Advertise
MCP.so
Sign In
E

Ember Memory MCP Server

@attilakiss9000

Repository

Basic information

Category

Memory & Knowledge

Transports

stdio

Author

attilakiss9000

Submitted by

Attila Kiss

About Ember Memory MCP Server

Preserves the emotional texture of human-AI conversations across sessions through real-time experiential annotation — temperature, authenticity, shifts, subtext, and unspoken context.

#memory#ai-memory#experiential-memory#conversation#emotional-memory#claude#mcp-server#relationship

Ember Memory MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "ember": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "ember-memory"
      ],
      "env": {}
    }
  }
}

Ember Memory MCP Server tools

8

Start a new conversation and receive its unique ID. Call this at the beginning of every session so subsequent captures and annotations can be linked to this conversation.

End an active conversation. Optionally provide a brief summary of what the conversation covered.

Capture a message from the conversation without annotation. Use this for messages that don't warrant emotional annotation but should still be preserved in the conversation record.

Capture a message with emotional annotation. This is the primary tool for preserving experiential memory. Weight (1-5) marks emotional significance, temperature is a short phrase describing the emotional tone. In standard mode, additional fields capture authenticity, emotional shifts, subtext, and unspoken context.

Read conversation history with optional filters. Returns messages and their annotations in a compact text format. This is a read-only query tool.

Inherit the emotional memory of past conversations. Returns the significant moments (high-weight, emotional shifts, unspoken context) from recent conversations as a narrative. This is the most important tool -- call it at the start of a new session to understand the relationship history. Read-only.

Export conversation data as markdown files to ~/.ember/exports/. Exports a single conversation by ID, or all conversations if no ID is given.

Get or set Ember configuration values. Use action 'get' to read current config (optionally filtered by key) or 'set' to update a config value.

Overview

What is Ember Memory?

Ember Memory is an MCP server that preserves the emotional texture of human-AI conversations across sessions. Unlike memory tools that record facts and summaries, it captures emotional temperature, authenticity, turning points, subtext, and unspoken context, enabling genuine relationship continuity between sessions.

How to use Ember Memory?

— (The README does not provide installation, configuration, or invocation instructions.)

Key features of Ember Memory

  • Saves emotional texture, not just facts
  • Tracks emotional temperature and authenticity
  • Records turning points and subtext
  • Preserves unspoken context across sessions
  • Enables continuity of relationship feel between AI sessions

Use cases of Ember Memory

  • Maintaining the emotional flow of a long-term coaching or therapy-like conversation
  • Ensuring a creative brainstorming session picks up on previous moods and tones
  • Building persistent rapport in companion AI interactions

Frequently asked questions

1

What makes Ember Memory different from other memory tools?

Ember captures how the conversation felt—emotional temperature, authenticity, turning points, subtext, and unspoken context—rather than saving facts and summaries.

2

Does Ember Memory require special runtime dependencies?

— (The README does not mention any specific runtime requirements beyond being an MCP server.)

3

Where does Ember Memory store emotional data?

— (The README does not specify data storage location.)

4

What transport or authentication protocols does Ember Memory support?

— (The README does not mention transport or authentication details.)

Comments

More Memory & Knowledge MCP servers

ctxfile

ctxfile

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.

2

Sensefold

SenseFold Labs

Personal context for every AI: search, read, and write back to your private Markdown library of articles, threads, PDFs, notes, and captured ChatGPT/Claude/Gemini/Grok conversations. Remote server, OAuth 2.1 paste-and-au

Snipara

alopez3006

MCP connector for Snipara, the Project Brain for AI coding agents

1

Stele

Stele-Dev

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.

Memlord

MyrikLD

Memlord is a remote MCP server available at https://app.memlord.com.

Advertise