AI agents call udemy_kurs_tara to retrieve information from Udemy MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and extracts course content information from Udemy for analysis purposes. While it uses browser automation (Playwright), the actual operation is scanning/reading course data and exporting it—no modifications to Udemy data, no deletions, no code execution on the target system, and no financial transactions. The scope is limited to instructor's own course content review.
From the tool's definition Tool description states it 'tarar' (scans) Udemy course and 'kaydeder' (saves) content as JSON. The verb 'tarar' (scan/crawl) indicates data retrieval without modification. Action is read-only inspection of course content using Playwright browser automation.
Attacks that exploit this kind of access
Playwright ile Udemy kursunu tarar, icerigini JSON olarak kaydeder. It is categorised as a Read tool in the Udemy MCP MCP Server, which means it retrieves data without modifying state.
Register the Udemy MCP server in PolicyLayer and add a rule for udemy_kurs_tara: 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 Udemy MCP. Nothing to install.
udemy_kurs_tara is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the udemy_kurs_tara 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 udemy_kurs_tara. 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.
udemy_kurs_tara is provided by the Udemy MCP server (mustafayilmazart/kesif-udemy-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 →