Get token balance for a wallet
AI agents call getTokenBalance to retrieve information from AMOCA Solana MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries blockchain state to retrieve token balance information. It performs no side effects, does not execute transactions, does not modify data, and does not move funds. It is a straightforward read operation on existing data. Even though it operates on financial assets, the tool itself only reports balances and cannot initiate trades, payments, or transfers.
From the tool's definition Tool name is 'getTokenBalance' and description states 'Get token balance for a wallet' — purely a retrieval operation with no modification, deletion, or financial transaction capability.
Attacks that exploit this kind of access
Get token balance for a wallet. It is categorised as a Read tool in the AMOCA Solana MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AMOCA Solana MCP Server MCP server in PolicyLayer and add a rule for getTokenBalance: 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 AMOCA Solana MCP Server. Nothing to install.
getTokenBalance 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 getTokenBalance 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 getTokenBalance. 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.
getTokenBalance is provided by the AMOCA Solana MCP Server MCP server (manolaz/amoca-solana-mcp-server). 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 →