Request to have the validator exit.
AI agents call validator_exit to retrieve information from Model Context Protocol Server for Solana Client without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though validator_exit only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Request to have the validator exit. It is categorised as a Read tool in the Model Context Protocol Server for Solana Client MCP Server, which means it retrieves data without modifying state.
Register the Model Context Protocol Server for Solana Client MCP server in PolicyLayer and add a rule for validator_exit: 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 Model Context Protocol Server for Solana Client. Nothing to install.
validator_exit 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 validator_exit 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 validator_exit. 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.
validator_exit is provided by the Model Context Protocol Server for Solana Client MCP server (tywenk/mcp-sol). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.