config_import · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What config_import does on Claude Flow

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

WHY IT NEEDS A POLICY

Why config_import needs a policy

This tool creates or modifies configuration data by importing JSON values into system runtimes. While reversible (configurations can be re-imported or edited), it affects critical infrastructure (daemon, MCP server, neural router) and could cause service degradation or security issues if malicious configuration is imported.

From the tool's definition Tool name is 'config_import' and description states it 'Import configuration from JSON' which modifies runtime configuration for daemon, MCP server, and neural router components.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

config_import Rate-limited

config_import 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": {
    "config_import": {
      "limits": [
        {
          "counter": "config_import_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 Claude Flow, so you can run agents against it safely.

FAQ

Questions about config_import

What does the config_import tool do? +

Import configuration from JSON Use when native settings.json edits are wrong because the values need to be read by the Ruflo runtime (daemon, MCP server, neural router) — those load via the config_* path, not by re-reading settings.json. For .gitignore / .editorconfig style files, native Edit is fine. It is categorised as a Write tool in the Claude Flow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on config_import? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for config_import: 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 Claude Flow. Nothing to install.

What risk level is config_import? +

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

Can I rate-limit config_import? +

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

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

config_import is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.