Skip to main content
Glama
peeyushcodes

Windows Developer MCP Server

Windows Developer MCP Server

A production-grade Model Context Protocol (MCP) server for Windows developer environments. Built on FastMCP, it equips AI assistants (e.g. LM Studio, Claude Desktop, VS Code extension) with comprehensive capabilities for terminal execution, filesystem navigation, git operations, runtime inspections, container management, SQLite queries, web browser interaction, and security-sandboxed system control.


Key Features

  • 🖥️ Windows Terminal Provider: PowerShell & CMD execution with execution limits, custom working directory support, and background session tracking.

  • 📁 Filesystem Provider: Safe file reading, structured writing, directory trees, file searches, hash generation, and metadata inspection.

  • 🌿 Git Provider: Repository status, commit logs, branch management, diffs, and staging support.

  • 🐍 Python Provider: Virtual environment management, package inspection, module verification, and version details.

  • 🟢 Node.js Provider: Node & npm version detection, global/local package details, and script runner inspection.

  • 🐳 Docker Provider: Container listing, inspection, log tailing, image management, and compose state checks.

  • ⚙️ Windows System Provider: Hardware/OS info, process manager, environment variable inspector, and system metrics.

  • 🌐 Network Provider: DNS resolution, ping utilities, port connectivity checks, and HTTP/HTTPS header inspections.

  • 🗄️ SQLite Provider: Database schema inspection, safe parameterized queries, table listing, and index overview.

  • 📊 Project Provider: Automated project type detection (Python, Node, Rust, Go, C#), dependency tree analysis, and structure summary.

  • 🐙 GitHub Provider: Public/private repository inspection, issue tracking, PR status, release fetching, and search via GitHub API / gh CLI.

  • 🌐 Browser Provider: Web page fetching, HTML text extraction, URL status checks, and launching Windows default web browser.

  • 🛡️ Security Guardrails: Strict path-traversal sandboxing, read-only mode, command allowlisting, destructive command confirmation, and audit logging.


Related MCP server: allcanuse-mcp

Architecture & Security Model

                    ┌────────────────────────┐
                    │       MCP Client       │
                    │ (LM Studio / Claude)   │
                    └───────────┬────────────┘
                                │ JSON-RPC (stdio)
                                ▼
                    ┌────────────────────────┐
                    │      server.py         │
                    │   (FastMCP Engine)     │
                    └───────────┬────────────┘
                                │
          ┌─────────────────────┴─────────────────────┐
          ▼                                           ▼
┌──────────────────┐                       ┌──────────────────┐
│  Security Layer  │                       │ ProviderRegistry │
│  - Path Sandbox  │                       └────────┬─────────┘
│  - Command Audit │                                │ Auto-Discovers
│  - Read-Only     │                                ▼
└──────────────────┘                       ┌──────────────────┐
                                           │  12 Providers    │
                                           │  (40+ Tools)     │
                                           └──────────────────┘

Security Features

  1. Workspace Sandboxing: All file read/write operations are constrained to the configured workspace root (workspace.path). Path traversal outside the workspace triggers WorkspaceViolationError.

  2. Command Validation: Built-in regex filters block destructive OS commands (format, del /f /s /q C:\*, shutdown, reg delete, Set-ExecutionPolicy Bypass).

  3. Read-Only Mode: Setting read_only = true in config.toml instantly converts the server into a non-destructive inspection tool.

  4. Destructive Command Confirmation: Commands altering filesystem state require explicit confirm = true parameter flags.

  5. Audit Logging: All tool invocations and security checks are recorded to rotated logs in logs/.


Installation

Prerequisites

  • Windows 10 / 11 or Windows Server 2019+

  • Python 3.12+

1. Clone & Setup Virtual Environment

git clone https://github.com/peeyushcodes/windows-developer-mcp.git
cd windows-developer-mcp

# Create virtual environment
python -m venv .venv
.\.venv\Scripts\Activate.ps1

2. Install Package with Dev Dependencies

pip install -e .[dev]

