get_safe_responders
AI agents call get_safe_responders to retrieve information from Oncallhealth 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 responder availability or safety status without modifying data. While the empty description reduces confidence, the naming pattern and context within a burnout analysis server strongly suggest this retrieves on-call health/status data rather than executing operations or creating changes.
From the tool's definition Tool name 'get_safe_responders' indicates retrieval of responder status data. Description is empty, limiting direct confirmation.
Attacks that exploit this kind of access
get_safe_responders. It is categorised as a Read tool in the Oncallhealth MCP Server, which means it retrieves data without modifying state.
Register the Oncallhealth MCP server in PolicyLayer and add a rule for get_safe_responders: 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 Oncallhealth. Nothing to install.
get_safe_responders 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_safe_responders 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_safe_responders. 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_safe_responders is provided by the Oncallhealth MCP server (rootly-ai-labs/mcp-on-call-health). 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 →