Change leverage (1-100x) on an existing Pear Protocol position. Higher leverage means greater liquidation risk for the same price move. WRITE: changes risk profile of a live position. Requires PEAR_TRADE_ENABLED=true.
AI agents use adjust_leverage to create or update resources in Mcp Pear — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Pear environment.
adjust_leverage modifies the leverage multiplier on an existing position, which changes the position's risk exposure and margin requirements. This is a reversible modification (leverage can be adjusted again), not an irreversible deletion. While it operates on financial positions, it does not move money or create new financial obligations—it adjusts the parameters of an existing position.
From the tool's definition Tool description explicitly states 'WRITE: changes risk profile of a live position' and 'Change leverage (1-100x) on an existing Pear Protocol position.' This modifies an active financial position's parameters reversibly.
Attacks that exploit this kind of access
Change leverage (1-100x) on an existing Pear Protocol position. Higher leverage means greater liquidation risk for the same price move. WRITE: changes risk profile of a live position. Requires PEAR_TRADE_ENABLED=true. It is categorised as a Write tool in the Mcp Pear MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Pear MCP server in PolicyLayer and add a rule for adjust_leverage: 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 Mcp Pear. Nothing to install.
adjust_leverage is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the adjust_leverage 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 adjust_leverage. 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.
adjust_leverage is provided by the Mcp Pear MCP server (marvelnwachukwu/mcp-pear). 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 →