Low Risk

validate_custom_pattern

Validate a custom pattern before adding it as a rule.

How to control validate_custom_pattern ↓

What validate_custom_pattern does on Tech Debt MCP Server

AI agents call validate_custom_pattern to retrieve information from Tech Debt MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why validate_custom_pattern needs a policy

This tool performs validation—a form of querying or checking logic against a provided pattern. It does not create rules (that would be Write via add_custom_rule), does not execute code (Execute), and does not delete or modify existing data (Destructive/Write). The blast radius of misuse is minimal: a malformed or malicious pattern failing validation has low impact.

From the tool's definition Tool name 'validate_custom_pattern' and description 'Validate a custom pattern before adding it as a rule' indicate a validation/check operation with no side effects. The verb 'validate' is a read-like query operation that tests input without modifying state.

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

How to control validate_custom_pattern

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 validate_custom_pattern:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "validate_custom_pattern": {}
  }
}

validate_custom_pattern is read-only, so it stays allowed — but 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.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about validate_custom_pattern

What does the validate_custom_pattern tool do? +

Validate a custom pattern before adding it as a rule. It is categorised as a Read tool in the Tech Debt MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on validate_custom_pattern? +

Register the Tech Debt MCP Server MCP server in PolicyLayer and add a rule for validate_custom_pattern: 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 validate_custom_pattern? +

validate_custom_pattern is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit validate_custom_pattern? +

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

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

validate_custom_pattern 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.