AI agents use add_markdown to create or update resources in Jlab — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Jlab environment.
Adding a markdown cell creates new data in the notebook in a reversible manner. This is a Write operation rather than Execute because it does not run code or trigger external operations—it merely appends a markdown cell. The severity is low because markdown cells are documentation content with no side effects, and changes can be easily undone by deleting the cell.
From the tool's definition Tool name is 'add_markdown' and description states it 'Add a markdown cell to the notebook.' This is a create operation that adds content to the notebook.
Attacks that exploit this kind of access
Add a markdown cell to the notebook. It is categorised as a Write tool in the Jlab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Jlab MCP server in PolicyLayer and add a rule for add_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 Jlab. Nothing to install.
add_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 add_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 add_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.
add_markdown is provided by the Jlab MCP server (kdkyum/jlab-mcp). 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 →