Developer · Local MCP server

Memograph

Graph-based memory system for LLMs with knowledge graphs and semantic search.

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.Indhar01/memograph
Version
0.4.0
Status
Active
Category
developer
Transport
stdio (local process)
Package
PyPI
Published
2026-06-25
Updated
2026-06-25
Publisher
Indhar01 (GitHub)
Namespace
Namespace verified by the MCP Registry via GitHub (github.com/Indhar01) · how
Repository
github.com/Indhar01/MemoGraph
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
PyPIruntime: uvxmemograph0.4.0stdioMEMOGRAPH_VAULT (required), MEMOGRAPH_READONLY, MEMOGRAPH_PROVIDER, MEMOGRAPH_MODEL, ANTHROPIC_API_KEY (secret), OPENAI_API_KEY (secret), OLLAMA_HOST

How to connect Memograph

Memograph runs locally from a Python package published to PyPI: memograph version 0.4.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install - the usual command is uvx memograph. It reads these environment variables: MEMOGRAPH_VAULT (required), MEMOGRAPH_READONLY, MEMOGRAPH_PROVIDER, MEMOGRAPH_MODEL, ANTHROPIC_API_KEY (secret), OPENAI_API_KEY (secret) and OLLAMA_HOST; set them in the client's configuration for this server.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "memograph": {
      "command": "uvx",
      "args": [
        "memograph"
      ],
      "env": {
        "MEMOGRAPH_VAULT": "<value>",
        "MEMOGRAPH_READONLY": "<value>",
        "MEMOGRAPH_PROVIDER": "<value>",
        "MEMOGRAPH_MODEL": "<value>",
        "ANTHROPIC_API_KEY": "<secret>",
        "OPENAI_API_KEY": "<secret>",
        "OLLAMA_HOST": "<value>"
      }
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More developer servers

All 5,152 →
ServerRunsEndpoint or package
MeminiLocal-first project memory and mistake-prevention guardrails for AI coding agents.Local · stdionpm: memini
memoMemory for AI agents - MLX (Apple Silicon) or CPU (Linux), sqlite-vec + BM25, zero cloud.Local · stdioPyPI: mlx-memo
MemocallRecall past Claude Code conversations from any project as clean, compact Markdown.Local · stdionpm: memocall
MemocoreShared memory for all your AI agents, your whole team and every MCP client - save, search, recall.Remote · HTTPLive check: sign-in requiredmemocore.ai
MemoirPersistent memory for AI coding tools via MCP. Remembers across sessions and machines.Local · stdionpm: memoir-cli
Memoize - persistent agent memoryPersistent cross-session memory shared by Codex, Claude Code, ChatGPT, and other AI agents.Remote · HTTPLive check: sign-in requiredmemoize.xyz
memoricProvenance-first database for teams and agents: every value carries sources, rules and coverage.Remote · HTTPLive check: sign-in requiredapp.memoric.io
MemoroPersonal AI memory layer on your own computer. Read/write durable memory across MCP clients.Local · stdionpm: @memoro/mcp-server