datadog_list_hosts
AI agents call datadog_list_hosts to retrieve information from Integrations MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to query Datadog infrastructure to enumerate hosts. While the description is empty (lowering confidence slightly), the naming convention 'list_*' is a strong indicator of a retrieval operation with no side effects. Listing hosts in a monitoring platform is a read-only query that does not modify, delete, or execute anything. It poses minimal risk to data integrity or system state.
From the tool's definition Tool name 'datadog_list_hosts' indicates a list operation, which retrieves or queries data. The 'list' verb is characteristic of Read operations that fetch information without modifying state.
Attacks that exploit this kind of access
datadog_list_hosts. It is categorised as a Read tool in the Integrations MCP MCP Server, which means it retrieves data without modifying state.
Register the Integrations MCP server in PolicyLayer and add a rule for datadog_list_hosts: 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 Integrations MCP. Nothing to install.
datadog_list_hosts 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 datadog_list_hosts 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 datadog_list_hosts. 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.
datadog_list_hosts is provided by the Integrations MCP server (shriram-vasudevan/integrations-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 →