AI agents call get_token_balances to retrieve information from Solblade without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves token balance information, which is a read-only operation with no side effects. It queries blockchain data but does not execute transactions, modify account state, or commit financial obligations. The context of a scoped MCP server with granular permissions reinforces that balance queries are restricted to informational access.
From the tool's definition Tool name 'get_token_balances' and description 'Get all SPL token balances for a wallet' indicate a query operation that retrieves account data without modifying state.
Attacks that exploit this kind of access
Get all SPL token balances for a wallet. It is categorised as a Read tool in the Solblade MCP Server, which means it retrieves data without modifying state.
Register the Solblade MCP server in PolicyLayer and add a rule for get_token_balances: 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 Solblade. Nothing to install.
get_token_balances 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_token_balances 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_token_balances. 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_token_balances is provided by the Solblade MCP server (nullxnothing/solblade). 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 →