Home / MCP registry index / com.sulvo.publisher-revenue-audit/audit
com.sulvo.publisher-revenue-audit/audit
com.sulvo.publisher-revenue-audit/audit in the official MCP registry.
Endpoint https://publisher-revenue-audit.sulvo.com/mcp.
The registry describes it as: Publisher revenue audit: ads.txt and ad-stack checks, Sulvo onboarding, and Boost ad-block recovery
We read its 41 tools on 2026-10-26. Nothing in them matched our tool-poisoning rules.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.
Tools it advertises
check_https_certificate run_agentic_readiness_audit check_crawler_blocks get_sulvo_boost_setup start_sulvo_revenue_onboarding get_sulvo_revenue_onboarding_status attach_sulvo_revenue_audit connect_sulvo_backup_provider import_sulvo_backup_units review_sulvo_placement_recommendations save_sulvo_placement_plan map_sulvo_placement_backup get_sulvo_installation_instructions verify_sulvo_placement_installation lock_sulvo_placement_revision run_sulvo_activation_preflight verify_sulvo_site_ownership submit_sulvo_activation_workspace submit_sulvo_site_for_approval set_sulvo_onboarding_journey rollback_sulvo_activation get_sulvo_activation_smoke_status run_publisher_revenue_audit apply_for_sulvo_account start_sulvo_signup create_sulvo_signup_account update_sulvo_signup_company get_sulvo_signup_ads_txt verify_sulvo_signup_ads_txt get_sulvo_signup_status submit_sulvo_signup_documents get_publisher_revenue_audit_checklist get_publisher_monetization_benchmarks create_sulvo_ad_unit create_sulvo_interstitial_units create_sulvo_auto_sticky_units delete_sulvo_ad_unit get_sulvo_report list_sulvo_advanced_reports save_sulvo_advanced_report delete_sulvo_advanced_report
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/com-sulvo-publisher-revenue-audit-audit)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.