AI agents call get-soon-testnet-last-transaction to retrieve information from SVM-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries blockchain transaction history from a testnet. It has no capability to modify, delete, or execute operations. The data queried is on a testnet (not production), and the operation is purely informational. A malicious agent could use it to enumerate transactions, but this causes no direct harm. Classified as Read with low severity.
From the tool's definition Tool name 'get-soon-testnet-last-transaction' and description 'Get the last transaction of an address on the Soon testnet' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get the last transaction of an address on the Soon testnet. It is categorised as a Read tool in the SVM-MCP MCP Server, which means it retrieves data without modifying state.
Register the SVM- MCP server in PolicyLayer and add a rule for get-soon-testnet-last-transaction: 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 SVM-MCP. Nothing to install.
get-soon-testnet-last-transaction 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-soon-testnet-last-transaction 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-soon-testnet-last-transaction. 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-soon-testnet-last-transaction is provided by the SVM- MCP server (rkmonarch/svm-mcp). 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 →