Skip to main content
Glama
cloudcostwise

cloudcostwise

cloudcostwise

PyPI Downloads Python 3.11+ MCP server AWS access: read-only Sharing: opt-in only License: Apache-2.0

Find AWS waste from your terminal or your AI assistant, including the kinds AWS's own tools don't flag. cloudcostwise scans your account on your own machine, with your own read-only AWS credentials.

don't, and 13 more go further than the closest AWS check.

pipx install cloudcostwise
cloudcostwise scan

From an AI assistant (the server starts with uvx, so install uv first):

claude mcp add -s user cloudcostwise -- uvx cloudcostwise mcp   # Claude Code
gemini mcp add -s user cloudcostwise uvx cloudcostwise mcp   # Gemini CLI

Then ask it: "Where am I wasting money on AWS?" Setup for Codex, Cursor and Kiro is further down.

What it finds that AWS's tools don't (every check, with the closest AWS check):

  • EBS snapshots whose volume is gone, or whose AMI was deregistered

  • Idle Application and Network Load Balancers, and Application Load Balancers carrying almost no traffic

  • CloudWatch log groups set to never expire, keeping a year or more, or empty for 30+ days

  • Empty S3 buckets, and incomplete multipart uploads whose parts keep billing

  • EFS file systems with no mount targets, or large ones with no cheaper storage tier set

  • Old and untagged ECR images still billed for storage

  • Lambda provisioned concurrency that is paid for and barely used

  • Idle Lightsail instances and load balancers, and Lightsail disks and static IPs attached to nothing

For idle EC2, RDS and NAT gateways, rightsizing and Savings Plans, AWS's tools cover the same ground: use them too.

cloudcostwise scanning our test account: findings ranked by monthly cost

Before you run it with AWS credentials:

  • It cannot change your account. Every AWS call a scan makes is checked, and anything that isn't a Describe, List, Get, Search or Lookup is refused before it is sent, whatever your credentials allow.

  • It talks to AWS and nothing else, unless you say yes. After the first scan in a terminal it asks once whether to share a summary (the CLI version, finding count, estimated savings and checks run, printed before it asks; never account IDs, resource names, regions or ARNs). The default is no. cloudcostwise share --off turns it off for good; CLOUDCOSTWISE_SHARE=no turns it off for that environment. See Sharing a summary.

  • Through an AI assistant (MCP), the findings, including your account ID and resource IDs, go to that assistant like any tool output.

  • It is not quite free to run. The RI/Savings Plans checks, and one KMS spend read when the S3 bucket-key check finds a bucket, call Cost Explorer, which AWS bills at $0.01 a request, and a scan makes up to

  • It stores up to three small files: your share answer in ~/.config/cloudcostwise/share.json, the summary numbers of your last scan in ~/.config/cloudcostwise/last-summary.json (never sent by itself; see Sharing a summary) and, only if you use cloudcostwise exclude, your exclude list in ~/.config/cloudcostwise/exclude.json (it never leaves your machine). No report, cache or credentials are written.

  • Open source (Apache-2.0). Read the code: github.com/cloudwise-app/cloudcostwise.

Least-privilege IAM policy (71 read-only actions): docs/iam-policy.json. See a real scan first, no credentials needed: cloudcostwise.io/sample-scan.

  • 20 of CloudWise's 46 service checks: EC2, Lambda, SageMaker, WorkSpaces, Lightsail, EBS, S3, EFS, ECR, RDS, DynamoDB, ElastiCache, Elastic IPs, NAT gateways and load balancers, VPC endpoints, dangling DNS records, CloudWatch logs and dashboards, security posture, RI/Savings Plans opportunities, and Compute Optimizer.

