Medium Risk

add_custom_rule

Add a custom pattern-based tech debt rule.

How to control add_custom_rule ↓

What add_custom_rule does on Tech Debt MCP Server

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

Medium Risk

Why add_custom_rule needs a policy

This tool creates new custom rules in the tech debt analysis system, which modifies stored configuration state reversibly. It is not destructive (rules can be removed or overwritten), does not execute external code directly (the rule itself may later be executed by 'execute_custom_rules', but this tool only stores the rule definition), and does not involve financial or read-only operations.

From the tool's definition Tool name 'add_custom_rule' and description 'Add a custom pattern-based tech debt rule' indicate creation of new configuration/rule data.

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

How to control add_custom_rule

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_custom_rule": {
      "limits": [
        {
          "counter": "add_custom_rule_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

add_custom_rule 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.

  1. Create a free account and register Tech Debt MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about add_custom_rule

What does the add_custom_rule tool do? +

Add a custom pattern-based tech debt rule. It is categorised as a Write tool in the Tech Debt MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_custom_rule? +

Register the Tech Debt MCP Server MCP server in PolicyLayer and add a rule for add_custom_rule: 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 Tech Debt MCP Server. Nothing to install.

What risk level is add_custom_rule? +

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

Can I rate-limit add_custom_rule? +

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

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

add_custom_rule is provided by the Tech Debt MCP Server MCP server (pierrejanineh/techdebtmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Tech Debt MCP Server tool call.

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

Free to start. No card required.

16 Tech Debt MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.