Infer MCP Server

This is an MCP (Model Context Protocol) server providing resource access via SSH and RDBMS connections. It is designed to integrate with AI Copilot tools like GitHub Copilot in VS Code and Cursor.

Setup

Install dependencies: npm install
Build: npm run build
Run: npm start

Features

SSH command execution
PostgreSQL database queries
Classifier training orchestration via SSH profiles

Configuration

The server loads configuration from either INFER_MCP_CONFIG_PATH (JSON file) or INFER_MCP_CONFIG (JSON string). Example content:

{ "sshProfiles": { "training-cluster": { "host": "cluster.example.com", "port": 22, "username": "trainer", "privateKey": "-----BEGIN OPENSSH PRIVATE KEY-----..." } }, "training": { "defaultCommandTemplate": "python train.py --dataset={{datasetPath}} --class={{subclass}}", "defaultTimeoutMs": 600000 } }

sshProfiles define reusable credentials for tools such as trainClassifier.
training controls defaults for classifier jobs.

Integration

Configure in your AI tool's MCP settings to connect to this server.

For VS Code GitHub Copilot: Add to mcp.json in .vscode folder.

Debugging

You can debug this MCP server using VS Code's debugger.

Deploy Server

HTTP connection URL

-

security - not tested

F

license - not found

-

quality - not tested

How are these scores calculated?

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

Tools

Enables remote command execution via SSH and database queries through PostgreSQL connections. Supports classifier training orchestration with configurable SSH profiles for AI-assisted infrastructure management.

Infer MCP Server

Infer MCP Server

Setup

Features

Configuration

Integration

Debugging

Tools

New MCP Servers

MCP directory API