AI agents call get_token_price to retrieve information from Onchain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves pricing data from an external service (Jupiter) and returns it without any side effects. It does not modify state, execute code, delete data, or move funds. It is a straightforward read operation consistent with the server's read-only design.
From the tool's definition Tool description states 'Get the USD price of an SPL token' which is a pure data retrieval operation. Server description emphasizes 'read-only access' and lists this among query-based tools like 'get_account_info', 'get_sol_balance', 'get_token_holdings'.
Attacks that exploit this kind of access
Get the USD price of an SPL token by its mint address (via Jupiter). It is categorised as a Read tool in the Onchain MCP Server, which means it retrieves data without modifying state.
Register the Onchain MCP server in PolicyLayer and add a rule for get_token_price: 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 Onchain. Nothing to install.
get_token_price 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_price 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_price. 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_price is provided by the Onchain MCP server (sylvainlondon136/onchain-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 →