reload_config

THE RISK

High Risk

Why reload_config needs a policy

This tool triggers an external operation — reading and reloading a configuration file from disk into the running server's state. It's not a pure read (it changes server state) nor a write (it doesn't modify the file), but it executes a reload operation that affects the server's runtime behavior. Misuse could cause the server to load a maliciously crafted config file, hence medium severity.

From the tool's definition Reload custom patterns from the config file (.classmcp.json). Use this after modifying your config file.

Documented attack patterns abuse exactly the kind of access reload_config gives an agent:

POLICY

How to control reload_config

PolicyLayer is an MCP gateway — it sits between your AI agents and Classmcp, and nothing reaches the server without passing your rules. This is the rule we recommend for reload_config:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "reload_config": {
      "limits": [
        {
          "counter": "reload_config_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

reload_config stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Classmcp — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Classmcp tools

Write generate_css Generate CSS that defines all semantic classes. Add this to your project Write set_framework Set the CSS framework to use for all subsequent operations. Choose based on your project Read get_class Get the full utility classes for a semantic class name. Returns the CSS classes you should Read get_component Get a complete HTML component example using semantic classes. Great for seeing how classes Read get_ssr_info Get SSR/hydration safety information for a class pattern. Use this when building SSR/Next. Read list_classes List all available semantic class names, optionally filtered by category. Use this to disc Read list_custom_patterns List all custom (user-defined) patterns loaded from your config file. Read list_frameworks List all available CSS frameworks and their statistics.

All 10 Classmcp tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Classmcp → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about reload_config

What does the reload_config tool do? +

Reload custom patterns from the config file (.classmcp.json). Use this after modifying your config file. It is categorised as a Execute tool in the Classmcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on reload_config? +

Register the Class MCP server in PolicyLayer and add a rule for reload_config: 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 Classmcp. Nothing to install.

What risk level is reload_config? +

reload_config is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit reload_config? +

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

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

reload_config is provided by the Class MCP server (thedecipherist/classmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Classmcp tool call.

Start from Classmcp, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →