AI agents call get_protocol 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 is a data retrieval tool for DeFi protocol metadata. It queries information from DeFiLlama and a contract registry but performs no state changes, transactions, or irreversible operations. The worst-case misuse (an agent requesting malicious protocol data) poses minimal risk compared to tools that could execute trades or transfer funds. Classified as Read with low severity.
From the tool's definition Tool retrieves 'detailed protocol info', 'registry contract data', 'key functions', and 'supported tokens'—all read operations that query and return data without modifying or executing transactions.
Attacks that exploit this kind of access
Get detailed protocol info including registry contract data, key functions, and supported tokens. Merges DeFiLlama data with local contract registry. 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_protocol: 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_protocol 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_protocol 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_protocol. 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_protocol 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 →