One-shot: fetch + parse + extract for a spec, then emit a markdown
AI agents use generate_test_plan to create or update resources in Mk Spec Master — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mk Spec Master environment.
This tool creates and writes a new test plan document (markdown file/output) based on spec data. It is not destructive (doesn't delete/overwrite existing data), not financial, and not a direct code execution trigger. While it reads spec data, its primary function is to generate and emit new content, making Write the most applicable category.
From the tool's definition Tool 'generates' a test plan (write operation) and 'emits' markdown output, creating a new artifact. The description shows it 'fetches + parses + extracts', then produces output.
Attacks that exploit this kind of access
One-shot: fetch + parse + extract for a spec, then emit a markdown. It is categorised as a Write tool in the Mk Spec Master MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mk Spec Master MCP server in PolicyLayer and add a rule for generate_test_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 Mk Spec Master. Nothing to install.
generate_test_plan is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the generate_test_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.
Set action: deny in the PolicyLayer policy for generate_test_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.
generate_test_plan is provided by the Mk Spec Master MCP server (kao273183/mk-spec-master). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →