Repair broken Markdown from LLM output or copy-paste. Fixes unclosed code fences, broken tables
AI agents use repair_markdown to create or update resources in AI Answer Copier — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AI Answer Copier environment.
An AI agent can call repair_markdown faster than any human can review — one bad instruction and it creates or modifies resources in AI Answer Copier by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Repair broken Markdown from LLM output or copy-paste. Fixes unclosed code fences, broken tables. It is categorised as a Write tool in the AI Answer Copier MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AI Answer Copier MCP server in PolicyLayer and add a rule for repair_markdown: 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 AI Answer Copier. Nothing to install.
repair_markdown 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 repair_markdown 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 repair_markdown. 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.
repair_markdown is provided by the AI Answer Copier MCP server (xjtlumedia/mcp_markdown_formatter). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.