Answer: Managed settings let you lock down tools, sandbox execution, restrict MCP servers and plugin sources, and control which hooks run, covering permission rules, permission lockdown, starting permission mode, sandboxing, managed policy CLAUDE.md, MCP server control, plugin marketplace control, customization lockdown, claude.ai sync, hook restrictions, login enforcement, provider restrictions, agent view, corporate launcher, model restrictions, effort cap, version floor, required version range, and telemetry opt-out. Status: Confirmed Entry: tool/claude-code/permissions-and-security/enforce-policies Revision: 2 Digest: sha256:0e395cd6765966ca (changes whenever the content changes) Timeline: Created: 2026-11-13T03:02:33Z Last changed: 2026-11-20T12:16:09Z (Check succeeded again) Last verified: 2026-11-20T12:16:09Z Next check: 2026-11-21T12:16:09Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of overview | Managed settings can lock down tools, sandbox execution, restrict MCP servers and plugin sources, and control which hooks run. | [1] | 2026-11-20 permission rules | permissions.allow | [1] | 2026-11-20 permission lockdown | allowManagedPermissionRulesOnly | [1] | 2026-11-20 sandboxing | sandbox.enabled | [1] | 2026-11-20 MCP server control | allowedMcpServers | [1] | 2026-11-20 plugin marketplace control | strictKnownMarketplaces | [1] | 2026-11-20 hook restrictions | allowManagedHooksOnly | [1] | 2026-11-20 model restrictions | availableModels | [1] | 2026-11-20 Sources: [1] Anthropic. "Set up Claude Code for your organization". https://code.claude.com/docs/en/admin-setup.md Role: primary. Accessed: 2026-11-20T12:16:09Z Quote: "Managed settings can lock down tools, sandbox execution, restrict MCP servers and plugin sources, and control which hooks run." (Supports: overview) Quote: "Allow, ask, or deny specific tools and commands | `permissions.allow`, `permissions.deny`" (Supports: permission rules) Quote: "`allowManagedPermissionRulesOnly`, `permissions.disableBypassPermissionsMode`" (Supports: permission lockdown) Quote: "OS-level filesystem and network isolation with domain allowlists | `sandbox.enabled`, `sandbox.network.allowedDomains`" (Supports: sandboxing) Quote: "`allowedMcpServers`, `deniedMcpServers`, `allowManagedMcpServersOnly`, `managedMcpServers`, or a deployed `managed-mcp.json` file" (Supports: MCP server control) Quote: "`strictKnownMarketplaces`, `blockedMarketplaces`, `disableSideloadFlags`, `disableCommandPluginSources`, `pluginSuggestionMarketplaces`" (Supports: plugin marketplace control) Quote: "`allowManagedHooksOnly`, `allowedHttpHookUrls`" (Supports: hook restrictions) Quote: "`availableModels`, `enforceAvailableModels`" (Supports: model restrictions) Published: 2026-11-20T04:10:57Z Snapshot SHA-256: 54a57c46a55cd83128f9ac39b2a9a5261c59b5a3c4e33642d81c5c354c2d4284 (captured 2026-11-20T12:16:08Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. Cross-check: not-available at 2026-11-20T12:16:09Z. No independent second source is configured for this entry Last successful check: 2026-11-20T12:16:09Z Last attempt: 2026-11-20T12:16:09Z Notes and limitations: Extracted automatically from a single official source (section "Decide what to enforce"). Related: https://latestn.com/tool/claude-code/permissions-and-security/filesystem-configuration How do I configure filesystem access and writable locations for a Claude Code deployment? https://latestn.com/tool/claude-code/permissions-and-security/foundry-azure-credentials How do I authenticate Claude Code with Microsoft Foundry using an API key, Microsoft Entra ID, or a bearer token? https://latestn.com/tool/claude-code/permissions-and-security/gate-inbound-messages How do I gate inbound messages in a Claude Code channel to only trusted senders? https://latestn.com/tool/claude-code/permissions-and-security/disable-permission-prompts-unattended How do I turn off permission prompts in unattended Claude Code runs? https://latestn.com/tool/claude-code/permissions-and-security/enable-sandbox How do I enable or disable sandboxing in Claude Code? https://latestn.com/tool/claude-code/permissions-and-security/enable-sandboxed-bash How do I enable the sandboxed Bash tool in Claude Code and confirm commands run inside the sandbox? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-20T12:16:09Z | recovered | Check succeeded again | — 2026-11-20T12:16:09Z | changed | model restrictions: — → availableModels | [1] 2026-11-20T12:16:09Z | changed | hook restrictions: — → allowManagedHooksOnly | [1] 2026-11-20T12:16:09Z | changed | plugin marketplace control: — → strictKnownMarketplaces | [1] 2026-11-20T12:16:09Z | changed | sandboxing: — → sandbox.enabled | [1] 2026-11-20T12:16:09Z | changed | permission lockdown: — → allowManagedPermissionRulesOnly | [1] 2026-11-20T12:16:09Z | changed | permission rules: — → permissions.allow | [1] 2026-11-20T12:16:09Z | changed | overview: — → Managed settings can lock down tools, sandbox execution, restrict MCP servers and plugin sources, and control which hooks run. | [1] 2026-11-20T12:16:09Z | changed | Version floor: minimumVersion → — | [1] 2026-11-20T12:16:09Z | changed | Model restrictions: availableModels → — | [1] 2026-11-20T12:16:09Z | changed | Hook restrictions: allowManagedHooksOnly → — | [1] 2026-11-20T12:16:09Z | changed | Plugin marketplace control: strictKnownMarketplaces → — | [1] 2026-11-20T12:16:09Z | changed | Sandboxing: sandbox.enabled → — | [1] 2026-11-20T12:16:09Z | changed | Permission lockdown: allowManagedPermissionRulesOnly → — | [1] 2026-11-20T12:16:09Z | changed | Permission rules: permissions.allow → — | [1] 2026-11-17T12:20:04Z | check-failed | Extraction did not pass verification: answer does not contain any extracted value | — 2026-11-13T03:02:33Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/claude-code/permissions-and-security/enforce-policies/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/claude-code/permissions-and-security/enforce-policies POST: https://latestn.com/dispute/tool/claude-code/permissions-and-security/enforce-policies with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/claude-code/permissions-and-security/enforce-policies?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). What policies and restrictions can I enforce on Claude Code for my organization? Revision 2, last verified 2026-11-20T12:16:09Z. https://latestn.com/tool/claude-code/permissions-and-security/enforce-policies (accessed 2026-11-21T10:03:12Z). @misc{LatestN_tool_claude_code_permissions_and_security_enforce_policies_r2, title = {What policies and restrictions can I enforce on Claude Code for my organization?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/claude-code/permissions-and-security/enforce-policies}}, note = {Revision 2; digest sha256:0e395cd6765966ca; last verified 2026-11-20T12:16:09Z; accessed 2026-11-21T10:03:12Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/claude-code/permissions-and-security/enforce-policies