Skip to main content
Glama

get_memory_by_agent

Retrieve all stored memory entries for a specific agent to access relevant context and information for AI interactions.

Instructions

Get all memory entries for a specific agent

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
agentIdYesID of the agent to get memory for

Implementation Reference

  • src/index.ts:174-187 (registration)
    Tool registration in the ListTools response, including name, description, and input schema.
    {
      name: 'get_memory_by_agent',
      description: 'Get all memory entries for a specific agent',
      inputSchema: {
        type: 'object',
        properties: {
          agentId: {
            type: 'string',
            description: 'ID of the agent to get memory for',
          },
        },
        required: ['agentId'],
      },
    },
  • MCP server tool handler that processes the get_memory_by_agent tool call by invoking the RAG service and formatting the response.
    private async handleGetMemoryByAgent(args: { agentId: string }) {
      const results = await this.ragService.getMemoryByAgent(args.agentId);
      return {
        content: [
          {
            type: 'text',
            text: JSON.stringify(results, null, 2),
          },
        ],
      };
    }
  • RAG service method that delegates the getMemoryByAgent call to the vector database service.
    async getMemoryByAgent(agentId: string): Promise<SearchResult[]> {
      try {
        logger.info(`Getting memory for agent: ${agentId}`);
        return await this.vectorDatabase.getMemoryByAgent(agentId);
      } catch (error) {
        logger.error(`Error getting memory by agent: ${error}`);
        throw new Error(`Failed to get memory by agent: ${error}`);
      }
    }
  • Core implementation that queries the Pinecone memory index using a metadata filter for the specified agentId to retrieve all associated memory entries.
    async getMemoryByAgent(agentId: string): Promise<SearchResult[]> {
      try {
        const results = await this.memoryIndex.query({
          vector: new Array(CONFIG.EMBEDDING_DIMENSION).fill(0), // Dummy vector for metadata query
          topK: 10000, // Large number to get all memory entries
          includeMetadata: true,
          filter: { agentId }
        });
    
        if (results.matches) {
          return results.matches.map((match: any) => ({
            id: match.id,
            content: match.metadata?.content || '',
            metadata: match.metadata || {},
            score: match.score || 1.0
          }));
        }
    
        return [];
      } catch (error) {
        logger.error(`Error getting memory by agent: ${error}`);
        throw new Error(`Failed to get memory by agent: ${error}`);
      }
    }
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. It states the action 'Get all memory entries', implying a read operation, but does not disclose behavioral traits like whether it requires authentication, has rate limits, returns paginated results, or what format the entries are in. This leaves significant gaps for a tool with no annotation coverage.

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 is appropriately sized and front-loaded, making it easy to understand at a glance with zero waste.

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 does not explain what 'memory entries' entail, their structure, or how results are returned (e.g., list format, error handling). For a tool with no structured data support, this leaves the agent with insufficient information to use it effectively.

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 description adds minimal meaning beyond the input schema, which has 100% coverage and clearly describes the 'agentId' parameter. The description implies the parameter is for specifying the agent, but does not provide additional context such as valid ID formats or examples. With high schema coverage, the baseline of 3 is appropriate as the schema does the heavy lifting.

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 the resource 'memory entries for a specific agent', making the purpose unambiguous. However, it does not differentiate from sibling tools like 'search_memory' or 'get_stats', which might also retrieve memory-related data, so it lacks sibling distinction.

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 such as 'search_memory' or 'get_stats'. It implies usage for retrieving all entries for a specific agent, but offers no exclusions, prerequisites, or explicit context for selection among siblings.

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/santis84/mcp-rag'

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