MCP.so
登录

Epitome Personal Portable AI Memory Vault

@gunning4it

代码仓库

关于 Epitome Personal Portable AI Memory Vault

Epitome gives every AI agent shared, persistent memory of you. It stores memories, facts, and preferences in a personal knowledge graph, so any AI tool you use already knows your context. Connect via MCP using Streamable HTTP — no local install needed.

#memory#knowledge-graph#ai-agent#mcp#personalization

基本信息

分类

记忆与知识

传输方式

stdio

发布者

gunning4it

提交者

Josh G

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "epitome": {
      "type": "streamable-http",
      "url": "https://epitome.fyi/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_API_KEY>"
      }
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Epitome?

Epitome is a personal AI memory layer that gives every AI agent you use shared, persistent memory of your preferences, habits, history, and relationships — stored in a knowledge graph accessible by any MCP-compatible client. No local install is required; it connects via Streamable HTTP.

How to use Epitome?

Configure an MCP client with a streamable-http transport pointing to https://epitome.fyi/mcp and an API key in the authorization header. Obtain your API key from https://epitome.fyi/dashboard/settings. After setup, invoke any of the nine provided tools (e.g., get_user_context at conversation start, save_memory to store notes).

Key features of Epitome

  • Knowledge graph — entities and relationships extracted automatically from every interaction
  • Semantic search — vector-powered memory recall across all saved content
  • Structured data — track anything with auto-created tables and columns
  • Contradiction detection — automatic quality checks keep memory accurate
  • Per-user isolation — each user gets their own PostgreSQL schema

Use cases of Epitome

  • Provide every AI agent with your profile and recent context at conversation start
  • Log structured data like meals, workouts, expenses, or medications without manual schema setup
  • Save and search personal notes, reflections, or experiences via vector memory
  • Traverse relationship patterns (e.g., multi-hop connections) across your knowledge graph
  • Review and resolve memory contradictions to maintain data accuracy

FAQ from Epitome

How do I get an API key for Epitome?

Sign in at https://epitome.fyi/dashboard/settings to generate your API key.

Does Epitome require local installation?

No. Epitome runs as a cloud service and connects via Streamable HTTP — no files to install or servers to run locally.

Where is my data stored?

Each user gets their own PostgreSQL schema, ensuring per-user isolation. Data is stored on Epitome's servers.

What transport does Epitome use?

Epitome uses the MCP Streamable HTTP transport. Configure your client with type "streamable-http" and the URL https://epitome.fyi/mcp.

How many tools does Epitome provide?

Epitome provides nine MCP tools: get_user_context, update_profile, save_memory, search_memory, add_record, list_tables, query_table, query_graph, and review_memories.

评论

记忆与知识 分类下的更多 MCP 服务器

RAG Documentation MCP Server

hannesrudolph

An MCP server implementation that provides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.

267

Context Portal MCP (ConPort)

GreatScottyMac

Context Portal (ConPort): A memory bank MCP server building a project-specific knowledge graph to supercharge AI assistants. Enables powerful Retrieval Augmented Generation (RAG) for context-aware development in your IDE.

763

Jupyter Notebook MCP Server (for Cursor)

jbeno

Model Context Protocol (MCP) server designed to allow AI agents within Cursor to interact with Jupyter Notebook (.ipynb) files

157

Docs MCP Server

arabold

Grounded Docs MCP Server: Open-Source Alternative to Context7, Nia, and Ref.Tools

1.5K

Anytype MCP Server

anyproto

An MCP server enabling AI assistants to interact with Anytype - your encrypted, local and collaborative wiki - to organize objects, lists, and more through natural language.

467