MCP-Dev

Custom MCP tools
  • python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "dekstop-mcp-dev": {
      "command": "sh",
      "args": [
        "/path/to/MCP-dev/run.sh"
      ]
    }
  }
}

You have a lightweight local MCP server that lets you run custom tools and workflows in a controlled environment. It’s useful for development tasks where you want to execute scripts, shell commands, or small utilities from an MCP-enabled client while keeping everything self-contained.

How to use

You can enable and run the local MCP server from your MCP client. In your client, add the local MCP server configuration so the client can launch the server process and route tool calls to it. Enable the server globally or selectively per chat as you prefer. The server is designed to execute your local tools via a shell script, so ensure the script has the proper permissions and paths.

How to install

Prerequisites: you need Python 3 and a working virtual environment manager. You will also need an active shell to run the install commands.

# 1) Checkout to a local directory

# 2) Set up a virtual environment and install dependencies
python3 -m venv .venv --prompt MCP-dev
source .venv/bin/activate
python3 -m pip install -r requirements.txt

Additional setup guidance

Register the MCP server in your MCP client so the client can start and manage it. You can limit non-destructive tool calls by default to reduce risk; for tools like create_file, run_shell_command, and open_link, review before each call if you want extra safeguards.

{
  "mcpServers": {
    "MyCustomMCPTools": {
      "command": "sh",
      "args": [
        "/path/to/MCP-dev/run.sh"
      ]
    }
  }
}

Security and usage notes

If you plan to run scripts or commands, keep the sandboxed environment isolated and avoid installing new Python libraries outside the sandbox unless you explicitly need them. Use the local run script with appropriate permissions and review any tool calls that could affect your file system or external resources.

Optional: add system prompt

You can enhance behavior by adding a system prompt that guides how resources are accessed, how up-to-date information is sourced, and how the local filesystem can be used. Include guidance on where scripts and files should be saved and clarify any constraints on running external commands.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational