Read-only check against Google/Yahoo 2024 bulk-sender requirements: SPF + DKIM + DMARC presence, DMARC alignment mode, TLS for sending IPs, ARC, one-click unsubscribe, and spam-rate compatibility. Returns per-requirement pass/fail/warning verdict with the specific Google/Yahoo rule cited. Use bef...
AI agents call check_sender_requirements to retrieve information from Intodns without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and evaluates email sender configuration against Google/Yahoo requirements. It has no side effects, performs no code execution on the user's systems, and makes no persistent changes. The tool is purely informational—it checks whether domains meet security standards but does not enforce, modify, or execute anything.
From the tool's definition The description explicitly states "Read-only check" and "Returns per-requirement pass/fail/warning verdict". The tool performs validation checks against sender requirements without modifying, executing external operations, or deleting data.
Attacks that exploit this kind of access
Read-only check against Google/Yahoo 2024 bulk-sender requirements: SPF + DKIM + DMARC presence, DMARC alignment mode, TLS for sending IPs, ARC, one-click unsubscribe, and spam-rate compatibility. Returns per-requirement pass/fail/warning verdict with the specific Google/Yahoo rule cited. Use before sending bulk mail (5k+ messages/day to consumer providers); use check_email_security for the broader read of SPF/DKIM/DMARC alone. Single GET, no auth. It is categorised as a Read tool in the Intodns MCP Server, which means it retrieves data without modifying state.
Register the Intodns MCP server in PolicyLayer and add a rule for check_sender_requirements: 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 Intodns. Nothing to install.
check_sender_requirements 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 check_sender_requirements 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 check_sender_requirements. 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.
check_sender_requirements is provided by the Intodns MCP server (rosconl/intodns-mcp-server). 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 →