Skip to main content
Glama

execution in a secure and scalable lab setup.

βš™οΈ Lab Virtual MCP Server (Execute Code Remotely via Claude AI) Create a virtual lab for users to run custom code remotely using the Model Context Protocol (MCP) and integrate with Claude AI or other clients.

πŸ”— GitHub Repo

πŸ“‚ This repo has moved to base/base-mcp

πŸš€ What This Lab Server Does 🧠 Enables remote Python code execution through cline AI

πŸ§ͺ Supports real-time lab scenarios (code evaluation, sandbox testing, etc.)

πŸ“‹ Prerequisites Ensure you have the following on your system:

βœ… Python 3.10.11

βœ… pip (Python package manager)

βœ… fastmcp (to serve the MCP endpoint)

βœ… uv (virtual environment manager, via scoop or curl)

βœ… Access to Claude Desktop or Cursor or cline (for testing)

🧱 Installation Steps

  1. Clone the MCP Server Repo

  1. Set up Python Environment

cd McpSever_Remote_code_execution

  1. Set Up Virtual Environment

  1. Install Dependencies

  1. Run the Server

You now have a remote code execution server listening for requests via MCP.

πŸ§ͺ MCP Client Configuration For Claude Desktop / Cursor, update your mcp_config.json:

Beofre start Mcp set path

βœ… Available Tools (Prebuilt in MCP)

Tool Description execute_code Executes user-provided Python code

πŸ’‘ Recommendations for Lab Admins βœ… Add sandboxing logic to app.py if users can run arbitrary code.

βœ… Use Docker or subprocess isolation for safer execution (optional).

βœ… Monitor logs and set execution timeouts.

Available Tools

1 tool
execute_codeC

Execute code in a secure sandbox environment.

Inputs: payload, filepath, latest_generated. Returns: result

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    C2.9/5.0

    Scored across 1 tool

    Disambiguation5/5

    With only one tool, there is no possibility of ambiguity or overlap between tools. The tool 'execute_code' has a clear, distinct purpose that cannot be confused with any other tool in the set.

    Naming Consistency5/5

    A single tool inherently has perfect naming consistency, as there are no other tools to compare it against. The name 'execute_code' follows a clear verb_noun pattern, which would be consistent if more tools were added.

    Tool Count2/5

    One tool is generally too few for a server's purpose, as it limits functionality and may not cover the domain adequately. For a 'Lab Virtual MCP Server' that likely involves code execution, additional tools for managing environments, listing sessions, or handling inputs/outputs would be expected.

    Completeness1/5

    The tool set is severely incomplete for the inferred domain of a lab or virtual environment. With only an 'execute_code' tool, there are obvious gaps such as creating or deleting environments, listing available sessions, handling file uploads/downloads, or monitoring execution status, which are essential for a coherent workflow.

    Related MCP Connectors

    Related MCP Servers