Skip to main content
Glama

show_memory_path

Retrieve the absolute path of the active knowledge-graph file to enable structured reasoning and persistent memory access for AI assistants in complex problem-solving tasks.

Instructions

Return absolute path of the active knowledge-graph file.

Input Schema

NameRequiredDescriptionDefault
random_stringNoDummy parameter for no-parameter tools

Input Schema (JSON Schema)

{ "$schema": "http://json-schema.org/draft-07/schema#", "additionalProperties": false, "properties": { "random_string": { "description": "Dummy parameter for no-parameter tools", "type": "string" } }, "type": "object" }

Implementation Reference

  • The tool handler function that returns the JSON-stringified path to the memory file, using the MEMORY_PATH environment variable or a default path in the user's home directory.
    execute: async (_args, { log }) => { const memoryPath = process.env.MEMORY_PATH || path.join(os.homedir(), '.mcp-think-tank/memory.jsonl'); // Removed debug log return JSON.stringify(memoryPath); }
  • Zod schema defining the optional dummy input parameter for the tool.
    parameters: z.object({ random_string: z.string().describe("Dummy parameter for no-parameter tools").optional() }),
  • Registration of the show_memory_path tool in the registerUtilityTools function.
    server.addTool({ name: 'show_memory_path', description: 'Return absolute path of the active knowledge-graph file.', parameters: z.object({ random_string: z.string().describe("Dummy parameter for no-parameter tools").optional() }), execute: async (_args, { log }) => { const memoryPath = process.env.MEMORY_PATH || path.join(os.homedir(), '.mcp-think-tank/memory.jsonl'); // Removed debug log return JSON.stringify(memoryPath); } });
  • Invocation of registerUtilityTools during overall tool registration, which includes show_memory_path.
    registerUtilityTools(server);

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