Skip to main content
Glama

open_nodes

Retrieve specific entities from a knowledge graph by providing their names. Enhances structured thinking and problem-solving within AI workflows.

Instructions

Open specific nodes in the knowledge graph by their names

Input Schema

NameRequiredDescriptionDefault
namesYesArray of entity names to retrieve

Input Schema (JSON Schema)

{ "$schema": "http://json-schema.org/draft-07/schema#", "additionalProperties": false, "properties": { "names": { "description": "Array of entity names to retrieve", "items": { "minLength": 1, "type": "string" }, "type": "array" } }, "required": [ "names" ], "type": "object" }

Implementation Reference

  • The execute function for the 'open_nodes' tool. It retrieves entities from the knowledge graph using graph.getEntities(args.names), computes found and notFound lists, and returns a JSON string with entities, found names, notFound names, and a summary message.
    execute: async (args) => { const results = graph.getEntities(args.names); const found = results.map(entity => entity.name); const notFound = args.names.filter(name => !found.includes(name)); // Return as string return JSON.stringify({ entities: results, found, notFound: notFound.length > 0 ? notFound : null, message: `Found ${found.length} entities. ${notFound.length} entities not found.` }); }
  • The server.addTool call that registers the 'open_nodes' tool within the registerMemoryTools function, including name, description, parameters schema, and inline execute handler.
    server.addTool({ name: 'open_nodes', description: 'Open specific nodes in the knowledge graph by their names', parameters: Schemas.OpenNodesSchema, execute: async (args) => { const results = graph.getEntities(args.names); const found = results.map(entity => entity.name); const notFound = args.names.filter(name => !found.includes(name)); // Return as string return JSON.stringify({ entities: results, found, notFound: notFound.length > 0 ? notFound : null, message: `Found ${found.length} entities. ${notFound.length} entities not found.` }); } });
  • Zod schema for 'open_nodes' tool input parameters: an array of strings representing entity names to retrieve from the knowledge graph.
    export const OpenNodesSchema = z.object({ names: z.array(z.string().min(1)).describe('Array of entity names to retrieve') });

Other Tools

Related 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/flight505/mcp-think-tank'

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