Fetch a single-source price directly from a Pyth on-chain price
AI agents call get_pyth_solana_onchain 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 cryptocurrency price data from a blockchain oracle (Pyth Network on Solana) without modifying state, executing code, deleting data, or moving funds. It is a straightforward read operation that queries existing on-chain price information.
From the tool's definition Tool name contains 'get' and description states 'Fetch a single-source price directly from a Pyth on-chain price' - both indicate data retrieval with no modification or execution of external operations.
Attacks that exploit this kind of access
Fetch a single-source price directly from a Pyth on-chain price. 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_pyth_solana_onchain: 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_pyth_solana_onchain 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_pyth_solana_onchain 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_pyth_solana_onchain. 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_pyth_solana_onchain 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 →