servers / aws-finops-mcp-server
aws-finops-mcp-server
communityunknownpythonunmaintainedhealthy
An MCP server for AWS FinOps to analyze costs and audit for savings.
01Tools · 2
How to read this: tool names here are observed from a live tools/list handshake. The Risk label is a heuristic inferred from the tool name (write/destructive verbs), not from executing the tool — a conservative guess, not a verified capability. We never escalate risk from a description. Found one that's wrong? Tell us — we fix on report.
| Tool | Risk | Side effects | Approval |
|---|---|---|---|
| run_finops_audit
Get FinOps Audit Report findings for your AWS CLI Profiles.
Each Audit Report includes:
Stopped EC2 Instances,
Un-attached EBS VOlumes,
Un-associated EIPs,
Budget Status for your one or more specified AWS profiles. Except the budget status, other resources are region specific.
Args:
List of AWS CLI profiles as strings.
List of AWS Regions as strings.
all_profiles: If True, use all available profiles; otherwise, use the specified profiles.
Returns:
Processed Audit data for specified CLI Profile and regions in JSON(dict) format with errors caught from APIs.
| write | true | unknown |
| get_cost
Get cost data for a specified AWS profile for a single defined period.
The period can be defined by 'time_range_days' (last N days including today)
OR by explicit 'start_date_iso' and 'end_date_iso'.
If 'start_date_iso' and 'end_date_iso' are provided, they take precedence.
If no period is defined, defaults to the current month to date.
Tags can be provided as a list of "Key=Value" strings to filter costs.
Dimensions can be provided as a list of "Key=Value" strings to filter costs by specific dimensions.
If no tags or dimensions are provided, all costs will be returned.
Grouping can be done by a specific dimension, default is "SERVICE".
Args:
profile_name: The AWS CLI profile name to use.
all_profiles: If True, use all available profiles; otherwise, use the specified profiles.
time_range_days: Optional. Number of days for the cost data (e.g., last 7 days).
start_date_iso: Optional. The start date of the period (inclusive) in YYYY-MM-DD format.
end_date_iso: Optional. The end date of the period (inclusive) in YYYY-MM-DD format.
tags: Optional. List of cost allocation tags (e.g., ["Team=DevOps", "Env=Prod"]).
dimensions: Optional. List of dimensions to filter costs by (e.g., ["REGION=us-east-1", "AZ=us-east-1a"]).
group_by: Optional. The dimension to group costs by (default is "SERVICE").
Returns:
Dict: Processed cost data for the specified period.
| read | false | unknown |
02Install & source
uvx aws-finops-mcp-server
uvxpip install aws-finops-mcp-server
pip- repohttps://github.com/ravikiranvm/aws-finops-mcp-server
- packagehttps://pypi.org/project/aws-finops-mcp-server
- homepagehttps://github.com/ravikiranvm/aws-finops-mcp-server
- licenseMIT
- adoption181 stars · 54 forks
05Provenance & freshness
sourcesPyPI [p4]
last_checked2026-08-16 07:46Z
next_check2026-09-15 07:46Z
cadenceevery 720h
verifiedhandshake:failed metadata:passed tools_list:passed handshake:passed metadata:passed metadata:passed metadata:passed
index_statusindex — 8 unique facts >= 5
06Badge
Add the “as seen on MCPExplorer” badge to your README.
[](https://mcpexplorer.com/servers/aws-finops-mcp-server)
Next step
This is one server. A loadout combines the right servers, governance, and proven plays for a whole job — assembled deliberately, not tool-dumped.
Explore loadouts →