access_control

Access control: SSH, PAM, sudo, user audit, password policy, shell restriction

SERVERDefense SOURCEdefense-mcp-server

Medium RISK CLASS

Category Write

Parameters 121 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/defense/access-control.md

WHAT IT DOES

What access_control does on Defense

AI agents use access_control to create or update resources in Defense, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Defense environment.

Parameter	Type	Required	Description
`force`	boolean	—	Force past critical sanity check findings (caution: may cause lockouts)
`shell`	string	—	Shell to set
`action`	string	Yes	Action to perform
`module`	string	—	PAM module to configure
`dry_run`	boolean	—	Preview changes without executing
`service`	string	—	PAM service to audit, e.g. 'sshd', 'login', 'sudo'
`max_days`	number	—	Maximum days before password change (PASS_MAX_DAYS)
`min_days`	number	—	Minimum days between password changes (PASS_MIN_DAYS)
`settings`	string	—	Comma-separated key=value pairs, e.g. 'PermitRootLogin=no,MaxAuthTries=4'
`username`	string	—	Username to restrict
`check_all`	boolean	—	Check common-auth, common-password, etc.
`warn_days`	number	—	Days before expiry to warn user (PASS_WARN_AGE)

Parameters from the server's own tool schema.

RISK

Why access_control is rated Medium

While access_control includes audit/read capabilities (user audit), its primary functions are Write operations that create or modify system security configurations. These changes are reversible (policies can be reconfigured), distinguishing it from Destructive.

From the tool's definition Tool manages 'SSH, PAM, sudo, user audit, password policy, shell restriction' — these involve creating, modifying, or configuring authentication and authorization settings (e.g., updating PAM rules, changing password policies, modifying sudo permissions,…

Risk signalsAccepts freeform code/query input (shell) · High parameter count (37 properties)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs access_control safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Defense, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For access_control, this is the rule to start with:

access_control Rate-limited

access_control stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "access_control": {
      "limits": [
        {
          "counter": "access_control_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Defense, apply this rule, and every access_control call is checked against it from then on.

FAQ

Questions about access_control

What does the access_control tool do? +

Access control: SSH, PAM, sudo, user audit, password policy, shell restriction. It is categorised as a Write tool in the Defense MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does access_control accept? +

access_control accepts 12 parameters: force, shell, action, module, dry_run, service, max_days, min_days, settings, username, check_all, warn_days. Required: action. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on access_control? +

Register the Defense MCP server in PolicyLayer and add a rule for access_control: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Defense. Nothing to install.

What risk level is access_control? +

access_control is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit access_control? +

Yes. Add a rate_limit block to the access_control rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block access_control completely? +

Set action: deny in the PolicyLayer policy for access_control. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides access_control? +

access_control is provided by the Defense MCP server (defense-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Defense, and thousands of servers like it.

This server

All 31 Defense tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →