Gctrl runs on your own machine — the client starts it, so there is no endpoint to ping. 83 installs a week from npm. Last commit 17 Sep 2026.
Governed graph-native agent memory: knowledge extraction, fusion, hybrid RAG, scoped access tokens.
We read the source, 21 h ago · rules 3dff92dd89df
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);
- /var/run/docker.sock:/var/run/docker.sock:ro
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 gctrl -- npx -y gctrl-mcp
{
"mcpServers": {
"gctrl": {
"args": [
"-y",
"gctrl-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.gctrl]
command = "npx"
args = ["-y", "gctrl-mcp"]
{
"mcpServers": {
"gctrl": {
"args": [
"-y",
"gctrl-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"gctrl": {
"args": [
"-y",
"gctrl-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
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), GCTRL_API_TOKEN (Scoped GCTRL Access Token (gctrl_…) created in Settings → Access Control).
The author declared them in the registry entry; get the values from the project itself.
Offline 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.
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.
Rag Knowledge Graph MCP Server by MEOK AI Labs
Answers built from our own checks of this server.