Install and run

pipx install cloudcostwise          # or: uvx cloudcostwise scan
cloudcostwise scan                      # us-east-1 plus your profile's region
cloudcostwise scan --profile prod --regions all
cloudcostwise scan --format json > waste.json
cloudcostwise scan --format json --anonymize > waste-to-share.json   # then read it through before you email it

Options:

Option

Meaning

--profile NAME

AWS profile; otherwise the standard credential chain (env vars, SSO, instance role)

--regions LIST

Comma-separated regions, or all for every enabled region. Account-level checks (CloudWatch dashboards, orphaned DNS records, RI/Savings Plans) run once, in us-east-1, and are skipped with a warning if it is not listed

--format table|markdown|json

Output format

--anonymize

Replace the account ID and the resource IDs, names, ARNs and tag values it recognizes with stable placeholders (account-1, resource-1, ...; the same value always gets the same one). Waste type, region, savings, confidence, action wording, warnings and counts stay. Works with every --format; it runs locally and sends nothing. Anonymizing is not complete: it replaces the identifiers it recognizes, so review the file before you send it

--demo

Print a recorded scan of a CloudWise test account instead of scanning: sample data with every identifier replaced by a placeholder, no AWS call, no credentials, no network. The first and last line say it is sample data, and JSON output carries "demo": true. Works with every --format and with --anonymize; --profile and --regions are refused with it; --no-cost-explorer, --no-exclude and --parallel have nothing to change and are ignored. It never asks to share a summary and is never sent, whatever your share setting says

--no-exclude

Ignore your exclude list (see below) for this run and show every finding

--no-cost-explorer

Make no Cost Explorer call. AWS bills those at $0.01 per request and a scan makes up to about 10. Skips the RI/Savings Plans checks, the one KMS spend read and the one request that reads this account's last 30 days of spend (all regions; credits and refunds left out), so the score falls back to "without spend data"

--parallel N

Regions scanned at once, each in its own process (default 4; --regions all takes ~2–3 min instead of ~10)

--verbose

Show data warnings (checks that could not read a metric report it as missing, never as zero)

Related MCP server: AWS FinOps MCP Server

Try it without AWS credentials

uvx cloudcostwise scan --demo          # a recorded sample scan; any --format

In an AI assistant, call the scan tool with demo set to true: list_findings, explain_finding and fix_guidance then work on the sample. It is a recording of a CloudWise test account, not your account, and every result says so. Nothing is scanned, nothing leaves your machine, and a demo result is never shared.

Leave resources out of every scan

A finding you have already decided to keep (a bucket that looks idle but is not, a snapshot you retain on purpose) can go on a local exclude list that survives the next run:

cloudcostwise exclude add vol-0abc123def4567890 --reason "kept for the audit"   # a resource ID or a full ARN
cloudcostwise exclude list
cloudcostwise exclude remove vol-0abc123def4567890
cloudcostwise scan --no-exclude                                                   # ignore the list for one run
  • Matching: an identical ID always matches. An ARN you add matches a finding whose ID is that resource's name (the scan reports an RDS instance, Lambda function, log group, load balancer or DynamoDB table by its bare name) or an ARN of the same service and name (a load balancer is named by its name, not the hash in its ARN). A bare ID matches the ARN form only when it is AWS-shaped (vol-..., snap-..., i-...); a plain name such as default or mydb matches only an identical ID, so it cannot hide unrelated resources. To hide a resource the scan reports by name, add either its name or its ARN.

  • The partner build ignores this list (its CLI and MCP never apply it).

  • Every scan reads ~/.config/cloudcostwise/exclude.json fresh (next to share.json) and leaves matching findings out of the table, Markdown, JSON and MCP output and out of the savings total and the score. It says how many under "Left out on purpose" ("2 findings left out by your exclude list (cloudcostwise exclude list)"); the JSON adds excluded_by_list_count and excluded_by_list_resource_ids.

  • With --anonymize, the exclusion happens first; the excluded IDs are still scrubbed from warnings and notes, and the JSON list of excluded IDs is emptied, so none is printed; the count stays. --verbose lists the excluded IDs under "Left out on purpose" (table and Markdown) when you are not anonymizing.

  • The list is never sent to CloudWise. The optional shared summary counts what the report showed, after exclusions, and never includes the list.

