AI agents call get_chain to retrieve information from MoltLlama without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries DeFi chain metrics and protocol rankings. It has no side effects, does not modify data, execute code, delete anything, or move funds. It is a pure data query operation typical of informational APIs. The low severity reflects minimal risk even if queried with unexpected arguments — the worst outcome would be returning irrelevant data or an error.
From the tool's definition Tool name 'get_chain' and description specify retrieval of 'TVL overview', 'current TVL', 'TVL history', and 'top 20 protocols' — all query operations with no modification or execution capabilities.
Attacks that exploit this kind of access
Get chain TVL overview including current TVL, 24h/7d changes, TVL history (last 90 days), and top 20 protocols on the chain. It is categorised as a Read tool in the MoltLlama MCP Server, which means it retrieves data without modifying state.
Register the MoltLlama MCP server in PolicyLayer and add a rule for get_chain: 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 MoltLlama. Nothing to install.
get_chain 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_chain 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_chain. 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_chain is provided by the MoltLlama MCP server (moltllama/moltllama). 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 →