call_tool_arch_manager · Superkit MCP: Risk & Policy

WHAT IT DOES

What call_tool_arch_manager does on Superkit

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

PARAMETERS

Parameter	Type	Required
`force`	boolean	—
`action`	string	Yes
`status`	string	—
`specDir`	string	—
`phaseNum`	string	—
`planFile`	string	—
`specName`	string	—
`projectPath`	string	Yes

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why call_tool_arch_manager needs a policy

The tool performs operations like 'syncSpec', 'updatePhase', and 'completePlan' which modify architecture specifications and plans — reversible write operations. 'validateSpecs' and 'validateArch' are read-like, but the presence of update/sync/complete operations makes Write the dominant category.

From the tool's definition Manages architecture and specs tasks (validateSpecs, completePlan, validateArch, syncSpec, updatePhase)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

call_tool_arch_manager Rate-limited

call_tool_arch_manager 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": {
    "call_tool_arch_manager": {
      "limits": [
        {
          "counter": "call_tool_arch_manager_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Superkit, so you can run agents against it safely.

FAQ

Questions about call_tool_arch_manager

What does the call_tool_arch_manager tool do? +

Manages architecture and specs tasks (validateSpecs, completePlan, validateArch, syncSpec, updatePhase). It is categorised as a Write tool in the Superkit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does call_tool_arch_manager accept? +

call_tool_arch_manager accepts 8 parameters: force, action, status, specDir, phaseNum, planFile, specName, projectPath. Required: action, projectPath. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on call_tool_arch_manager? +

Register the Superkit MCP server in PolicyLayer and add a rule for call_tool_arch_manager: 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 Superkit. Nothing to install.

What risk level is call_tool_arch_manager? +

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

Can I rate-limit call_tool_arch_manager? +

Yes. Add a rate_limit block to the call_tool_arch_manager 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 call_tool_arch_manager completely? +

Set action: deny in the PolicyLayer policy for call_tool_arch_manager. 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 call_tool_arch_manager? +

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