DatabasesOfficial

Engram MCP Server

Engram is a hosted MCP server that provides reliable memory for AI agents:

1 starsUpdated May 14, 2026

Ads

Overview

Give your AI agents a memory they can trust. Engram lets your AI remember past conversations, facts, and decisions, so it feels more like a real teammate. This repository contains configuration templates for connecting MCP clients to Engram, a hosted memory service for AI agents. Engram is a hosted MCP server that provides reliable, explainable memory for AI agents: - Reliable memory: Agents remember conversations, facts, and decisions, with automatic knowledge graph extraction - Explainable retrieval: Every answer cites the memories and graph edges that justified it - Three-engine retrieval: BM25 + vector search + knowledge graph, fused and reranked - Bring your own model: All LLM calls route through your provider — no inference markup - Built-in controls: Organize memories into buckets, manage retention, and query with natural language

Installation

claude mcp add-json engram '{"type":"sse","url":"https://mcp.lumetra.io/mcp/sse","headers":{"Authorization":"Bearer <your-api-key>"}}'

Configuration

{
  "mcpServers": {
    "engram": {
      "url": "https://mcp.lumetra.io/mcp/sse",
      "headers": {
        "Authorization": "Bearer <your-api-key>"
      }
    }

Capabilities

Store facts for later recall
Save a piece of information with `store_memory`, optionally organizing it into a named bucket.
Search memories with natural language
Ask a question via `query_memory` and get AI-synthesized answers with citations to the source memories.
Browse stored memories by bucket
Use `list_memories` to retrieve recent entries from a specific bucket, newest first.
Manage memory buckets
Call `list_buckets` to see all available buckets, or `delete_memory` and `clear_memories` to remove stored content.