Gets all versions of a Retell agent
AI agents call get_agent_versions to retrieve information from RetellAI 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 version history metadata for an agent. It performs a query operation that returns data without creating, modifying, deleting, or executing any operations. The blast radius of misuse is minimal—an attacker gains visibility into agent versions but cannot alter configurations, delete data, or trigger external actions.
From the tool's definition Tool name 'get_agent_versions' and description 'Gets all versions of a Retell agent' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Gets all versions of a Retell agent. It is categorised as a Read tool in the RetellAI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the RetellAI MCP Server MCP server in PolicyLayer and add a rule for get_agent_versions: 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 RetellAI MCP Server. Nothing to install.
get_agent_versions 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_agent_versions 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_agent_versions. 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_agent_versions is provided by the RetellAI MCP Server MCP server (kuba2290/abhaybabbar_retellai-mcp-server). 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 →