AI agents call get_health to retrieve information from Mcp Pear without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves status information without modifying, executing, or destructing any data. It is purely diagnostic/monitoring in nature. Even though the server itself contains Write (adjust_leverage, create_agent_wallet), Execute (cancel_order), and Destructive (close_all_positions) tools, this specific tool only reads API health metadata.
From the tool's definition Tool name is 'get_health' and description states it 'Check[s] Pear Protocol API health. Returns service status, server timestamp, and uptime in seconds.' These are read-only queries with no side effects.
Attacks that exploit this kind of access
Check Pear Protocol API health. Returns service status, server timestamp, and uptime in seconds. Use this to verify the API is reachable before running other tools. It is categorised as a Read tool in the Mcp Pear MCP Server, which means it retrieves data without modifying state.
Register the Mcp Pear MCP server in PolicyLayer and add a rule for get_health: 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.
get_health 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_health 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_health. 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_health 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 →