Skip to main content
Glama

memory_query

Access and filter stored observations using keywords, dates, tags, or agents. Retrieve relevant data efficiently for enhanced decision-making and problem-solving in AI-driven workflows.

Instructions

Query the memory store with advanced filters

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
afterNoISO date to filter observations after
agentNoAgent that created the observations
beforeNoISO date to filter observations before
keywordNoText to search for in observations
limitNoMaximum number of results to return
tagNoTag to filter observations by

Implementation Reference

  • Registers the MCP tool 'memory_query' with the FastMCP server, including description, Zod parameter schema, and execute handler.
    server.addTool({ name: 'memory_query', description: 'Query the memory store with advanced filters', parameters: z.object({ keyword: z.string().optional().describe("Text to search for in observations"), before: z.string().optional().describe("ISO date to filter observations before"), after: z.string().optional().describe("ISO date to filter observations after"), tag: z.string().optional().describe("Tag to filter observations by"), agent: z.string().optional().describe("Agent that created the observations"), limit: z.number().optional().describe("Maximum number of results to return") }), execute: async (args) => { const results = await memoryStore.query({ keyword: args.keyword, time: { before: args.before, after: args.after }, tag: args.tag, agent: args.agent, limit: args.limit }); return JSON.stringify({ observations: results, count: results.length, message: `Found ${results.length} matching observations.` }); } });
  • Defines the MemoryQuery TypeScript interface used for querying observations, matching the tool's parameter structure.
    export interface MemoryQuery { keyword?: string; time?: { before?: string; after?: string; }; tag?: string; agent?: string; limit?: number; }
  • The execute handler for the memory_query tool, which maps arguments to MemoryQuery and calls memoryStore.query, returning JSON results.
    execute: async (args) => { const results = await memoryStore.query({ keyword: args.keyword, time: { before: args.before, after: args.after }, tag: args.tag, agent: args.agent, limit: args.limit }); return JSON.stringify({ observations: results, count: results.length, message: `Found ${results.length} matching observations.` }); }
  • Core implementation of the query method in JsonlMemoryStore, which iterates over all entities and observations, applies filters for keyword, time, tag, and limit, returning matching results.
    async query(query: MemoryQuery): Promise<{ entityName: string; observation: Observation; }[]> { await this.getLoadingPromise(); const results: { entityName: string; observation: Observation }[] = []; const keyword = query.keyword?.toLowerCase(); for (const [entityName, entity] of this.enhancedEntities.entries()) { for (const observation of entity.observations) { let matches = true; // Filter by keyword if (keyword && !observation.text.toLowerCase().includes(keyword)) { matches = false; } // Filter by time range if (query.time) { const obsTime = new Date(observation.timestamp).getTime(); if (query.time.after && obsTime < new Date(query.time.after).getTime()) { matches = false; } if (query.time.before && obsTime > new Date(query.time.before).getTime()) { matches = false; } } // Filter by tag (would require additional metadata tracking) // This is a placeholder for future implementation if (query.tag) { // Not implemented yet // For now, we'll just check if the tag appears in the text if (!observation.text.toLowerCase().includes(query.tag.toLowerCase())) { matches = false; } } // Filter by agent (would require additional metadata tracking) // This is a placeholder for future implementation if (query.agent) { // Not implemented yet matches = false; } if (matches) { results.push({ entityName, observation }); } } } // Apply limit if specified if (query.limit && query.limit > 0) { return results.slice(0, query.limit); } return results; }

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