ModelsAtlas
Explore
Atlas / MCP servers / elusznik / Code Execution Mode

Code Execution ModeSAFE

mcp/elusznik/code-execution-mode
MCP server by elusznik · agentic ai · agents · anthropic · Audited 2026-10-03
⚑ Report / re-scanSource ↗

An MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Implementation of Anthropic's and Cloudflare's ideas for reducing MCP tool definitions context bloat.

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
1 1r · 0w · 0d
Transport
stdio
License
GPL-3.0
Stars
339
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://mseep.ai/app/elusznik-mcp-server-code-execution-mode)

Stop paying 30,000 tokens per query. This bridge implements Anthropic's discovery pattern with rootless security—reducing MCP context from 30K to 200 tokens while proxying any stdio server.

[](https://www.anthropic.com/engineering/code-execution-with-mcp) [](https://blog.cloudflare.com/code-mode/) [](https://www.docker.com/blog/dynamic-mcps-stop-hardcoding-your-agents-world/) [](https://machinelearning.apple.com/research/codeact) [](https://modelcontextprotocol.io/) [](https://mseep.ai/app/4a84c349-1795-41fc-a299-83d4a29feee8)

Overview

This bridge implements the "Code Execution with MCP" pattern, a convergence of ideas from industry leaders:

  • Apple's [CodeAct](https://machinelearning.apple.com/research/codeact): "Your LLM Agent Acts Better when Generating Code."
  • Anthropic's [Code execution with MCP](https://www.anthropic.com/engineering/code-execution-with-mcp): "Building more efficient agents."
  • Cloudflare's [Code Mode](https://blog.cloudflare.com/code-mode/): "LLMs are better at writing code to call MCP, than at calling MCP directly."
  • Docker's [Dynamic MCPs](https://www.docker.com/blog/dynamic-mcps-stop-hardcoding-your-agents-world/): "Stop Hardcoding Your Agents’ World."
  • **Terminal Bench's [Terminus](
Read from source at commit 3c15429b69d2OBSERVED · 2026-10-03
02

Connect

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.

claude-code
claude mcp add code-execution -- uvx code-execution
claude-desktop
{
  "mcpServers": {
    "code-execution": {
      "command": "uvx",
      "args": [
        "code-execution"
      ]
    }
  }
}
03

Exposed tools (1)

1 read · 0 write · 0 destructive.

ToolRiskDescription
echoreadEcho the provided message
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (5)

LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
tests/test_entrypoint.py:218
exec(entrypoint, namespace)
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
tests/test_integration.py:100
result = eval(compiled, namespace, namespace)
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
requirements.txt
mcp, toon-format, pytest, pytest-asyncio
Why it matters. 4 requirement(s) not pinned with ==
Fix. pin exact versions
LOWSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README.md:258
- Ubuntu/Debian: `sudo apt-get install -y podman` or `curl -fsSL https://get.docker.com | sh`
LOWSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README.md:261
curl -LsSf https://astral.sh/uv/install.sh | sh

Gates applied: no_behavioural_pass.

Audited 2026-10-03 · audit v0.4.1 · source sha 3c15429b69d2full audit observations/trust-audit/mcp-server/elusznik__code-execution-mode.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-033c15429b69d2SAFEB89first audit
06

Questions

What is the Code Execution Mode MCP server?

An MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Implementation of Anthropic's and Cloudflare's ideas for reducing MCP tool definitions context bloat.

What tools does Code Execution Mode expose?

1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Code Execution Mode safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Code Execution Mode need?

No credential environment variables were found in its source, so it appears to need none.

How does Code Execution Mode run?

It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as code-execution.

How current is this page?

The grade is for one exact copy of the source (3c15429b69d2), read on 2026-10-03. The repository is watched and re-audited when it changes.

Advertisement