AI agents call get_chainlog_address to retrieve information from Usdd Test without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only lookup of chainlog addresses for protocol keys. It retrieves pre-existing configuration data (address mappings) from the USDD protocol without creating, modifying, or deleting anything. The operation has no side effects and is purely informational. Confidence is high based on the clear read-only semantics of 'resolve' and 'get' in the name and description.
From the tool's definition Tool name 'get_chainlog_address' and description 'Resolve one USDD Chainlog key' indicate a lookup/query operation that retrieves address data without modifying state.
Attacks that exploit this kind of access
Resolve one USDD Chainlog key, such as MCD_USDD, MCD_JOIN_USDD, MCD_JOIN_ETH_A, or PROXY_ACTIONS. It is categorised as a Read tool in the Usdd Test MCP Server, which means it retrieves data without modifying state.
Register the Usdd Test MCP server in PolicyLayer and add a rule for get_chainlog_address: 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 Usdd Test. Nothing to install.
get_chainlog_address 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_chainlog_address 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_chainlog_address. 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_chainlog_address is provided by the Usdd Test MCP server (mcp-server-usdd-test). 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 →