Or using uv:

uv pip install -e .[dev]

Configuration

The server is configured via config.toml in the project root:

[server]
name = "Windows Developer MCP"
version = "0.1.0"

[workspace]
path = "."                  # Root directory for file operations
read_only = false           # Set to true to block all modifications

[security]
timeout = 60                # Default command execution timeout (seconds)
require_confirmation = true # Require confirm=true for destructive actions
max_output_length = 50000   # Maximum characters returned per tool execution

[providers]
terminal   = true
filesystem = true
git        = true
python     = true
node       = true
docker     = true
windows    = true
network    = true
sqlite     = true
project    = true
github     = true
browser    = true

Integration with MCP Clients

LM Studio Configuration

Add to your LM Studio mcp_config.json:

{
  "mcpServers": {
    "windows-developer-mcp": {
      "command": "C:\\Users\\<YourUsername>\\terminal-mcp\\.venv\\Scripts\\python.exe",
      "args": ["C:\\Users\\<YourUsername>\\terminal-mcp\\server.py"]
    }
  }
}

Claude Desktop Configuration

Add to %APPDATA%\Claude\claude_desktop_config.json:

{
  "mcpServers": {
    "windows-developer-mcp": {
      "command": "C:\\Users\\<YourUsername>\\terminal-mcp\\.venv\\Scripts\\python.exe",
      "args": ["C:\\Users\\<YourUsername>\\terminal-mcp\\server.py"]
    }
  }
}

Provider & Tool Matrix

Provider

Tools Included

Description

Terminal

run_powershell, run_cmd, get_working_directory, set_working_directory

Execute shell commands safely with timeouts & CWD control.

Filesystem

read_file, write_file, list_directory, tree, file_exists, file_info, search_files, hash_file

Read, write, list, search, and hash files within workspace bounds.

Git

git_status, git_log, git_branch, git_diff

Inspect git repository status, history, branches, and diffs.

Python

python_version, pip_version, check_package

Environment info and package availability checks.

Node

node_version, npm_version, package_info

Inspect Node runtime, npm version, and package.json details.

Docker

docker_info, list_containers, container_logs

Container inspection and log retrieval.

Windows

system_info, list_processes, environment_variables

Process listing, OS details, and env var inspection.

Network

ping, dns_lookup, check_port, fetch_headers

Connectivity testing and DNS lookup utilities.

SQLite

sqlite_tables, sqlite_schema, sqlite_query

Query and inspect local SQLite database files.

Project

detect_project_type, analyze_structure

Auto-detect framework & generate project summaries.

GitHub

search_repos, list_issues, list_prs, get_release

GitHub API / gh CLI repository integrations.

Browser

open_url, fetch_page, extract_text, check_url

Web page fetching, clean text extraction, and browser opening.


Testing & Quality Assurance

Run the full test suite using pytest:

.\.venv\Scripts\pytest.exe -v

Run code formatting and linting audit:

.\.venv\Scripts\ruff.exe check .

License

MIT License — see LICENSE for details.

Install Server
A
license - permissive license
B
quality
C
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Related MCP Servers

  • A
    license
    -
    quality
    D
    maintenance
    A production-ready MCP server that provides AI assistants with comprehensive GitHub developer tooling including PR analysis, code review, changelog generation, dependency auditing, commit summarization, and refactoring suggestions.
    Last updated
    15
    ISC
  • A
    license
    -
    quality
    B
    maintenance
    A MCP server for Windows/Linux that provides 90+ tools enabling AI assistants to systematically manage local systems, including system probing, command execution, file editing, network diagnostics, and more.
    Last updated
    12
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    A production-ready MCP server that enables AI assistants to execute shell commands, manage files, monitor system resources, and automate complex workflows with advanced features like stock tracking and web automation.
    Last updated
    7
    43
    MIT

View all related MCP servers

Related MCP Connectors

  • Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.

  • A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…

  • MCP server for AI agent profiles and smart notes. 60+ coding prompt packs with expert personas.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/peeyushcodes/windows-developer-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server