Get execution client software (name, version, GitHub repo, language) running on a chain, aggregated from live RPC endpoints. Omit chainId to get a summary across all chains.
AI agents call get_clients 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 retrieves metadata about execution clients running on blockchain chains. It has no side effects, does not create, modify, or delete data, and does not execute code or commit financial transactions. It is a straightforward data query operation consistent with the Read category.
From the tool's definition Tool description states 'Get execution client software' and 'aggregated from live RPC endpoints' — retrieves and queries data about blockchain infrastructure without modification.
Attacks that exploit this kind of access
Get execution client software (name, version, GitHub repo, language) running on a chain, aggregated from live RPC endpoints. Omit chainId to get a summary across all chains. 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 get_clients: 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.
get_clients 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_clients 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_clients. 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_clients 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 →