Skip to main content
mcpSource-backed

AWS FinOps MCP Server

Read-only AWS FinOps MCP server that lets Claude query Cost Explorer cost and usage data, compare AWS CLI profiles, filter by tags or dimensions, check AWS Budgets, and audit for stopped EC2 instances, unattached EBS volumes, and unassociated Elastic IP addresses across selected regions.

Review first review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Source URLs
https://github.com/ravikiranvm/aws-finops-mcp-server/blob/main/README.md, https://github.com/ravikiranvm/aws-finops-mcp-server
Brand
AWS FinOps MCP Server
Brand domain
github.com
Safety notes
The reviewed MCP tools are annotated read-only and call AWS APIs for cost, budget, identity, EC2 instance, EBS volume, and Elastic IP inspection., Cost Explorer API calls can incur AWS charges; the upstream README notes get_cost makes Cost Explorer calls that are billed by AWS., all_profiles can query every locally configured AWS CLI profile, so use explicit profiles unless broad account comparison is approved., Cost, budget, stopped-instance, unattached-volume, and unassociated-EIP findings are advisory FinOps signals, not deletion instructions or guaranteed savings., AWS pricing, budget forecasts, tags, and resource state can be delayed, incomplete, or affected by account configuration.
Privacy notes
Results can expose AWS account IDs, profile names, service spend, usage dimensions, cost allocation tags, budget names, budget limits, forecasted spend, region names, instance IDs, instance types, EBS volume IDs and sizes, Elastic IP allocation IDs, and public IP addresses., AWS credentials stay in the local AWS CLI profile, but MCP client logs, model transcripts, generated reports, screenshots, and shared prompts can still reveal sensitive financial and infrastructure context., Restrict AWS profiles to least privilege, avoid long-lived static keys where possible, and do not paste access keys or secret keys into prompts or committed config files.
Author
Ravi Kiran Vallamkonda
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-06

Decision playbook

Review trust signals before you adopt

Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.

Compare context
Selected

0

Current score

63

Baseline

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Needs review

Confirm ownership and provenance before trusting install instructions.

  • Source link availableRequired

    Open the canonical repository and verify ownership.

    Done
  • Source provenance statusRequired

    Marked as source-backed.

    Done
  • Metadata reviewed

    No reviewed flag detected in metadata.

    Pending

Safety and privacy checks

Complete

Validate risk disclosures before installation or API wiring.

  • Safety notes presentRequired

    Review the listed safety guidance before running commands.

    Done
  • Privacy notes presentRequired

    Review data handling notes before connecting accounts or secrets.

    Done
  • Trust level risk gateRequired

    Trust level does not block evaluation.

    Done

Package and install checks

Needs review

Check package metadata and artifact integrity signals.

  • Install payload available

    Install or copy payload is available for review.

    Done
  • Package verification flag

    No package verification flag provided.

    Pending
  • Checksum metadata

    No checksum provided for downloaded artifact.

    Pending

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

  • Compare tray has multiple entries

    Add at least one more entry to compare trust differences.

    Pending
  • Baseline comparison available

    No baseline peer selected yet.

    Pending
  • Diverging trust signals identified

    No major trust-signal divergence found.

    Pending

Setup at a glance

CLI install

Copy-ready — paste the snippet to get started.

15 minutes

Adoption plan

Balanced adoption plan

Current risk score 24/100. Use staged verification before broader rollout.

Risk 24

Pre-adoption checks

Validate source and review signals before any execution.

  • Confirm source provenanceRequired

    Source URL/provenance metadata is present.

    Done
  • Confirm metadata review state

    No review metadata found; increase manual validation.

    Pending
  • Verify install payload

    Install/config payload exists and can be inspected.

    Done

Security checks

Confirm safety, privacy, and package integrity signals.

  • Review safety notesRequired

    Safety notes are present.

    Done
  • Review privacy notesRequired

    Privacy notes are present.

    Done
  • Verify package integrity metadata

    No package verification/checksum metadata.

