generate_fix_plan · Navable MCP: Risk & Policy

WHAT IT DOES

What generate_fix_plan does on Navable MCP

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

WHY IT NEEDS A POLICY

Why generate_fix_plan needs a policy

This tool creates or modifies a structured plan file (.navable-plan.json) with accessibility fix recommendations. It performs a Write operation (reversible data creation/modification) rather than Read (it transforms data and writes output), Execute (no code execution or external operations triggered), or Destructive (the file can be modified or removed).

From the tool's definition Tool description states it will "write it to .navable-plan.json", indicating file creation/modification. The action is reversible and non-destructive—the JSON file can be edited or deleted.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate_fix_plan Rate-limited

generate_fix_plan 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": {
    "generate_fix_plan": {
      "limits": [
        {
          "counter": "generate_fix_plan_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 Navable MCP, so you can run agents against it safely.

FAQ

Questions about generate_fix_plan

What does the generate_fix_plan tool do? +

Convert a scan result into a structured AccessibilityFixPlan and write it to .navable-plan.json.\n\n. It is categorised as a Write tool in the Navable MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on generate_fix_plan? +

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

What risk level is generate_fix_plan? +

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

Can I rate-limit generate_fix_plan? +

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

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

generate_fix_plan is provided by the Navable MCP server (web-dna/navable-web-accessibility-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.