  • A missing file is an empty list. A file that cannot be read is treated as empty with a warning on stderr; the scan still runs, and exclude add leaves that file alone until you fix or delete it.

What AWS's free tools don't flag

This tool has 56 proven checks (L2 or above in VALIDATION.md: each fired on a real AWS resource built to trigger it and stayed silent on a healthy twin). 19 of them flag waste that none of AWS's own tools flag, and 13 more go further than the closest AWS check, going by AWS's lists of what its tools cover (Trusted Advisor, Cost Optimization Hub, Compute Optimizer; checked 2026-10-11).

Check

What it finds

Closest AWS check

ami_orphaned_snapshot

EBS snapshots left behind by an AMI that was deregistered

None

classic_lb_migration

Classic Load Balancers that would cost less as an ALB or NLB

None

elasticache_data_tiering_opportunity

Redis OSS or Valkey replication groups on r6g/r7g nodes that would cost less on data-tiering r6gd nodes

None

elasticache_engine_migration

Redis OSS or Memcached clusters that would cost about 20% less on Valkey

None

elasticache_extended_support_cost

ElastiCache engine versions billed the Extended Support surcharge

None

empty_log_group

CloudWatch log groups that have stored nothing for 30+ days

None

idle_lightsail

Stopped or idle Lightsail instances that still bill their bundle price

None

lambda_arm64_migration

Lambda functions that would cost about 20% less on arm64 (Graviton)

None

lambda_provisioned_concurrency_idle

Lambda provisioned concurrency that is paid for and barely used

None

lightsail_idle_load_balancer

Idle Lightsail load balancers

None

lightsail_unattached_disk

Lightsail disks attached to nothing

None

lightsail_unattached_static_ip

Lightsail static IPs attached to nothing

None

low_traffic_alb

Application Load Balancers carrying almost no traffic

None

multiple_eips_per_instance

Extra Elastic IPs on one instance, each billed as a public IPv4 address

None

no_lifecycle_efs

Large EFS file systems with no Infrequent Access or Archive tiering

None

orphaned_ebs_snapshot

EBS snapshots whose source volume no longer exists

None

previous_gen_sagemaker_instance

SageMaker instances on a previous generation with a cheaper current one

None

s3_empty_bucket

Empty S3 buckets left behind for 30+ days

None

stopped_sagemaker_notebook_storage

Stopped SageMaker notebook instances whose ML storage volume keeps billing

None

dynamodb_no_autoscaling

Provisioned DynamoDB tables with no auto scaling on their read or write capacity

Idle recommendation for DynamoDB provisioned tables: Compute Optimizer (and Cost Optimization Hub) look at the same provisioned tables, but only flag ones with no consumed capacity at all. Security Hub CSPM control DynamoDB.1 (tables should scale capacity with demand) checks for auto scaling, but it is an availability control with no cost wording, and its Recover > Resilience category is one Trusted Advisor does not show (checked 2026-11-05).

elasticache_replication_waste

Replicas kept on non-production ElastiCache replication groups, each billed like a full node

Amazon ElastiCache Multi-AZ clusters: Trusted Advisor's check looks at the same clusters with the opposite aim, alerting when Multi-AZ is inactive and recommending at least one replica per shard. Compute Optimizer, the source of Cost Optimization Hub's idle recommendations, calls a Redis or Valkey cluster idle only when all its nodes are idle over 14 days. None of the three tools documents a check for replicas on a non-production group that is in use (checked 2026-11-02).

excessive_retention_log_group

Log groups keeping a year or more of data they are billed to store

Amazon CloudWatch Log Group Retention Period: Trusted Advisor checks log group retention but flags retention shorter than a minimum (365 days by default) for compliance, so long, costly retention passes it.

idle_efs

EFS file systems with no mount targets: nothing can read them, and they still bill

Amazon EFS no mount target redundancy: Trusted Advisor checks EFS mount targets for multi-AZ redundancy, not file systems with no mount targets at all, and EFS is not among the resources Compute Optimizer or Cost Optimization Hub cover.

