ToolTrust
C27/100
elusznik

mcp-server-code-execution-mode

mcpmain@27d23b8e2c76

@elusznik

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.

By elusznik | 14 findings | Scanned 6/22/2026 | tooltrust-scanner/v0.3.19 | 334

2 Critical1 High1 Low10 Info

Risk Summary

Needs Approval

Excessive Permissions plus Dep Visibility raises enough risk that this tool should not be auto-trusted.

Potential impact: The agent may gain overly broad access to files, network, databases, or execution capabilities.

Recommended action: Keep this tool behind manual approval and avoid unattended runs until the risky capabilities are narrowed or removed.

Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.

Security Findings (14)

  • CriticalAS-006

    đŸ’ģArbitrary Code Execution ×2

    heuristic signal

    tool name or description implies arbitrary script/code execution (evaluate_script, execute javascript, etc.)

    CODEINTERPRETER_CREATE_SANDBOXCODEINTERPRETER_EXECUTE_CODE

    Fix: This tool can execute arbitrary code or shell commands on the host system. Remove it unless strictly required. If kept: (1) restrict access to trusted users/agents only, (2) require human approval before each invocation (Claude Desktop: set approval_required: true; other clients: enable equivalent confirmation), (3) use the most restrictive sandbox or read-only mode available, and (4) never expose this tool to untrusted input sources.

  • HighAS-012

    🔄Tool Drift

    Tool set changed silently at vsha-27d23b8e2c76: 5 tool(s) added, 1 tool(s) removed without a version bump.

    + 5 added

    CODEINTERPRETER_CREATE_SANDBOXCODEINTERPRETER_EXECUTE_CODECODEINTERPRETER_GET_FILE_CMDCODEINTERPRETER_RUN_TERMINAL_CMDCODEINTERPRETER_UPLOAD_FILE_CMD

    − 1 removed

    run-code

    Fix: The set of tools exposed by this server changed between scans of the same version — a sign the package was silently updated without a version bump. Audit the changelog and all tool definitions before trusting this server. Pin to a specific commit hash rather than a floating version tag.

  • LowAS-011

    ℹī¸Missing Rate-Limit / Timeout

    CODEINTERPRETER_CREATE_SANDBOX:tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration

    Fix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.

  • InfoAS-002

    ⚠ī¸Excessive Permissions ×5

    declared capabilities: code/command execution, filesystem access

    CODEINTERPRETER_CREATE_SANDBOXCODEINTERPRETER_RUN_TERMINAL_CMD

    declared capabilities: code/command execution, network access, filesystem access

    CODEINTERPRETER_EXECUTE_CODE

    declared capabilities: filesystem access

    CODEINTERPRETER_GET_FILE_CMDCODEINTERPRETER_UPLOAD_FILE_CMD

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • InfoAS-014

    ℹī¸Dependency Inventory Unavailable ×5

    Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.

    CODEINTERPRETER_CREATE_SANDBOXCODEINTERPRETER_EXECUTE_CODECODEINTERPRETER_GET_FILE_CMDCODEINTERPRETER_RUN_TERMINAL_CMDCODEINTERPRETER_UPLOAD_FILE_CMD

    Fix: Review and remediate the identified issue.

Scan this tool yourself

Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.

Install once, then scan any MCP server:

$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash
$ tooltrust-scanner scan --server "npx -y mcp-server-code-execution-mode"

Adjust the package name if your npm registry name differs from the tool ID. View source

Add badge to your README

Copy this Markdown to show your ToolTrust grade on GitHub.

[![ToolTrust Grade C](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-c.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)