List all audio files that have been transcribed and stored in the knowledge base.
AI agents call list_transcripts to retrieve information from MCP Audio RAG Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about stored transcripts without modifying, executing operations, or deleting data. It is a straightforward read operation that retrieves metadata about existing transcripts in the knowledge base.
From the tool's definition Tool name 'list_transcripts' and description 'List all audio files that have been transcribed and stored' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
List all audio files that have been transcribed and stored in the knowledge base. It is categorised as a Read tool in the MCP Audio RAG Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Audio RAG Server MCP server in PolicyLayer and add a rule for list_transcripts: 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 MCP Audio RAG Server. Nothing to install.
list_transcripts 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 list_transcripts 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 list_transcripts. 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.
list_transcripts is provided by the MCP Audio RAG Server MCP server (matheusslg/mcp-audio-rag). 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 →