idle_load_balancer

Idle Application and Network Load Balancers

Idle Load Balancers: Trusted Advisor flags idle Classic Load Balancers only (Business Support+ or higher); its documentation says Application and Network Load Balancers are not included.

incomplete_multipart

Incomplete S3 multipart uploads whose stored parts keep billing

Amazon S3 Incomplete Multipart Upload Abort Configuration: Trusted Advisor flags buckets whose lifecycle configuration lacks a rule to abort incomplete multipart uploads after 7 days; it does not find the incomplete uploads that are already stored and billing.

lambda_excessive_timeout

Lambda timeouts set far above what the function needs

AWS Lambda functions with excessive timeouts: Trusted Advisor flags functions where more than 10% of invocations time out; it does not flag a configured timeout set far above the function's real duration.

no_retention_log_group

Log groups set to never expire, so they grow every month

Amazon CloudWatch Log Group Retention Period: Trusted Advisor checks log group retention but flags retention below a minimum, so a log group set to never expire passes it.

old_ecr_images

Old ECR images still billed for storage

Amazon ECR Repository without lifecycle policy configured: Trusted Advisor checks that an ECR repository has a lifecycle policy; it does not flag the old images already stored.

oversized_sagemaker_endpoint

SageMaker endpoints serving traffic on bigger instances than they need

Idle recommendation for SageMaker endpoints: Compute Optimizer flags SageMaker endpoints with zero invocations over 14 days but gives no rightsizing for endpoints that serve traffic on oversized instances.

s3_kms_bucket_key_disabled

S3 buckets on SSE-KMS default encryption with the S3 Bucket Key off, so every object request is a billed KMS call

S3.17 S3 general purpose buckets should be encrypted at rest with AWS KMS keys: Shown in Trusted Advisor as a Security Hub CSPM control (Business Support+ or higher, Security Hub CSPM with the Foundational Security Best Practices standard, AWS Config recording). It checks only that a bucket is encrypted with a KMS key (SSE-KMS or DSSE-KMS) and fails SSE-S3, so it passes an SSE-KMS bucket with the bucket key off; no S3 control mentions S3 Bucket Keys or KMS request cost. Trusted Advisor's S3 cost checks look at lifecycle and multipart settings, and neither Compute Optimizer nor Cost Optimization Hub lists S3 or KMS among its resource types (checked 2026-11-16).

s3_rapid_growth

S3 buckets whose Standard storage at least doubled in 30 days and grew by 10 GB or more

Amazon S3 Bucket Lifecycle Policy Configured: Trusted Advisor's S3 cost checks (lifecycle policy configured, incomplete multipart upload abort, version-enabled buckets without a lifecycle policy) look at bucket configuration, not at how fast a bucket is growing. Neither Compute Optimizer nor Cost Optimization Hub lists S3 among its resource types, so none of the three tools documents a check for a bucket that grows quickly (checked 2026-11-03).

untagged_ecr_images

Untagged ECR images still billed for storage

Amazon ECR Repository without lifecycle policy configured: Trusted Advisor checks that an ECR repository has a lifecycle policy; it does not flag the untagged images already stored.

For idle EC2, RDS and NAT gateways, rightsizing and Savings Plans, AWS's tools cover the same ground: use them too. Trusted Advisor's cost checks need a Business, Enterprise or Unified Operations support plan; Cost Optimization Hub and Compute Optimizer are free.

The hosted CloudWise product adds 23 more proven checks that none of AWS's tools flag, across AWS Backup, AppSync, CloudFront, Elastic Beanstalk, FSx, Glue, KMS, Kinesis, Route 53, Step Functions.

