Return live prices for up to 50 symbols in a single upstream batch
AI agents call get_prices_batch to retrieve information from OracleForge MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves real-time price feed data from multiple sources (Pyth, Chainlink, Uniswap v3) but performs no state modification, code execution, or financial transactions. Even though it accesses financial data (crypto prices), it is purely informational—merely querying and returning prices does not move money or commit financial obligations.
From the tool's definition Tool name and description indicate a read-only operation: 'Return live prices' is a query that retrieves cryptocurrency price data without modifying, deleting, or executing any operations.
Attacks that exploit this kind of access
Return live prices for up to 50 symbols in a single upstream batch. It is categorised as a Read tool in the OracleForge MCP MCP Server, which means it retrieves data without modifying state.
Register the OracleForge MCP server in PolicyLayer and add a rule for get_prices_batch: 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 OracleForge MCP. Nothing to install.
get_prices_batch 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_prices_batch 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_prices_batch. 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_prices_batch is provided by the OracleForge MCP server (maxiaworld/oracleforge). 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 →