em_swarm_health
AI agents call em_swarm_health to retrieve information from Execution Market without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on naming convention alone, 'health' typically indicates monitoring or retrieval of system state (Read category). However, the empty description significantly limits confidence. Given the sibling tools handle task management and financial operations (USDC payments), this isolated tool most likely queries swarm/system health metrics without side effects.
From the tool's definition Tool name 'em_swarm_health' suggests a health check or status query operation. Description is empty, providing no explicit confirmation of functionality.
Attacks that exploit this kind of access
em_swarm_health. It is categorised as a Read tool in the Execution Market MCP Server, which means it retrieves data without modifying state.
Register the Execution Market MCP server in PolicyLayer and add a rule for em_swarm_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 Execution Market. Nothing to install.
em_swarm_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 em_swarm_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 em_swarm_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.
em_swarm_health is provided by the Execution Market MCP server (https://mcp.execution.market/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 →