List all replicas in your account
AI agents call list_replicas to retrieve information from Tavus MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a retrieval operation to enumerate existing replicas. It has no destructive, generative, or state-changing effects. While it reveals information about account resources, the read-only nature and low sensitivity of replica metadata listings classify it as a Read-category tool with low severity.
From the tool's definition Tool name 'list_replicas' and description 'List all replicas in your account' indicate a query operation that retrieves data without modification or side effects.
Attacks that exploit this kind of access
List all replicas in your account. It is categorised as a Read tool in the Tavus MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Tavus MCP Server MCP server in PolicyLayer and add a rule for list_replicas: 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 Tavus MCP Server. Nothing to install.
list_replicas 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_replicas 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_replicas. 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_replicas is provided by the Tavus MCP Server MCP server (rakeshdavid/tavus-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 →