{"title":"Codex and Claude Code command allowlists do not cover separately launched MCP servers","description":"Both products document destination controls for sandboxed commands and descendants, but network access, domain enforcement and administrator restrictions are separate configuration decisions. Neither command allowlist extends to separately launched MCP-server networking.","dataset_id":"spd:codex-vs-claude-code-when-does-a-network-allowlist-actually-constrain-commands-879a935f","canonical_url":"https://superpowerdaily.com/research/codex-vs-claude-code-when-does-a-network-allowlist-actually-constrain-commands-879a935f","version_url":"https://superpowerdaily.com/research/codex-vs-claude-code-when-does-a-network-allowlist-actually-constrain-commands-879a935f","version":"Live","snapshot_hash":null,"date_created":null,"date_modified":"2026-11-19T17:13:36.309Z","license":{"name":"Superpower Daily data reuse terms","url":"https://superpowerdaily.com/terms"},"license_url":"https://superpowerdaily.com/terms","coverage_note":"The sample covers the supplied local-session documentation for Codex and Claude Code, not every deployment or execution path. Codex documents sandboxed scripts, programs and child processes as covered; Claude documents shell commands and descendants as covered. The shared MCP finding concerns separately launched servers, not every possible MCP deployment. Sources are citation-only.","measurement_technique":["Synthesize the saved evidence without treating its recovery as a new collection or experiment. Preserve the November 18, 2026, 21:31 UTC cutoff.","Use the six supplied primary documents: OpenAI security, managed configuration and configuration reference; Anthropic sandboxing, settings precedence and settings reference. The candidate proposed five documents, but the supplied evidence includes a sixth settings-reference document.","Plan an evidence_matrix with columns for product, local-session scenario, required settings, shell and descendant coverage, exceptions, administrator control, platform/version caveat and supporting document.","Code matched scenarios as documented constrained, approval-dependent, outside scope or unspecified. Keep documented configuration behavior separate from observed runtime behavior.","Populate rows for networking disabled or enabled, destination enforcement, managed-only domains, escalation or exclusions, replacement proxies and separately launched MCP servers. Do not turn these categorical findings into a quantitative chart."],"methodology":["Synthesize the saved evidence without treating its recovery as a new collection or experiment. Preserve the November 18, 2026, 21:31 UTC cutoff.","Use the six supplied primary documents: OpenAI security, managed configuration and configuration reference; Anthropic sandboxing, settings precedence and settings reference. The candidate proposed five documents, but the supplied evidence includes a sixth settings-reference document.","Plan an evidence_matrix with columns for product, local-session scenario, required settings, shell and descendant coverage, exceptions, administrator control, platform/version caveat and supporting document.","Code matched scenarios as documented constrained, approval-dependent, outside scope or unspecified. Keep documented configuration behavior separate from observed runtime behavior.","Populate rows for networking disabled or enabled, destination enforcement, managed-only domains, escalation or exclusions, replacement proxies and separately launched MCP servers. Do not turn these categorical findings into a quantitative chart."],"metrics":[{"label":"Verified observations","value":"0","detail":"0 measured fields"},{"label":"Supported claims","value":"9","detail":"9 material findings"},{"label":"Cited sources","value":"6","detail":"6 primary or authoritative"},{"label":"Research score","value":"78","detail":"Automated topic and evidence score"}],"columns":[{"key":"entity","label":"Entity"},{"key":"metric","label":"Metric"},{"key":"value","label":"Value"},{"key":"unit","label":"Unit"},{"key":"observed","label":"Observed"},{"key":"source","label":"Source"},{"key":"transform","label":"Transform"}],"data":[],"sources":[{"name":"OpenAI","title":"Agent approvals & security | ChatGPT Learn","url":"https://learn.chatgpt.com/docs/agent-approvals-security","records":0},{"name":"Anthropic","title":"All settings - Claude Code Docs","url":"https://code.claude.com/docs/en/settings-reference","records":0},{"name":"OpenAI","title":"Configuration Reference | ChatGPT Learn","url":"https://learn.chatgpt.com/docs/config-file/config-reference","records":0},{"name":"Anthropic","title":"Configure the sandboxed Bash tool - Claude Code Docs","url":"https://code.claude.com/docs/en/sandboxing","records":0},{"name":"OpenAI","title":"Managed configuration | ChatGPT Learn","url":"https://learn.chatgpt.com/docs/enterprise/managed-configuration","records":0},{"name":"Anthropic","title":"Settings files and precedence - Claude Code Docs","url":"https://code.claude.com/docs/en/settings","records":0}],"provenance":{"publisher":"Superpower Daily","source_count":6,"source_urls":["https://learn.chatgpt.com/docs/agent-approvals-security","https://code.claude.com/docs/en/settings-reference","https://learn.chatgpt.com/docs/config-file/config-reference","https://code.claude.com/docs/en/sandboxing","https://learn.chatgpt.com/docs/enterprise/managed-configuration","https://code.claude.com/docs/en/settings"],"methodology":["Synthesize the saved evidence without treating its recovery as a new collection or experiment. Preserve the November 18, 2026, 21:31 UTC cutoff.","Use the six supplied primary documents: OpenAI security, managed configuration and configuration reference; Anthropic sandboxing, settings precedence and settings reference. The candidate proposed five documents, but the supplied evidence includes a sixth settings-reference document.","Plan an evidence_matrix with columns for product, local-session scenario, required settings, shell and descendant coverage, exceptions, administrator control, platform/version caveat and supporting document.","Code matched scenarios as documented constrained, approval-dependent, outside scope or unspecified. Keep documented configuration behavior separate from observed runtime behavior.","Populate rows for networking disabled or enabled, destination enforcement, managed-only domains, escalation or exclusions, replacement proxies and separately launched MCP servers. Do not turn these categorical findings into a quantitative chart."],"snapshot_hash":null},"distributions":{"csv":"https://superpowerdaily.com/api/research/codex-vs-claude-code-when-does-a-network-allowlist-actually-constrain-commands-879a935f?format=csv","json":"https://superpowerdaily.com/api/research/codex-vs-claude-code-when-does-a-network-allowlist-actually-constrain-commands-879a935f?format=json"}}