Excerpt of a real scan of our test account (cloudcostwise 0.1.15, us-east-1, 2026-10-27). The resources there are deliberately tiny, which is why the amounts are cents:

no_retention_log_group  x6  $0.06/mo
    us-east-1       /aws/lambda/cwfx-clo464-docdb-connect                               $0.01/mo
    us-east-1       /aws/lambda/cwfx-ec-hold-driver                                     $0.01/mo
    us-east-1       /aws/sagemaker/Endpoints/cwfx-w8b-ep-big                            $0.01/mo
    us-east-1       /aws/sagemaker/Endpoints/cwfx-w8b-ep-big-control                    $0.01/mo
    us-east-1       /aws/sagemaker/Endpoints/cwfx-w8b-ep-idle                           $0.01/mo
    us-east-1       /aws/sagemaker/Endpoints/cwfx-w8b-ep-idle-control                   $0.01/mo
old_ecr_images  x1  $0.06/mo
    us-east-1       cwfx-old-ecr-images                                                 $0.06/mo
untagged_ecr_images  x1  $0.02/mo
    us-east-1       cwfx-untagged-ecr-images                                            $0.02/mo
idle_efs  x1  $0.01/mo
    us-east-1       fs-090bfb32bd49de8b7                                                $0.01/mo

Use it from Claude Code, Codex, Cursor, Kiro or Gemini CLI

cloudcostwise mcp runs the same scan as an MCP server (stdio). Then ask your assistant: "Where am I wasting money on AWS?"

The plugin and registry entries start the server with uv, so install uv first (brew install uv or pipx install uv).

Claude Code, as a plugin (asks for your AWS profile):

/plugin marketplace add cloudwise-app/cloudcostwise
/plugin install cloudcostwise@cloudcostwise

Claude, as a skill with no MCP server: the folder plugins/cloudcostwise holds one Markdown skill that tells Claude how to run a pinned release of this CLI in your terminal and read the result. It contains no code. To use it in Claude Code, copy plugins/cloudcostwise/skills/aws-waste-scan into ~/.claude/skills/.

Claude Code, as a plain MCP server:

claude mcp add cloudcostwise -- uvx cloudcostwise mcp
# a specific profile:
claude mcp add cloudcostwise -e AWS_PROFILE=prod -- uvx cloudcostwise mcp

Codex (~/.codex/config.toml):

[mcp_servers.cloudcostwise]
command = "uvx"
args = ["cloudcostwise", "mcp"]
env = { AWS_PROFILE = "prod" }

Cursor: Add to Cursor (uses your default AWS credentials), or edit ~/.cursor/mcp.json (.cursor/mcp.json in a project):

{
  "mcpServers": {
    "cloudcostwise": {
      "command": "uvx",
      "args": ["cloudcostwise", "mcp"],
      "env": { "AWS_PROFILE": "prod" }
    }
  }
}

Kiro (~/.kiro/settings/mcp.json, or .kiro/settings/mcp.json in a workspace): the same JSON as Cursor.

Gemini CLI, as an extension:

gemini extensions install https://github.com/cloudwise-app/cloudcostwise

Gemini CLI removes environment variables whose names contain KEY, SECRET, TOKEN or similar words (such as AUTH and CREDENTIAL) before it starts any MCP server, the extension and the plain server below alike. So AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY and AWS_SESSION_TOKEN set in your shell never reach cloudcostwise, while AWS_PROFILE and AWS_REGION do (AWS_DEFAULT_REGION is removed too, so set the region in the profile). If your credentials are only in the environment, put them in a profile in ~/.aws (file and SSO profiles both work).

Gemini CLI, as a plain MCP server:

gemini mcp add -s user cloudcostwise uvx cloudcostwise mcp
# a specific profile:
gemini mcp add -s user -e AWS_PROFILE=prod cloudcostwise uvx cloudcostwise mcp

In each client, leave out AWS_PROFILE to use the standard AWS credential chain. Codex passes only a few basic variables (such as HOME and PATH) to MCP servers, so AWS_PROFILE or credentials set in your shell do not reach it: set the profile in env as above.

Tools, all read-only: scan, list_findings, explain_finding, fix_guidance. fix_guidance returns the steps and AWS CLI command as text for you to review; nothing is ever executed. The assistant is told about the Cost Explorer cost before it scans, and include_cost_explorer=false skips it.

