timeRange: {
                  type: "object",
                  properties: {
                    start: { type: "string", format: "date-time" },
                    end: { type: "string", format: "date-time" },
                  },
                },
                granularity: {
                  type: "string",
                  enum: ["hour", "day", "week", "month", "year"],
                  default: "day",
                },
                aggregation: {
                  type: "string",
                  enum: ["count", "success_rate", "activity_level", "diversity"],
                  default: "count",
                },
                filters: {
                  type: "object",
                  properties: {
                    types: { type: "array", items: { type: "string" } },
                    projects: { type: "array", items: { type: "string" } },
                    outcomes: { type: "array", items: { type: "string" } },
                    tags: { type: "array", items: { type: "string" } },
                  },
                },
              },
            },
            analysisType: {
              type: "string",
              enum: ["patterns", "metrics", "predictions", "insights"],
              default: "patterns",
            },
          },
        },
      },
      {
        name: "memory_visualization",
        description: "Generate visual representations of memory data",
        inputSchema: {
          type: "object",
          properties: {
            visualizationType: {
              type: "string",
              enum: [
                "dashboard",
                "timeline",
                "network",
                "heatmap",
                "distribution",
                "trends",
                "custom",
              ],
              default: "dashboard",
            },
            options: {
              type: "object",
              properties: {
                timeRange: {
                  type: "object",
                  properties: {
                    start: { type: "string", format: "date-time" },
                    end: { type: "string", format: "date-time" },
                  },
                },
                includeCharts: { type: "array", items: { type: "string" } },
                config: {
                  type: "object",
                  properties: {
                    width: { type: "number", default: 800 },
                    height: { type: "number", default: 600 },
                    theme: {
                      type: "string",
                      enum: ["light", "dark", "auto"],
                      default: "light",
                    },
                    exportFormat: {
                      type: "string",
                      enum: ["svg", "png", "json", "html"],
                      default: "svg",
                    },
                    interactive: { type: "boolean", default: true },
                  },
                },
              },
            },
            customVisualization: {
              type: "object",
              properties: {
                type: {
                  type: "string",
                  enum: [
                    "line",
                    "bar",
                    "scatter",
                    "heatmap",
                    "network",
                    "sankey",
                    "treemap",
                    "timeline",
                  ],
                },
                query: {
                  type: "object",
                  properties: {
                    filters: { type: "object" },
                    groupBy: { type: "string" },
                    aggregation: { type: "string" },
                  },
                },
              },
            },
          },
        },
      },
      {
        name: "memory_export_advanced",
        description: "Advanced memory export with multiple formats and options",
        inputSchema: {
          type: "object",
          properties: {
            outputPath: { type: "string", description: "Output file path" },
            options: {
              type: "object",
              properties: {
                format: {
                  type: "string",
                  enum: [
                    "json",
                    "jsonl",
                    "csv",
                    "xml",
                    "yaml",
                    "sqlite",
                    "archive",
                  ],
                  default: "json",
                },
                compression: {
                  type: "string",
                  enum: ["gzip", "zip", "none"],
                  default: "none",
                },
                includeMetadata: { type: "boolean", default: true },
                includeLearning: { type: "boolean", default: true },
                includeKnowledgeGraph: { type: "boolean", default: true },
                filters: {
                  type: "object",
                  properties: {
                    types: { type: "array", items: { type: "string" } },
                    dateRange: {
                      type: "object",
                      properties: {
                        start: { type: "string", format: "date-time" },
                        end: { type: "string", format: "date-time" },
                      },
                    },
                    projects: { type: "array", items: { type: "string" } },
                    tags: { type: "array", items: { type: "string" } },
                    outcomes: { type: "array", items: { type: "string" } },
                  },
                },
                anonymize: {
                  type: "object",
                  properties: {
                    enabled: { type: "boolean", default: false },
                    fields: { type: "array", items: { type: "string" } },
                    method: {
                      type: "string",
                      enum: ["hash", "remove", "pseudonymize"],
                      default: "hash",
                    },
                  },
                },
                encryption: {
                  type: "object",
                  properties: {
                    enabled: { type: "boolean", default: false },
                    algorithm: {
                      type: "string",
                      enum: ["aes-256-gcm", "aes-192-gcm", "aes-128-gcm"],
                      default: "aes-256-gcm",
                    },
                    password: { type: "string" },
                  },
                },
              },
            },
          },
          required: ["outputPath"],
        },
      },
      {
        name: "memory_import_advanced",
        description:
          "Advanced memory import with validation and conflict resolution",
        inputSchema: {
          type: "object",
          properties: {
            inputPath: { type: "string", description: "Input file path" },
            options: {
              type: "object",
              properties: {
                format: {
                  type: "string",
                  enum: [
                    "json",
                    "jsonl",
                    "csv",
                    "xml",
                    "yaml",
                    "sqlite",
                    "archive",
                  ],
                  default: "json",
                },
                mode: {
                  type: "string",
                  enum: ["merge", "replace", "append", "update"],
                  default: "merge",
                },
                validation: {
                  type: "string",
                  enum: ["strict", "loose", "none"],
                  default: "strict",
                },
                conflictResolution: {
                  type: "string",
                  enum: ["skip", "overwrite", "merge", "rename"],
                  default: "skip",
                },
                backup: { type: "boolean", default: true },
                dryRun: { type: "boolean", default: false },
                mapping: {
                  type: "object",
                  description: "Field mapping for different schemas",
                },
                transformation: {
                  type: "object",
                  properties: {
                    enabled: { type: "boolean", default: false },
                    rules: {
                      type: "array",
                      items: {
                        type: "object",
                        properties: {
                          field: { type: "string" },
                          operation: {
                            type: "string",
                            enum: ["convert", "transform", "validate"],
                          },
                          params: { type: "object" },
                        },
                      },
                    },
                  },
                },
              },
            },
          },
          required: ["inputPath"],
        },
      },
      {
        name: "memory_migration",
        description:
          "Create and execute migration plans between different memory systems",
        inputSchema: {
          type: "object",
          properties: {
            action: {
              type: "string",
              enum: ["create_plan", "execute_migration", "validate_compatibility"],
              default: "create_plan",
            },
            sourcePath: { type: "string", description: "Source data path" },
            migrationPlan: {
              type: "object",
              properties: {
                sourceSystem: { type: "string" },
                targetSystem: { type: "string", default: "DocuMCP" },
                mapping: { type: "object" },
                transformations: { type: "array" },
                validation: { type: "array" },
                postProcessing: { type: "array", items: { type: "string" } },
              },
            },
            sourceSchema: { type: "object", description: "Source system schema" },
            targetSchema: { type: "object", description: "Target system schema" },
            options: {
              type: "object",
              properties: {
                autoMap: { type: "boolean", default: true },
                preserveStructure: { type: "boolean", default: true },
                customMappings: { type: "object" },
              },
            },
          },
        },
      },
      {
        name: "memory_optimization_metrics",
        description: "Get comprehensive optimization metrics and recommendations",
        inputSchema: {
          type: "object",
          properties: {
            includeRecommendations: { type: "boolean", default: true },
            timeRange: {
              type: "object",
              properties: {
                start: { type: "string", format: "date-time" },
                end: { type: "string", format: "date-time" },
              },
            },
          },
        },
      },
    ];
  • Utility to retrieve the singleton KnowledgeGraph instance used by tool handlers.
    export async function getKnowledgeGraph(): Promise<KnowledgeGraph> {
      if (!globalKnowledgeGraph) {
        return await initializeKnowledgeGraph();
      }
      return globalKnowledgeGraph;
    }
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 mentions querying but doesn't specify if this is a read-only operation, what permissions are needed, how results are returned (e.g., pagination, format), or any rate limits. For a query tool with zero annotation coverage, this is a significant gap in transparency.

