AI agents call get_pulse to retrieve information from Curistat without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves current market data without side effects. It returns informational snapshots of market conditions for trading products (ES, NQ, etc.) similar to sibling tools like get_forecast_today and get_regime. No data is created, modified, deleted, or executed. The severity is low because misuse would only result in viewing market information, which cannot harm systems or data integrity.
From the tool's definition Tool name 'get_pulse' and description 'Get a market conditions snapshot for a product' indicate data retrieval with no modification, deletion, or code execution. The verb 'get' and 'snapshot' confirm read-only operations.
Attacks that exploit this kind of access
Get a market conditions snapshot for a product. It is categorised as a Read tool in the Curistat MCP Server, which means it retrieves data without modifying state.
Register the Curistat MCP server in PolicyLayer and add a rule for get_pulse: 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 Curistat. Nothing to install.
get_pulse 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_pulse 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_pulse. 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_pulse is provided by the Curistat MCP server (moxiespirit/curistat-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 →