Memphora

io.github.MemphoraPublished by GitHub account Memphorav0.1.3Updated Oct 27, 2026

Add persistent memory to AI assistants. Store and recall info across conversations.

VerifiedSTDIODesktop onlyKnowledge & MemoryAI & ML

Overview

AI-generated overview

Memphora gives an AI assistant persistent memory: it stores facts and preferences and recalls them across conversations via the Memphora cloud service.

What you can do
  • Search stored memories for relevant information
  • Store new information for later recall
  • Extract memories automatically from a conversation
  • List all stored memories
  • Delete a specific memory
When to use it
Use it when you want an assistant to remember your preferences, facts and context between separate chats, or to build up a personal knowledge base that is searched automatically when relevant.
Requirements
Runs locally as a Python package (pip install memphora-mcp, or uvx memphora-mcp) over stdio. Needs a Memphora account and API key supplied as MEMPHORA_API_KEY; MEMPHORA_USER_ID optionally names the memory namespace (defaults to mcp_default_user). Requires network access to Memphora's cloud.
Before you install
Memories are stored in Memphora's cloud, so personal facts and conversation content leave your machine. The API key is a secret and must be kept out of shared config files. The assistant can write and delete memories, and may store information automatically without asking.

Installation

In SourceWeft

  1. Open Memphora in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

[Memphora Logo]

Memphora MCP Server

Add persistent memory to Claude, Cursor, Windsurf, and other AI assistants using the Model Context Protocol (MCP).

[PyPI] [License] [Website]

What is this?

This MCP server connects your AI assistant to Memphora, giving it the ability to:

  • Remember information across conversations
  • Search your personal knowledge base
  • Extract insights from conversations automatically
  • Recall your preferences, facts, and context

Quick Start

1. Install

bash
# Using pippip install memphora-mcp
# Or using uvx (recommended for Claude Desktop)uvx memphora-mcp

2. Get Your API Key

  1. Go to memphora.ai/dashboard
  2. Create an account or sign in
  3. Copy your API key from the dashboard

3. Configure Claude Desktop

Add to your Claude Desktop config file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

json
{  "mcpServers": {    "memphora": {      "command": "uvx",      "args": ["memphora-mcp"],      "env": {        "MEMPHORA_API_KEY": "your_api_key_here",        "MEMPHORA_USER_ID": "your_unique_user_id"      }    }  }}

4. Restart Claude Desktop

Close and reopen Claude Desktop. You should see the Memphora tools available!

Usage Examples

Storing Memories

Just tell Claude something about yourself:

You: "I work at Google as a software engineer"Claude: [stores memory] "Got it! I'll remember that you work at Google as a software engineer."
You: "My favorite programming language is Python"Claude: [stores memory] "Noted! I'll remember that Python is your favorite programming language."

Recalling Memories

Ask Claude about things you've told it before:

You: "Where do I work?"Claude: [searches memories] "You work at Google as a software engineer."
You: "What programming languages do I like?"Claude: [searches memories] "Your favorite programming language is Python."

Automatic Context

Claude will automatically search your memories when relevant:

You: "Can you help me with some code?"Claude: [searches memories for context]        "Sure! Since you prefer Python and work at Google, I'll write this in Python          following Google's style guide..."

Available Tools

ToolDescription
memphora_searchSearch memories for relevant information
memphora_storeStore new information for future recall
memphora_extract_conversationExtract memories from a conversation
memphora_list_memoriesList all stored memories
memphora_deleteDelete a specific memory

Configuration Options

Environment VariableDescriptionDefault
MEMPHORA_API_KEYYour Memphora API keyRequired
MEMPHORA_USER_IDUnique identifier for your memoriesmcp_default_user

Using with Other MCP Clients

Cursor

Add to your Cursor settings:

json
{  "mcp": {    "servers": {      "memphora": {        "command": "uvx",        "args": ["memphora-mcp"],        "env": {          "MEMPHORA_API_KEY": "your_api_key_here"        }      }    }  }}

Windsurf

Add to your Windsurf MCP configuration:

json
{  "mcpServers": {    "memphora": {      "command": "python",      "args": ["-m", "memphora_mcp"],      "env": {        "MEMPHORA_API_KEY": "your_api_key_here"      }    }  }}

Development

Running Locally

bash
# Clone the repogit clone https://github.com/Memphora/memphora-mcp.gitcd memphora-mcp
# Install dependenciespip install -e ".[dev]"
# Set your API keyexport MEMPHORA_API_KEY="your_key"
# Run the serverpython -m memphora_mcp

Testing

bash
pytest tests/

Privacy & Security

  • Your memories are stored securely in Memphora's cloud
  • Each user has isolated memory storage
  • API keys are stored locally on your machine
  • All communication is encrypted via HTTPS

Support

License

MIT License - see LICENSE for details.

Source: README.md at commit 3117f9b

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.3LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts