# get_inference_usage

A read tool on the Vultr MCP MCP server.

Agent View of the PolicyLayer registry record for `get_inference_usage`. HTML page: https://policylayer.com/tools/rsp2k-mcp-vultr/get-inference-usage

## Facts

- Tool: `get_inference_usage`
- Server: Vultr MCP (`rsp2k/mcp-vultr`) — https://policylayer.com/tools/rsp2k-mcp-vultr.md
- Homepage: https://github.com/rsp2k/mcp-vultr
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_inference_usage",
    "arguments": {}
  }
}
```

## Why get_inference_usage is rated Low

This tool retrieves usage metrics or statistics related to inference services. It performs no modifications, deletions, or external actions—it merely queries and returns data. Even though the description is absent, the 'get_' prefix and 'usage' noun strongly indicate a read-only retrieval operation with low severity.

From the tool's own definition: "Tool name 'get_inference_usage' indicates retrieval of usage data. The description is empty, but the naming pattern 'get_' is consistent with sibling tools like 'get_instance_details', 'get_domain_info', etc., which are Read operations."

## Use case

AI agents call get_inference_usage to retrieve information from Vultr MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Vultr MCP:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_inference_usage": {}
  }
}
```

## Other tools on Vultr MCP (283)

- `delete` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete.md
- `delete_bare_metal_server` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-bare-metal-server.md
- `delete_cdn_ssl_certificate` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-cdn-ssl-certificate.md
- `delete_cdn_zone` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-cdn-zone.md
- `delete_collection` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-collection.md
- `delete_connection_pool` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-connection-pool.md
- `delete_dns_domain` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-dns-domain.md
- `delete_dns_record` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-dns-record.md
- `delete_domain` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-domain.md
- `delete_export` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-export.md
- `delete_forwarding_rule` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-forwarding-rule.md
- `delete_group` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-group.md
- `delete_ipv4` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-ipv4.md
- `delete_iso` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-iso.md
- `delete_kafka_topic` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-kafka-topic.md
- `delete_kubernetes_cluster` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-kubernetes-cluster.md
- `delete_kubernetes_cluster_with_resources` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-kubernetes-cluster-with-resources.md
- `delete_kubernetes_node` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-kubernetes-node.md
- `delete_kubernetes_node_pool` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-kubernetes-node-pool.md
- `delete_logical_database` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-logical-database.md
- `delete_record` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-record.md
- `delete_rule` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-rule.md
- `delete_serverless_inference` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-serverless-inference.md
- `delete_ssl` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-ssl.md
- `delete_startup_script` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-startup-script.md
- `delete_user` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-user.md
- `delete_vpc2` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/delete-vpc2.md
- `purge_cdn_zone` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/purge-cdn-zone.md
- `remove_ip_whitelist_entry` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/remove-ip-whitelist-entry.md
- `remove_resource_from_collection` — Destructive — https://policylayer.com/tools/rsp2k-mcp-vultr/remove-resource-from-collection.md
- …and 253 more: https://policylayer.com/tools/rsp2k-mcp-vultr.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=rsp2k-mcp-vultr · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/rsp2k-mcp-vultr