AI agents call getContractAddresses to retrieve information from Remote Mcp Authless without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation that retrieves contract addresses associated with the user. However, severity is elevated to medium (rather than low) because: (1) the server lacks authentication (per server description), meaning any client can invoke this tool; (2) contract addresses are sensitive identifiers that could enable unauthorized parties to identify, track, or target specific smart contracts; (3) combined with…
From the tool's definition Tool name is 'getContractAddresses' and description states 'Get all contract addresses for the user' — a retrieval operation with no modification capability.
Documented attack patterns abuse exactly the kind of access getContractAddresses gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Remote Mcp Authless, and nothing reaches the server without passing your rules. This is the rule we recommend for getContractAddresses:
{
"version": "1",
"default": "deny",
"tools": {
"getContractAddresses": {}
}
}getContractAddresses is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get all contract addresses for the user. It is categorised as a Read tool in the Remote Mcp Authless MCP Server, which means it retrieves data without modifying state.
Register the Remote Mcp Authless MCP server in PolicyLayer and add a rule for getContractAddresses: 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 Remote Mcp Authless. Nothing to install.
getContractAddresses 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 getContractAddresses 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 getContractAddresses. 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.
getContractAddresses is provided by the Remote Mcp Authless MCP server (kalepail/stellar-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Remote Mcp Authless, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Remote Mcp Authless tools catalogued and risk-classified — across an index of 43,000+ MCP servers.