get_instrument
Get details for a specific instrument by name
This record as markdown: /tools/aadarshvelu-derive-mcp/get-instrument.md
What get_instrument does on Derive MCP Server
AI agents call get_instrument to retrieve information from Derive MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why get_instrument is rated Low
This tool retrieves financial market data (instrument details) without modifying, executing, or deleting anything. It is a simple lookup query against a public API. There are no side effects, no code execution, and no financial transactions. The low severity reflects that accessing public market data poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'get_instrument' and description 'Get details for a specific instrument by name' indicate a retrieval operation.
Attacks that exploit this kind of access
The rule that runs get_instrument safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Derive MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_instrument, this is the rule to start with:
get_instrument is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Derive MCP Server, apply this rule, and every get_instrument call is checked against it from then on.
Questions about get_instrument
Get details for a specific instrument by name. It is categorised as a Read tool in the Derive MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Derive MCP Server MCP server in PolicyLayer and add a rule for get_instrument: 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 Derive MCP Server. Nothing to install.
get_instrument 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_instrument 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_instrument. 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_instrument is provided by the Derive MCP Server MCP server (aadarshvelu/derive-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Derive MCP Server, and thousands of servers like it.
This server
Across the catalogue