Skip to main content
Glama

get_agent_summary

Retrieve a concise summary of an agent's configuration, including core memory snippets and attached tools/sources, to understand current settings before making modifications.

Instructions

Provides a concise summary of an agent's configuration, including core memory snippets and attached tool/source names. Use list_agents to find agent IDs. Follow up with modify_agent to change settings or attach_tool to add capabilities.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
agent_idYesThe ID of the agent to summarize.

Implementation Reference

  • The core handler function that implements the get_agent_summary tool logic. It fetches agent state, core memory blocks, attached tools, and sources from the Letta API endpoints concurrently and compiles them into a structured JSON summary returned as tool content.
    export async function handleGetAgentSummary(server, args) { if (!args?.agent_id) { server.createErrorResponse('Missing required argument: agent_id'); } const agentId = args.agent_id; const encodedAgentId = encodeURIComponent(agentId); const headers = server.getApiHeaders(); try { logger.info(`Fetching summary for agent ${agentId}...`); // Fetch data from multiple endpoints concurrently const [agentStateRes, coreMemoryRes, toolsRes, sourcesRes] = await Promise.allSettled([ server.api.get(`/agents/${encodedAgentId}`, { headers }), server.api.get(`/agents/${encodedAgentId}/core-memory/blocks`, { headers }), server.api.get(`/agents/${encodedAgentId}/tools`, { headers }), server.api.get(`/agents/${encodedAgentId}/sources`, { headers }), ]); // Process Agent State if (agentStateRes.status === 'rejected' || agentStateRes.value.status !== 200) { const errorInfo = agentStateRes.reason?.response?.data || agentStateRes.reason?.message || agentStateRes.value?.data || 'Unknown error fetching agent state'; logger.error(`Failed to fetch agent state for ${agentId}:`, errorInfo); // If agent doesn't exist, return a specific error if ( agentStateRes.reason?.response?.status === 404 || agentStateRes.value?.status === 404 ) { server.createErrorResponse(`Agent not found: ${agentId}`); } server.createErrorResponse(`Failed to fetch agent state: ${JSON.stringify(errorInfo)}`); } const agentState = agentStateRes.value.data; // Process Core Memory (optional, might fail if agent has none) let coreMemoryBlocks = []; if (coreMemoryRes.status === 'fulfilled' && coreMemoryRes.value.status === 200) { coreMemoryBlocks = coreMemoryRes.value.data.map((block) => ({ label: block.label, value_snippet: block.value.substring(0, 100) + (block.value.length > 100 ? '...' : ''), })); } else { logger.warn( `Could not fetch core memory for ${agentId}:`, coreMemoryRes.reason?.response?.data || coreMemoryRes.reason?.message || 'Non-200 status', ); } // Process Tools (optional) let attachedTools = []; if (toolsRes.status === 'fulfilled' && toolsRes.value.status === 200) { attachedTools = toolsRes.value.data.map((tool) => ({ id: tool.id, name: tool.name, type: tool.tool_type, })); } else { logger.warn( `Could not fetch tools for ${agentId}:`, toolsRes.reason?.response?.data || toolsRes.reason?.message || 'Non-200 status', ); } // Process Sources (optional) let attachedSources = []; if (sourcesRes.status === 'fulfilled' && sourcesRes.value.status === 200) { attachedSources = sourcesRes.value.data.map((source) => ({ id: source.id, name: source.name, })); } else { logger.warn( `Could not fetch sources for ${agentId}:`, sourcesRes.reason?.response?.data || sourcesRes.reason?.message || 'Non-200 status', ); } // Construct the summary const summary = { agent_id: agentState.id, name: agentState.name, description: agentState.description, system_prompt_snippet: agentState.system.substring(0, 200) + (agentState.system.length > 200 ? '...' : ''), llm_config: agentState.llm_config?.handle || `${agentState.llm_config?.model_endpoint_type}/${agentState.llm_config?.model}`, embedding_config: agentState.embedding_config?.handle || `${agentState.embedding_config?.embedding_endpoint_type}/${agentState.embedding_config?.embedding_model}`, core_memory_blocks: coreMemoryBlocks, attached_tools_count: attachedTools.length, attached_tools: attachedTools, attached_sources_count: attachedSources.length, attached_sources: attachedSources, }; return { content: [ { type: 'text', text: JSON.stringify(summary), }, ], }; } catch (error) { // Catch any unexpected errors during processing logger.error(`Unexpected error for agent ${agentId}:`, error); server.createErrorResponse(`Failed to get agent summary: ${error.message}`); } }
  • The tool definition object including name, description, and inputSchema requiring 'agent_id'.
    export const getAgentSummaryDefinition = { name: 'get_agent_summary', description: "Provides a concise summary of an agent's configuration, including core memory snippets and attached tool/source names. Use list_agents to find agent IDs. Follow up with modify_agent to change settings or attach_tool to add capabilities.", inputSchema: { type: 'object', properties: { agent_id: { type: 'string', description: 'The ID of the agent to summarize.', }, }, required: ['agent_id'], }, };
  • The switch case in the main CallToolRequestSchema handler that dispatches 'get_agent_summary' calls to handleGetAgentSummary.
    case 'get_agent_summary': return handleGetAgentSummary(server, request.params.arguments);
  • Import of the handler and definition from the implementation file.
    import { handleGetAgentSummary, getAgentSummaryDefinition } from './agents/get-agent-summary.js';
  • Inclusion of getAgentSummaryDefinition in the allTools array for registration with the MCP server.
    getAgentSummaryDefinition,

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/oculairmedia/Letta-MCP-server'

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