AI agents call mft_price to retrieve information from Baselings without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries price data from Uniswap V3 Quoter. It performs information retrieval without modifying state, executing transactions, or triggering external operations. The explicit READ-ONLY designation and absence of any state-changing capability place it firmly in the Read category. Severity is low because price queries cannot cause harm—they inform decisions but don't execute them.
From the tool's definition Tool description explicitly states 'READ-ONLY, no wallet needed' and specifies it 'returns price per token, the pool used, and timestamp' - pure data retrieval with no side effects.
Attacks that exploit this kind of access
Get current MfT token price in USD via Uniswap V3 Quoter. READ-ONLY, no wallet needed. Returns price per token, the pool used, and timestamp. It is categorised as a Read tool in the Baselings MCP Server, which means it retrieves data without modifying state.
Register the Baselings MCP server in PolicyLayer and add a rule for mft_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 Baselings. Nothing to install.
mft_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 mft_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 mft_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.
mft_price is provided by the Baselings MCP server (jimbo530/baselings-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 →