// SCAN REPORT

Vultr MCP

284 tools. 119 can modify or destroy data without limits.

30 destructive tools with no built-in limits. Policy required.

Last updated: 11 Jun 2026

119 can modify or destroy data

165 read-only

284 tools total

Community server · catalogue entry verified 11/06/2026

How to control Vultr MCP ↓

TOOL MAP

What Vultr MCP exposes to your agents

Read (165) Write / Execute (81) Destructive / Financial (30)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Vultr MCP tools

Destructive · High delete This tool permanently removes block storage volumes, which cannot be undone. Destructive · Critical delete_bare_metal_server Deleting a bare metal server is a destructive action that cannot be undone and results in loss of the server instance and associated resources. Destructive · High delete_cdn_ssl_certificate Deleting an SSL certificate from a CDN zone is a destructive, non-reversible action that cannot be undone programmatically. Destructive · High delete_cdn_zone Deleting a CDN zone is an irreversible action that removes configuration and potentially disrupts content delivery.

119 of Vultr MCP's 284 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Vultr MCP

PolicyLayer is an MCP gateway — it sits between your AI agents and Vultr MCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "detach_from_instance": {
    "limits": [
      {
        "counter": "detach_from_instance_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_cdn_performance": {
    "limits": [
      {
        "counter": "analyze_cdn_performance_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Vultr MCP — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON VULTR →

Free to start. No card required.

FULL CATALOGUE

All 284 Vultr MCP tools

DESTRUCTIVE 30 tools

EXECUTE 16 tools

Execute scale_kubernetes_node_pool scale_kubernetes_node_pool Execute start Start a stopped instance. Execute start_bare_metal_server Start a bare metal server. Execute start_maintenance Start maintenance on a database. Execute start_migration start_migration Execute start_version_upgrade Start a database engine version upgrade. Execute stop Stop a running instance. Execute stop_bare_metal_server Stop a bare metal server. Execute stop_migration Stop an ongoing database migration. Execute reboot Reboot an instance. Execute reboot_bare_metal_server Reboot a bare metal server. Execute recycle_kubernetes_node recycle_kubernetes_node Execute reinstall reinstall Execute reinstall_bare_metal_server reinstall_bare_metal_server Execute upgrade_kubernetes_cluster upgrade_kubernetes_cluster Execute setup_kubernetes_cluster_for_workload setup_kubernetes_cluster_for_workload

WRITE 65 tools

Write detach_from_instance detach_from_instance Write fork_database fork_database Write regenerate_keys Regenerate the S3 access keys for an Object Storage instance. Write add_export add_export Write add_ip_whitelist_entry add_ip_whitelist_entry Write add_resource_to_collection add_resource_to_collection Write attach attach Write attach_to_instance attach_to_instance Write configure_basic_web_lb configure_basic_web_lb Write convert_instance_ip convert_instance_ip Write create create Write create_bare_metal_server create_bare_metal_server Write create_cdn_ssl_certificate create_cdn_ssl_certificate Write create_cdn_zone create_cdn_zone Write create_collection create_collection Write create_common_startup_script create_common_startup_script Write create_connection_pool create_connection_pool Write create_dns_domain Create a new DNS domain with a default A record Write create_dns_record Create a new DNS record for a domain Write create_domain create_domain Write create_forwarding_rule create_forwarding_rule Write create_from_url create_from_url Write create_group Create a new firewall group. Write create_ipv4 Create a new IPv4 address for an instance. Write create_iso Create a new ISO image from URL. Write create_kafka_topic create_kafka_topic Write create_kubernetes_cluster create_kubernetes_cluster Write create_kubernetes_node_pool create_kubernetes_node_pool Write create_logical_database Create a new logical database within a managed database instance. Write create_read_replica create_read_replica Write create_record create_record Write create_rule create_rule Write create_serverless_inference Create a new serverless inference subscription. Write create_startup_script Create a new startup script. Write create_user create_user Write create_vpc2 create_vpc2 Write disable_auto_ssl Disable Auto SSL for a load balancer. Write generate_kubernetes_credentials generate_kubernetes_credentials Write import_zone_file import_zone_file Write promote_collection_environment promote_collection_environment Write promote_read_replica Promote a read replica to a standalone database. Write restore_from_backup restore_from_backup Write setup_cdn_for_website setup_cdn_for_website Write setup_mysql_database setup_mysql_database Write setup_permissions Configure permissions for a subaccount. Write setup_postgresql_database setup_postgresql_database Write setup_service_user setup_service_user Write setup_standard_user setup_standard_user Write setup_website Set up basic DNS records for a website. Write update update Write update_bare_metal_server update_bare_metal_server Write update_cdn_zone update_cdn_zone Write update_collection_permissions update_collection_permissions Write update_connection_pool update_connection_pool Write update_dns_record Update an existing DNS record with new configuration Write update_group update_group Write update_kafka_topic update_kafka_topic Write update_kubernetes_cluster update_kubernetes_cluster Write update_kubernetes_node_pool update_kubernetes_node_pool Write update_record update_record Write update_serverless_inference Update an existing serverless inference subscription. Write update_startup_script update_startup_script Write update_user update_user Write update_user_access_control update_user_access_control Write update_vpc2 Update VPC 2.0 description.

READ 165 tools

OTHER 8 tools

Other async_tool An asynchronous test tool Other async_tool_with_params An async tool with parameters Other detach detach Other optimize_inference_costs optimize_inference_costs Other sync_tool A synchronous test tool Other test_tool A simple test tool Other generate_docker_credentials generate_docker_credentials Other setup_web_server_rules setup_web_server_rules

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Vultr MCP

Can an AI agent delete data through the Vultr MCP server? +

Yes. The Vultr MCP server exposes 30 destructive tools including delete, delete_bare_metal_server, delete_cdn_ssl_certificate. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Vultr MCP? +

The Vultr MCP server has 65 write tools including detach_from_instance, fork_database, regenerate_keys. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Vultr MCP.

How many tools does the Vultr MCP server expose? +

284 tools across 4 categories: Destructive, Execute, Read, Write. 165 are read-only. 119 can modify, create, or delete data.

How do I enforce a policy on Vultr MCP? +

Register the Vultr MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Vultr MCP tool call.

Deterministic rules across all 284 Vultr MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON VULTR →

Free to start. No card required.

284 Vultr MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.