cloudcostwise
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AWS_PROFILE | No | AWS profile to use; otherwise the standard credential chain (env vars, SSO, instance role) is used. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
cloudcostwise finds AWS waste with the user's own credentials and cannot modify AWS: non-read calls are refused, and fix_guidance only returns text. Call scan first (it takes 30-60 seconds per region), then list_findings, explain_finding and fix_guidance on its results. Before the first scan, tell the user two things. The RI/Savings Plans checks (and one KMS spend read, only if an S3 bucket-key finding appears) call Cost Explorer, which AWS bills at $0.01 per request (a few cents a scan), and include_cost_explorer=false skips them. Results, including the account ID and resource IDs, come back to you, the assistant. scan with demo=true shows a recorded scan of a CloudWise test account (sample data, every identifier a placeholder) without calling AWS; the later tools then work on it, and you must tell the user it is sample data, not their account. This server never sends a scan or its summary to CloudWise unless the user's own setting says so.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scanA | Scan the user's AWS account for waste with their local credentials (read-only; any non-read AWS call is refused). Takes 30-60 s per region; up to 4 regions run at once. COST: the RI/Savings Plans checks call Cost Explorer, billed by AWS at $0.01 per request (a few cents a scan), plus one request for the last 30 days of spend and, only when an S3 bucket-key finding exists, one for KMS request spend (one per scan, not per region), which scores the result; tell the user before running, and pass include_cost_explorer=false to skip them (the score is then labelled "without spend data"). regions: comma-separated, or 'all'; default us-east-1 plus the profile's region. demo=true: show a recorded scan of a CloudWise test account (sample data, no AWS call, no credentials; profile, regions and include_cost_explorer are ignored) and say it is sample data. |
| list_findingsB | List findings from the last scan, with ids, optionally filtered by waste type or a minimum monthly saving in USD. |
| explain_findingA | Explain one finding: what was detected, the threshold, the pricing used, why it is waste, the risk of acting, and how validated this check is. |
| fix_guidanceA | How to fix one finding: the recommended action and, where known, the AWS CLI command, as text for the user to review. Never executes anything. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| scan-account | Scan the account for waste, then list and summarise the findings. |
| explain-finding | Explain one finding from the last scan. |
| fix-guidance | Present the fix guidance for one finding, read-only caveat first. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| scan-latest | The last scan's findings as JSON, held in this process. Read-only: never starts a scan or calls AWS. |
| scan-latest-summary | The one-screen text summary of the last scan. Read-only: never starts a scan or calls AWS. |
| checks | The free checks and the waste types each can report, read from the shipped detector code. |
TDQS
Scored across 4 tools
Each tool targets a distinct step: scan runs a new scan, list_findings reads results from the last scan, explain_finding and fix_guidance cover separate aspects of a single finding. The only mild overlap is scan vs list_findings, since the latter depends on the former and both deal with finding output.
Three tools follow a clear verb_noun pattern (explain_finding, fix_guidance, list_findings), but 'scan' is a bare verb that breaks the pattern. The set is still readable, but the convention is not uniform.
Four tools are well-scoped for a focused AWS waste-scanning workflow: run scan, list results, explain a finding, and give fix guidance. Each tool earns its place without bloat.
Core workflow coverage is strong: scan, list findings, explain, and fix guidance cover the main agent needs. Minor gaps exist around exporting results, historical scan comparison, or acknowledging/dismissing findings, but these are workable omissions for the stated read-only purpose.