Docs
MCP

MCP tools reference

The tools the emma MCP server exposes to your AI client — what each does, its parameters, and whether it needs confirmation.

The emma MCP server exposes your infrastructure to any MCP-compatible AI client (Claude Desktop, Cursor, your own agent) as a set of tools. This page lists them by category.

Set up the server first — see Connect the MCP server. All tools are scoped to the emma account whose token you configured.

Resources

list_resources

Lists the resources in your account, optionally filtered by type, provider, or region.

ParameterTypeRequiredDescription
typestringnoFilter by resource type (vm, volume, k8s, …)
providerstringnoFilter by cloud provider
regionstringnoFilter by region

Effects: read-only. Example: list_resources(type: "vm", region: "eu-central")

get_resource

Returns the full detail of a single resource by id.

ParameterTypeRequiredDescription
idstringyesThe resource id

Effects: read-only.

Cost

get_cost

Returns cost figures for the account, a provider, or a single resource over a time window.

ParameterTypeRequiredDescription
scopestringnoaccount (default), provider, or resource
idstringconditionalRequired when scope is provider or resource
periodstringnoe.g. last_30d (default), mtd

Effects: read-only.

Security

get_security_findings

Returns open security findings (exposed ports, permissive rules, unencrypted volumes).

ParameterTypeRequiredDescription
severitystringnoMinimum severity: low / medium / high

Effects: read-only.

Global options

Every tool accepts these:

OptionDescription
--tokenThe emma access token (or set EMMA_TOKEN) — scopes every call to your account
--formatjson (default) or text

These read tools never mutate infrastructure. Write actions (create/resize/delete) are not exposed over MCP without a confirmation flow — see Safety & confirmations.

See also

How is this guide?

Last updated on 17 Jul 2026

On this page