Search for blockchain chains by name or other attributes
AI agents call search_chains to retrieve information from Chains API without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search query against blockchain chain metadata—a pure read operation that retrieves information without modifying state, executing code, or causing financial transactions. The blast radius of misuse is minimal (information disclosure only). Confidence is high given explicit search semantics and the read-only pattern of all sibling tools.
From the tool's definition Tool description states it 'Search for blockchain chains by name or other attributes' with no mention of modification, deletion, or execution.
Attacks that exploit this kind of access
Search for blockchain chains by name or other attributes. It is categorised as a Read tool in the Chains API MCP Server, which means it retrieves data without modifying state.
Register the Chains API MCP server in PolicyLayer and add a rule for search_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 Chains API. Nothing to install.
search_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 search_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 search_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.
search_chains is provided by the Chains API MCP server (johnaverse/chains-api). 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 →