Recent borrow events. Optionally filter by market ID and/or account address.
AI agents call get_borrows to retrieve information from Graph Lending without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical borrow event data from lending protocols via Graph queries. It performs no side effects, creates no new data, executes no code, and causes no destructive or financial operations. It is a straightforward read operation that fetches structured data about past borrowing activity.
From the tool's definition Tool name 'get_borrows' with description 'Recent borrow events. Optionally filter by market ID and/or account address.' indicates data retrieval without modification. The description explicitly states querying past events with optional filtering parameters.
Attacks that exploit this kind of access
Recent borrow events. Optionally filter by market ID and/or account address. It is categorised as a Read tool in the Graph Lending MCP Server, which means it retrieves data without modifying state.
Register the Graph Lending MCP server in PolicyLayer and add a rule for get_borrows: 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 Graph Lending. Nothing to install.
get_borrows 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_borrows 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_borrows. 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_borrows is provided by the Graph Lending MCP server (paulieb14/graph-lending-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 →