Engram Mcp Server
@lumetra-io
Engram Mcp Server について
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.
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"engram": {
"url": "https://engram.lumetra.io",
"headers": {
"X-API-Key": "<your-api-key>"
}
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is Engram Mcp Server?
Engram Mcp Server is a hosted MCP (Model Context Protocol) server that gives AI agents reliable, persistent memory. It allows agents to remember past conversations, facts, and decisions, making them feel more like real teammates. The service is provided by Lumetra and is free during public beta with no credit card required.
How to use Engram Mcp Server?
To use Engram Mcp Server, sign up at lumetra.io to get an API key, then configure your MCP client (e.g., Claude Code, Windsurf, Cursor) with the server URL https://engram.lumetra.io and your API key in the appropriate config file or command. After restarting the client, the agent will have access to memory tools like store_memory, search_memories, and delete_by_event.
Key features of Engram Mcp Server
- Provides reliable, persistent memory for AI agents
- Works with Claude Code, Windsurf, Cursor, and other MCP clients
- Built-in tools for storing, searching, and deleting memories
- Includes
explain_retrievalto show why results were chosen - No local installation required – fully hosted service
Use cases of Engram Mcp Server
- Support workflows that carry forward prior ticket context and follow‑ups
- Code reviews that remember ADRs, brittle areas, and post‑mortems
- Shared metric definitions with approved joins and SQL snippets
- Consistent on‑brand content by centralizing voice and approved claims
FAQ from Engram Mcp Server
Is Engram Mcp Server free to use?
Yes, it is free during the public beta and does not require a credit card.
Do I need to install anything locally?
No. Engram is a hosted service running at https://engram.lumetra.io; there is no local installation required.
Which MCP clients are supported?
The README provides configuration examples for Claude Code, Windsurf, and Cursor. It also notes that other MCP clients are supported via the same configuration pattern.
What memory tools are available?
The tools include: store_memory, store_memories, search_memories, memory_index, delete_by_event, and explain_retrieval.
「メモリとナレッジ」の他のコンテンツ
Solomd
zhitongblogA markdown editor — and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / Cursor drive your vault directly. 14 AI providers BYOK.
MCP server for Obsidian
MarkusPfundsteinMCP server that interacts with Obsidian via the Obsidian rest API community plugin
Anytype MCP Server
anyprotoAn MCP server enabling AI assistants to interact with Anytype - your encrypted, local and collaborative wiki - to organize objects, lists, and more through natural language.
mcp-local-rag
nkapila6"primitive" RAG-like web search model context protocol (MCP) server that runs locally. ✨ no APIs ✨
🧠 Ultimate MCP Server
DicklesworthstoneComprehensive MCP server exposing dozens of capabilities to AI agents: multi-provider LLM delegation, browser automation, document processing, vector ops, and cognitive memory systems
コメント