Gctrl runs on your own machine — the client starts it, so there is no endpoint to ping. 73 installs a week from npm. Last commit 28 Oct 2026.
Governed graph-native agent memory: knowledge extraction, fusion, hybrid RAG, scoped access tokens.
What the code does
We read the source, 4 d ago · rules 995398eba69f
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.
if !std::path::Path::new("/.dockerenv").exists() {
return subprocess.run(args, **kw)
const filePath = path.join(config.uploadDir, filename);
let mut stream = UnixStream::connect("/var/run/docker.sock")
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
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.
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.
claude mcp add gctrl -e 'GCTRL_API_TOKEN=<GCTRL_API_TOKEN>' -- npx -y gctrl-mcp{
"mcpServers": {
"gctrl": {
"command": "npx",
"args": [
"-y",
"gctrl-mcp"
],
"env": {
"GCTRL_API_TOKEN": "<GCTRL_API_TOKEN>"
}
}
}
}[mcp_servers.gctrl]
command = "npx"
args = ["-y", "gctrl-mcp"]
env = { GCTRL_API_TOKEN = "<GCTRL_API_TOKEN>" }{
"mcpServers": {
"gctrl": {
"command": "npx",
"args": [
"-y",
"gctrl-mcp"
],
"env": {
"GCTRL_API_TOKEN": "<GCTRL_API_TOKEN>"
}
}
}
}{
"servers": {
"gctrl": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"gctrl-mcp"
],
"env": {
"GCTRL_API_TOKEN": "<GCTRL_API_TOKEN>"
}
}
}
}Put your own value in place of
<GCTRL_API_TOKEN> (Scoped GCTRL Access Token (gctrl_…) created in Settings → Access Control).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
GCTRL_GATEWAY_URL (URL of your GCTRL harness MCP gateway, e.g. http://localhost:4000/api/agent/mcp (recommended mode)), GCTRL_API_URL (Direct GCTRL API base URL (alternative to gateway mode), e.g. http://localhost:4000/api).
Alternatives to Gctrl
same job, measured the same wayOffline codebase knowledge graph: 91% token reduction vs naive RAG, plus cross-session agent memory.
Cognitive memory for AI agents. Atkinson-Shiffrin, RAG, knowledge graph. 100+ tools.
97-domain knowledge graphs for AI agents — 4× F1 of RAG, 11× fewer tokens. MCP-native.
Self-hosted memory for AI agents over MCP: knowledge graph, vectors, graph RAG, cited answers.
Persistent knowledge memory for AI agents. Hybrid search, code graph, pgvector.
NVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.
Salesforce AgentForce knowledge graph — 40 nodes, Einstein Trust Layer, 11x fewer tokens than RAG.
Self-hosted MCP memory server: a typed knowledge graph on Postgres 16 and pgvector.
Gctrl — questions
Answers built from our own checks of this server.