Graphkeeper runs on your own machine — the client starts it, so there is no endpoint to ping. 207 installs a week from pypi. Last commit 25 Sep 2026.
Mines git history for file co-change patterns into a queryable knowledge graph via MCP.
We read the source, 18 h ago · rules ccca72095570
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
return subprocess.run(
absolute = os.path.normpath(os.path.join(raw_dir, source_file))
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
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.
claude mcp add graphkeeper -- uvx graphkeeper-cli
{
"mcpServers": {
"graphkeeper": {
"args": [
"graphkeeper-cli"
],
"command": "uvx"
}
}
}
[mcp_servers.graphkeeper]
command = "uvx"
args = ["graphkeeper-cli"]
{
"mcpServers": {
"graphkeeper": {
"args": [
"graphkeeper-cli"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"graphkeeper": {
"args": [
"graphkeeper-cli"
],
"command": "uvx"
}
}
}
Turns Obsidian vaults into AI-queryable knowledge graphs with 12 tools
Turn any codebase into a queryable knowledge graph — offline-first, zero API keys.
Knowledge-graph memory server for AI tools via MCP
Live public demo: query one person's learning and work history as a knowledge graph via MCP.
Graph-native memory for AI agents: a knowledge graph built from conversation, via MCP.
Persistent memory for Claude via weighted, interconnected knowledge nodes.
Knowledge coverage map and health score. Ingest docs into a governed knowledge graph via MCP.
Compresses AI chat sessions into a typed knowledge graph. Local/offline via Ollama.
Answers built from our own checks of this server.