Get information about available Deepgram models (transcription and TTS).
AI agents call get_models to retrieve information from Deepgram MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves static information about available models—a read-only operation with no side effects. There is no code execution, data modification, deletion, or financial impact. The minimal blast radius from misuse (returning model information) justifies a low severity rating.
From the tool's definition Tool name 'get_models' and description 'Get information about available Deepgram models' indicate a simple retrieval operation that queries model metadata without modifying, deleting, or executing operations.
Attacks that exploit this kind of access
Get information about available Deepgram models (transcription and TTS). It is categorised as a Read tool in the Deepgram MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Deepgram MCP Server MCP server in PolicyLayer and add a rule for get_models: 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 Deepgram MCP Server. Nothing to install.
get_models 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_models 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_models. 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_models is provided by the Deepgram MCP Server MCP server (reddheeraj/deepgram-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 →