mcpbeat Sign in

Knowledge Graph MCP Server

by zcsabbagh Your server? Claim it
local only

Knowledge Graph MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 57 installs a week from pypi. Last commit 30 Dec 2025.

Knowledge graph MCP for student learning with spaced repetition and mastery tracking

Installs per day peak 16 · avg 7 · +8% w/w
a month agotoday
57
Installs / week
pypi · knowledge-graph-mcp
1
Stars
0 open issues
30 Dec 2025
Last commit
0 releases in 90 days
MIT
License
Python

Nothing serious here today

Today is the operative word: we check Knowledge Graph MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

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 knowledge-graph-mcp -- uvx knowledge-graph-mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "knowledge-graph-mcp": {
      "args": [
        "knowledge-graph-mcp"
      ],
      "command": "uvx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.knowledge-graph-mcp]
command = "uvx"
args = ["knowledge-graph-mcp"]
.cursor/mcp.json
{
  "mcpServers": {
    "knowledge-graph-mcp": {
      "args": [
        "knowledge-graph-mcp"
      ],
      "command": "uvx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "knowledge-graph-mcp": {
      "args": [
        "knowledge-graph-mcp"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: KNOWLEDGE_GRAPH_DB_PATH (Custom path for SQLite database file (optional, defaults to ~/.knowledge_graph/knowledge.db)). The author declared them in the registry entry; get the values from the project itself.

Alternatives to Knowledge Graph MCP

same job, measured the same way
Kindex
by wandercom

Persistent knowledge graph and MCP server for AI workflows with git-tracked project context.

1 685 installs/wk local only
Kindex
by jmcentire

Persistent knowledge graph and MCP server for AI workflows with git-tracked project context.

local only
Memograph
by indhar01

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

119 installs/wk local only
Mnemograph
by tm42

Event-sourced knowledge graph memory for AI coding agents with semantic search

148 installs/wk local only
Neuromcp
by adelelo13

Semantic memory for AI agents with hybrid search, knowledge graph, and consolidation

289 installs/wk local only
Octobrain
by muvon

Persistent memory for AI assistants with semantic search and knowledge graph relationships.

411 installs/wk local only
Alaya MCP
by securityronin

Local memory engine for AI agents with knowledge graphs, forgetting, and semantic recall

70 installs/wk local only
Flipnem
by flipnem

Build and study spaced-repetition flashcards with your agent.

answering

Knowledge Graph MCP — questions

Answers built from our own checks of this server.

Why is there no uptime for Knowledge Graph MCP?
Knowledge Graph MCP 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 knowledge-graph-mcp was installed 57 times last week.
How do I connect Knowledge Graph MCP?
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 knowledge-graph-mcp straight from pypi; nothing to host, nothing to sign up for.
How many people use Knowledge Graph MCP?
The pypi package knowledge-graph-mcp was installed 57 times in the last week. Week over week that is +8%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Knowledge Graph MCP open source?
Yes — it is published under the MIT licence, written in Python and 1 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.