list_available_checkpoints
AI agents call list_available_checkpoints to retrieve information from Evo2 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 metadata about available model versions. It is a read-only operation with no ability to modify, execute code, delete data, or incur financial obligations. The blast radius if misused is minimal—an agent could only learn what checkpoints exist, which is non-sensitive operational information.
From the tool's definition Tool name 'list_available_checkpoints' clearly indicates a query/enumeration operation that retrieves available model checkpoints. No description is provided, but the name pattern is consistent with information retrieval (list/get operations).
Attacks that exploit this kind of access
list_available_checkpoints. It is categorised as a Read tool in the Evo2 MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Evo2 MCP Server MCP server in PolicyLayer and add a rule for list_available_checkpoints: 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 Evo2 MCP Server. Nothing to install.
list_available_checkpoints 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_available_checkpoints 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_available_checkpoints. 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_available_checkpoints is provided by the Evo2 MCP Server MCP server (not-a-feature/evo2-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 →