No tool can share a scan: the server sends a summary only when your own setting says yes (below). Otherwise the first scan of a session whose summary was saved ends with a note that nothing was sent, and that cloudcostwise share --last, run in your own terminal, shows the summary and sends it only if you type y. With the setting on, each scan that sends a summary says whether CloudWise confirmed it arrived.

Resources are read-only views of the last scan held by the running server. Reading one never starts a scan or calls AWS; before the first scan they say so:

  • cloudcostwise://scan/latest: the last scan's findings as JSON.

  • cloudcostwise://scan/latest/summary: the one-screen text summary.

  • cloudcostwise://checks: the checks and the waste types each can report.

Prompts appear in the slash menu of clients that support them: scan-account (optional profile and regions), explain-finding and fix-guidance (each takes a finding_id). None asks the assistant to change anything in AWS. In Claude Code, /mcp__cloudcostwise__fix-guidance with a finding id from list_findings presents the guidance with the read-only caveat first.

Permissions

The minimal policy the checks use is in docs/iam-policy.json. AWS-managed ReadOnlyAccess also works, but it is much broader than the scan needs. It was derived from a scan of an account with most supported resource types; if a check lacks a permission, the scan says so in its data warnings instead of failing. EC2 instance prices come from the AWS Price List when the AWS credentials the scan uses, or failing that your default AWS credentials, allow pricing:GetProducts, and from built-in prices (adjusted by region) otherwise.

One of those reads, lambda:ListFunctions, returns each function's environment variables as plain text. The scan reads only sizing and configuration fields and none of those values reaches a finding, a report or a file, but anyone holding the role can read them.

Sharing a summary (optional)

The default is no. After a scan prints, and only when both your input and output are a terminal, the CLI may ask once whether to share a summary with CloudWise. It prints exactly what it would send before it asks: the CLI version, whether the scan ran in the CLI or MCP, the number of findings, the estimated monthly savings and the number of checks run. Never account IDs, resource IDs or names, regions, ARNs or tags.

Two further, separate yeses, asked only at that interactive prompt and only if you type an email address: "please email me about this report" (nothing from the report is uploaded; you can produce it yourself with --format markdown) and "tell me when new checks land" (marketing email; we confirm by reply before adding you to anything, and you can withdraw consent at any time by replying to or emailing cloudwise@cloudcostwise.io). Answer once and it does not ask again on that machine.

cloudcostwise share --status       # what is set, and whether a summary is saved and was shared
cloudcostwise share --last         # show the last scan's summary; send it only if you type y
cloudcostwise share --off          # never ask, never send by itself (unless CLOUDCOSTWISE_SHARE=yes is set); also deletes the saved summary
cloudcostwise share --on           # send a summary after each scan
cloudcostwise share --reset        # forget the answer and ask once more

The last scan's summary. After every scan, in the CLI or through MCP (never a demo), the same fields the summary carries are saved in ~/.config/cloudcostwise/last-summary.json, with the time they were saved, whether a send was attempted, and whether CloudWise confirmed it. Nothing else is in it: no identifiers, and --anonymize or your exclude list change it only as they change the summary (excluded findings are not counted). The file never leaves your machine by itself. cloudcostwise share --last reads it, shows you exactly what would be sent and sends it only if you type y, then offers the same optional email questions. It runs only in a terminal where you can type, has no option that answers for you, and tries to send each summary at most once: a failed attempt is not retried (run a new scan to share again), and a summary already sent because of your setting counts too. Every send of a saved summary first records the attempt in the file; if it cannot, nothing is sent. This is how you share a scan you ran through an AI assistant. share --off deletes the file; the next scan saves a new one, which still goes nowhere unless you run share --last and type y, or CLOUDCOSTWISE_SHARE=yes is set in the environment (it wins over share.json). A failure to write the file never fails a scan.

