Activegzoonet/cortex
Local-first knowledge graph for developers. Watches your files, builds a knowledge graph with LLMs, lets you query across projects.
Quick Answer
- 1. gzoonet/cortex gives AI agents databases capabilities with 18 GitHub stars and a quality score of 60/99.
- 2. Install: Run
npx -y cortexor add the config to your MCP client. - 3. Runtime: npm — no authentication required.
- 4. Health: Actively maintained — last checked 7/29/2026.
Overview
Category: Databases
Runtime: npm
Install: npx -y cortex
Auth: No auth required
Source: community
Stars: 18
Setup time: ~30 sec
What You Can Build
With the gzoonet/cortex MCP server, your AI assistant can:
- Access databases functionality through natural language
- Use the server immediately with no API key setup
- Combine with other MCP servers for cross-tool automation workflows
- Run with npm for reliable, consistent deployments
Health Status
ActiveLast commit: 7/5/2026
Checked: 7/29/2026
Page updated: June 13, 2026
One-Click Install
Copy the snippet for your MCP client and paste it in.
Claude Desktop
Add to claude_desktop_config.json
{
"mcpServers": {
"cortex": {
"command": "npx",
"args": [
"-y",
"cortex"
],
"env": {}
}
}
}Cursor
Settings → MCP Servers → Add
{
"mcpServers": {
"cortex": {
"command": "npx -y cortex"
}
}
}Saves as .cursor/mcp.json in the download. Move it to your project root.
VS Code
Use with MCP extension
{
"mcpServers": {
"cortex": {
"command": "npx -y cortex"
}
}
}SDK & Code Integration Examples
Connect to gzoonet/cortex programmatically using TypeScript or Python MCP SDKs.
import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";
// Initialize gzoonet/cortex MCP client transport
const transport = new StdioClientTransport({
command: "npx",
args: ["-y","cortex"],
});
const client = new Client(
{ name: "mcp-app-client", version: "1.0.0" },
{ capabilities: { tools: {} } }
);
async function connectAndRun() {
await client.connect(transport);
const tools = await client.listTools();
console.log("Connected to gzoonet/cortex. Available tools:", tools);
}
connectAndRun().catch(console.error);MCP Server Configuration
Add this to your claude_desktop_config.json
{
"mcpServers": {
"cortex": {
"command": "npx",
"args": ["-y","cortex"],
"env": {}
}
}
}Topics
Error Resolution & Troubleshooting Matrix
Common JSON-RPC protocol error codes and environment troubleshooting for gzoonet/cortex.
-32600 (Invalid Request)Cause: Malformed JSON-RPC payload sent to server
Resolution: Verify MCP client payload adheres to JSON-RPC 2.0 specs.
-32601 (Method Not Found)Cause: Requested tool or resource method does not exist
Resolution: Call list_tools() to inspect supported tool names.
-32602 (Invalid Params)Cause: Missing or invalid tool arguments
Resolution: Check argument schema types against tool definition.
-32603 (Internal Error)Cause: Unhandled execution exception inside server process
Resolution: Inspect process stderr logs or check API key credentials.
AUTH_KEY_MISSINGCause: Required environment variable not set in MCP config
Resolution: Define required API key under 'env' object in claude_desktop_config.json.
STDIO_PIPE_CLOSEDCause: Server process crashed on startup
Resolution: Run install command manually in terminal to inspect error output.
Quality Score
Automated quality ranking of maintaining source repository.
Own this server?
Claim your listing to update description, links, and category — and get a verified badge.
Claim this listing →Similar MCP Servers
Other servers in the Databases category.
PostgreSQL MCP Server
MCP server for PostgreSQL databases — query tables, inspect schemas, run migrations via AI.
SQLite MCP Server
MCP server for SQLite databases — query, analyze, and manage SQLite databases through AI.
Supabase MCP Server
MCP server for Supabase — manage databases, auth, storage, and edge functions.
Redis MCP Server
MCP server for Redis — manage caches, queues, and key-value stores through AI.