mcpbeat

Adaptive Memory Graph MCP Server

io.github.raskolnikovdd/adaptive-memory-graph
local only

Adaptive Memory Graph runs on your own machine — the client starts it, so there is no endpoint to ping. 89 installs a week from pypi. Last commit 11 Mar 2026.

Persistent memory for Claude via weighted, interconnected knowledge nodes.

Installs per day peak 41 · avg 15 · +3% w/w
a month agotoday
89
Installs / week
pypi · adaptive-memory-graph
0
Stars
0 open issues
11 Mar 2026
Last commit
0 releases in 90 days
MIT
License
Python

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add adaptive-memory-graph -- uvx adaptive-memory-graph
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "adaptive-memory-graph": {
      "args": [
        "adaptive-memory-graph"
      ],
      "command": "uvx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.adaptive-memory-graph]
command = "uvx"
args = ["adaptive-memory-graph"]
.cursor/mcp.json
{
  "mcpServers": {
    "adaptive-memory-graph": {
      "args": [
        "adaptive-memory-graph"
      ],
      "command": "uvx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "adaptive-memory-graph": {
      "args": [
        "adaptive-memory-graph"
      ],
      "command": "uvx"
    }
  }
}

Adaptive Memory Graph — questions

Answers built from our own checks of this server.

Why is there no uptime for Adaptive Memory Graph?
Adaptive Memory Graph runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package adaptive-memory-graph was installed 89 times last week.
How do I connect Adaptive Memory Graph?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls adaptive-memory-graph straight from pypi; nothing to host, nothing to sign up for.
How many people use Adaptive Memory Graph?
The pypi package adaptive-memory-graph was installed 89 times in the last week. Week over week that is +3%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Adaptive Memory Graph open source?
Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.