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 extremely concise with a single sentence: 'Query the knowledge graph for relationships and paths'. It's front-loaded and wastes no words, making it easy to parse quickly. Every part of the sentence contributes to the core purpose.

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 complexity implied by querying a knowledge graph, the lack of annotations, 0% schema coverage, no output schema, and a nested parameter object, the description is incomplete. It doesn't address how to formulate queries, what results look like, or behavioral aspects, making it inadequate for effective tool use.

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

Parameters2/5

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

The input schema has 1 parameter ('query') with 0% description coverage, and the description adds no semantic information about it. It doesn't explain what the query object should contain, how to structure it, or what types of queries are supported. With low schema coverage, the description fails to compensate, leaving parameters undocumented.

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

Purpose3/5

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

The description states the tool's purpose as 'Query the knowledge graph for relationships and paths', which includes a verb ('query') and resource ('knowledge graph'). However, it's vague about what constitutes 'relationships and paths' and doesn't differentiate from sibling tools like 'memory_contextual_search' or 'memory_recall', which might also query memory systems. The purpose is understandable but lacks specificity.

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 many sibling tools (e.g., 'memory_contextual_search', 'memory_recall', 'memory_insights'), there's no indication of context, prerequisites, or exclusions. This leaves the agent without clear direction for tool selection.

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

Install Server

Other Tools

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