Get all currently open (pending) futures positions.
AI agents call get_pending_positions to retrieve information from Bitunix MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns data about existing positions without modifying, deleting, or executing trades. It is a read-only operation that retrieves account state information. While it operates in a financial context (BitUnix exchange), the tool itself performs no financial transaction, commitment, or irreversible action.
From the tool's definition Tool name 'get_pending_positions' and description 'Get all currently open (pending) futures positions' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get all currently open (pending) futures positions. It is categorised as a Read tool in the Bitunix MCP MCP Server, which means it retrieves data without modifying state.
Register the Bitunix MCP server in PolicyLayer and add a rule for get_pending_positions: 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 Bitunix MCP. Nothing to install.
get_pending_positions 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_pending_positions 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_pending_positions. 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_pending_positions is provided by the Bitunix MCP server (luiinventions/bitunix-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 →