MCP Server Code Execution Mode
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_BRIDGE_CPUS | No | CPU limit | |
| MCP_BRIDGE_PIDS | No | Process limit | 128 |
| MCP_BRIDGE_IMAGE | No | Container image | python:3.12-slim |
| MCP_BRIDGE_MEMORY | No | Memory limit | 512m |
| MCP_BRIDGE_RUNTIME | No | Container runtime (podman/docker) | auto |
| MCP_BRIDGE_TIMEOUT | No | Default timeout | 30s |
| MCP_BRIDGE_STATE_DIR | No | Host directory for IPC sockets and temp state | ./.mcp-bridge |
| MCP_BRIDGE_MAX_TIMEOUT | No | Max timeout | 120s |
| MCP_BRIDGE_CONTAINER_USER | No | Run as UID:GID | 65534:65534 |
| MCP_BRIDGE_RUNTIME_IDLE_TIMEOUT | No | Shutdown delay | 300s |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| run_pythonA | The Code Execution MCP engine. Executes Python code in a stateful, persistent rootless sandbox environment similar to a Jupyter notebook. Variables, functions, and imports are preserved across calls. Use this tool for general code execution, data analysis, or when the user asks to 'run code'. Supports loading additional MCP servers via the 'servers' array. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| code-execution-capabilities | Capability overview, helper reference, and sandbox usage notes (call runtime.capability_summary() inside the sandbox for this text). |
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'run_python' has a clearly defined and distinct purpose for executing Python code in a sandboxed environment.
The naming follows a consistent verb_noun pattern with 'run_python', and since there is only one tool, there is no inconsistency to evaluate. The naming is clear and predictable.
A single tool is too few for a server named 'MCP Server Code Execution Mode', which suggests a broader scope for code execution. While the tool is powerful, the set feels thin and limited, lacking coverage for other potential operations like managing sessions or handling different languages.
The tool set is severely incomplete for a code execution server. It only supports Python execution, missing obvious gaps such as tools for other programming languages, session management, code inspection, or error handling, which are essential for a comprehensive code execution environment.