This record as markdown: /tools/defillama/get-v2-chains.md
What get_v2_chains does on Defillama
AI agents call get_v2_chains to retrieve information from Defillama without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why get_v2_chains is rated Low
This tool retrieves (gets) current TVL metrics for all chains. It performs a read-only query operation with no side effects, no code execution, and no data modification. The blast radius of misuse is minimal—an agent could only retrieve publicly available DeFi data, which carries no financial, destructive, or system-level risk.
From the tool's definition Tool name 'get_v2_chains' and description 'Get current TVL of all chains' indicates a retrieval operation that queries blockchain TVL data without modifying state.
Attacks that exploit this kind of access
The rule that runs get_v2_chains safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Defillama, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_v2_chains, this is the rule to start with:
get_v2_chains is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Defillama, apply this rule, and every get_v2_chains call is checked against it from then on.
Questions about get_v2_chains
Get current TVL of all chains. It is categorised as a Read tool in the Defillama MCP Server, which means it retrieves data without modifying state.
Register the Defillama MCP server in PolicyLayer and add a rule for get_v2_chains: 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 Defillama. Nothing to install.
get_v2_chains 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_v2_chains 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_v2_chains. 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_v2_chains is provided by the Defillama MCP server (@nic0xflamel/defillama-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Defillama, and thousands of servers like it.
This server
Across the catalogue