Without a terminal (a pipe, CI, a script) nothing is asked and nothing is sent unless you set CLOUDCOSTWISE_SHARE=yes (or no) yourself, or write ~/.config/cloudcostwise/share.json. Those settings carry the summary only (the CLI version, finding count, estimated savings and checks run, plus whether the scan came from the CLI or MCP), never an email address. The MCP server never prompts, its scan tool has no sharing parameter, and it sends only when one of those settings says yes. A failed or slow connection is ignored: the CLI waits about 3 seconds at most, after the results are printed, and the MCP server waits as long before it returns the scan result, so it can say whether the summary was sent. CLOUDCOSTWISE_SHARE_URL sends the summary to a test server instead of CloudWise, and is accepted only for http(s)://localhost, http(s)://127.0.0.1 and https://api-staging.cloudcostwise.io (anything else is refused and nothing is sent).

How the numbers are counted

Each finding shows an estimated monthly saving. Advisory waste types, ones CloudWise could not validate against a real AWS resource, are listed but never added to the total.

For consultancies and MSPs

The partner licence runs on your own machine like this tool: the other 26 service checks, one scan across every client account, and a client report under your firm's name. One price per firm, unlimited client accounts: https://cloudcostwise.io/partners?utm_source=cloudcostwise&utm_medium=readme.

What the hosted product adds

The other 26 service checks (Glue, ECS, Step Functions, Backup, CloudFront, commitments and more), history and trends, alerts, and safe automated fixes: https://cloudcostwise.io/connect?utm_source=cloudcostwise&utm_medium=cli.

Tell us where it's wrong

A false positive, a miss, or a dollar figure that looks off: post it in issue #1, or email cloudwise@cloudcostwise.io if you'd rather not post in public. The waste types and counts from your scan are enough. Leave out account IDs and resource names. Every report gets a reply, and a confirmed false positive gets fixed in the next release.

License

Open source under the Apache License 2.0 (see LICENSE.md). 0.1.18 and later are Apache-2.0. 0.1.17 and earlier are FSL-1.1-ALv2 (each becomes Apache-2.0 two years after it ships).

How we know it's right

See VALIDATION.md: the validation level of every waste type this tool reports, from L0 (unit-tested) to L2 (fired on a real AWS resource and stayed silent on a healthy twin) and beyond.

Available Tools

4 tools
explain_findingA
Read-onlyIdempotent

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.

Inputs: finding_id (required). Returns: result

fix_guidanceA
Read-onlyIdempotent

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.

Inputs: finding_id (required). Returns: result

list_findingsB
Read-onlyIdempotent

List findings from the last scan, with ids, optionally filtered by waste type or a minimum monthly saving in USD.

Inputs: waste_type, min_monthly_savings. Returns: result

scanA
Read-onlyIdempotent

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.

Inputs: demo, profile, regions, include_cost_explorer. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 4 tools

    Disambiguation4/5

    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.

    Naming Consistency3/5

    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.

    Tool Count5/5

    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.

    Completeness4/5

    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.

    Maintenance

    ActivityActive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      A
      maintenance
      Enables AI assistants to analyze AWS cloud costs, audit for waste, monitor budgets, and generate FinOps reports using natural language across multiple AWS profiles and regions, while keeping credentials on the local machine.
      -
    • F
      license
      Not graded
      quality
      A
      maintenance
      Enables AI assistants to analyze AWS cloud costs, audit for waste such as idle EC2 instances and unattached volumes, and check budget status through natural language. Runs locally against existing AWS CLI profiles, allowing read-only queries across multiple accounts and regions while credentials stay on the user's machine.
      -
    • F
      license
      Not graded
      quality
      A
      maintenance
      Enables AI assistants to analyze AWS cloud costs, audit for waste such as stopped EC2 instances and unattached EBS volumes, monitor budgets, and query multi-profile and multi-region cost data using natural language. It runs locally and uses existing AWS CLI profiles so credentials remain on the user's machine.
      -
    • F
      license
      Not graded
      quality
      A
      maintenance
      Enables AI assistants to query AWS cost and usage data by tags, time ranges, and service groupings, audit accounts for wasted resources like stopped EC2 instances and unattached EBS volumes, and monitor budget status across multiple CLI profiles and regions using natural language. All credentials stay on the local machine, with read-only access to AWS APIs.
      -