Skip to main content
Glama

Projectron

Overview

Projectron is a local MCP server built with NestJS and TypeScript. It gives AI clients a controlled way to work with your computer through tools for filesystem, terminal, browser, documents, processes, network, and system operations.

Related MCP server: GPT-to-Windows

Features

  • MCP over Streamable HTTP and STDIO.

  • Local filesystem, terminal, browser, and document tools.

  • Process and system inspection and management.

  • Approval prompts for protected operations.

  • Configurable filesystem access roots.

  • Local JSON-based storage; no database required.

Requirements

  • Node.js

  • pnpm

Setup

pnpm install
cp .env.example .env

Review .env before starting. In particular, configure the allowed filesystem roots and choose the MCP transports you want to enable.

Run

HTTP server (development):

pnpm start:dev

MCP endpoint: http://127.0.0.1:3639/mcp (adjust the host or port if changed in .env).

STDIO server:

pnpm build
pnpm start:mcp:stdio

For an MCP client that supports remote HTTP servers, add the HTTP endpoint above. For a local STDIO client, use the built entry point:

node /absolute/path/to/Projectron/dist/modules/mcp/transports/stdio.transport.js

Run the STDIO process from the Projectron directory so it can load the project's environment configuration.

Development

pnpm start:dev   # Start with watch mode
pnpm build       # Compile the application
pnpm lint        # Run lint checks
pnpm test        # Run unit tests
pnpm test:e2e    # Run end-to-end tests

Protected tools may request explicit approval. Review each prompt before allowing an operation.

Author

Tarikul Islam
GitHub / Portfolio: github.com/Tarikul3639

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI clients to securely control and interact with a local Windows machine through 218 configurable tools for files, Git, processes, Windows UI, browser automation, WSL, Office, recovery, skills, and child MCP servers.
      8 npm
      MIT
    • F
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to control and interact with a local Windows computer through authenticated MCP tools, including file operations, shell commands, process management, HTTP requests, and system/media inspection.
      -