AI agents call get_embed_snippet to retrieve information from Yanifend without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves static embedding configuration data without creating, modifying, deleting, or executing operations. It is purely informational and read-only. While it exposes an API key (a sensitive credential), the tool itself does not move money, execute code, or modify state. The sensitivity of the API key itself does not change the tool's functional category from Read.
From the tool's definition get_embed_snippet returns a ready-to-paste embed snippet (api key + widget URL + script tag) for one personage. The tool 'Get' retrieves data with no side effects—it reads and returns configuration information needed to embed a widget.
Attacks that exploit this kind of access
Get the ready-to-paste embed (api key + widget URL + <script> tag) for ONE personage. It is categorised as a Read tool in the Yanifend MCP Server, which means it retrieves data without modifying state.
Register the Yanifend MCP server in PolicyLayer and add a rule for get_embed_snippet: 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 Yanifend. Nothing to install.
get_embed_snippet 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 get_embed_snippet 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 get_embed_snippet. 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.
get_embed_snippet is provided by the Yanifend MCP server (skippedaga/yanifend-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 →