Get the balance of a specific token for the wallet
AI agents call get_token_balance to retrieve information from KaiaFun MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves wallet token balance information without creating, modifying, deleting, or executing any operations. It is a read-only query that returns data about the current state of a blockchain wallet. While the server itself handles financial assets (memecoins), this specific tool only reads balance data, making it a Read category with low severity risk.
From the tool's definition Tool name is 'get_token_balance' and description states 'Get the balance of a specific token for the wallet' — purely a query operation with no modification or execution of external effects.
Attacks that exploit this kind of access
Get the balance of a specific token for the wallet. It is categorised as a Read tool in the KaiaFun MCP MCP Server, which means it retrieves data without modifying state.
Register the KaiaFun MCP server in PolicyLayer and add a rule for get_token_balance: 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 KaiaFun MCP. Nothing to install.
get_token_balance 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_balance 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_balance. 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_balance is provided by the KaiaFun MCP server (weero-finance/kaiafun-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 →