    Pending

Rollout

Adopt in controlled steps based on the selected plan.

  • Run in isolated sandbox firstRequired

    Use a constrained sandbox and observe behavior across multiple tasks.

    Pending
  • Roll out graduallyRequired

    Roll out to a small cohort before wider usage.

    Pending
  • Set monitoring and fallback

    Define rollback path and monitor errors after adoption.

    Pending

Evidence readiness

Evidence readiness matrix · balanced

Missing required evidence: Metadata review. Risk score 31.

Risk 31

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Missing

Review metadata is missing.

Required in this preset

Safety notes

Present

Safety notes are present.

Required in this preset

Privacy notes

Present

Privacy notes are present.

Optional in this preset

Package integrity

Missing

Package integrity metadata is missing.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required gaps: Metadata review

Decision timeline

Decision timeline · balanced

Blocking gaps: Check metadata review status. Risk 28.

Risk 28

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is missing.

Pending

verify

Review safety notesRequired

Safety notes are available.

Done

verify

Review privacy notes

Privacy notes are available.

Done

verify

Validate package integrity metadata

Package integrity metadata is missing.

Pending

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

Blockers: Check metadata review status

Prerequisite readiness

Prerequisite readiness

5 prerequisites to line up before setup. Have accounts and credentials ready first. Includes a review or approval gate.

0/5 ready
Account & credentials1Install & runtime1Permissions & scopes1Review & approval1General115 minutes

Safety & privacy surface

Safety & privacy surface

5 safety and 3 privacy notes across 4 risk areas. Review closely: credentials & tokens, network access.

4 areas
  • SafetyGeneralThe reviewed MCP tools are annotated read-only and call AWS APIs for cost, budget, identity, EC2 instance, EBS volume, and Elastic IP inspection.
  • SafetyNetwork accessCost Explorer API calls can incur AWS charges; the upstream README notes get_cost makes Cost Explorer calls that are billed by AWS.
  • SafetyLocal filesall_profiles can query every locally configured AWS CLI profile, so use explicit profiles unless broad account comparison is approved.
  • SafetyGeneralCost, budget, stopped-instance, unattached-volume, and unassociated-EIP findings are advisory FinOps signals, not deletion instructions or guaranteed savings.
  • SafetyGeneralAWS pricing, budget forecasts, tags, and resource state can be delayed, incomplete, or affected by account configuration.
  • PrivacyLocal filesResults can expose AWS account IDs, profile names, service spend, usage dimensions, cost allocation tags, budget names, budget limits, forecasted spend, region names, instance IDs, instance types, EBS volume IDs and sizes, Elastic IP allocation IDs, and public IP addresses.
  • PrivacyCredentials & tokensAWS credentials stay in the local AWS CLI profile, but MCP client logs, model transcripts, generated reports, screenshots, and shared prompts can still reveal sensitive financial and infrastructure context.
  • PrivacyCredentials & tokensRestrict AWS profiles to least privilege, avoid long-lived static keys where possible, and do not paste access keys or secret keys into prompts or committed config files.

Safety notes

  • The reviewed MCP tools are annotated read-only and call AWS APIs for cost, budget, identity, EC2 instance, EBS volume, and Elastic IP inspection.
  • Cost Explorer API calls can incur AWS charges; the upstream README notes get_cost makes Cost Explorer calls that are billed by AWS.
  • all_profiles can query every locally configured AWS CLI profile, so use explicit profiles unless broad account comparison is approved.
  • Cost, budget, stopped-instance, unattached-volume, and unassociated-EIP findings are advisory FinOps signals, not deletion instructions or guaranteed savings.
  • AWS pricing, budget forecasts, tags, and resource state can be delayed, incomplete, or affected by account configuration.

Privacy notes

  • Results can expose AWS account IDs, profile names, service spend, usage dimensions, cost allocation tags, budget names, budget limits, forecasted spend, region names, instance IDs, instance types, EBS volume IDs and sizes, Elastic IP allocation IDs, and public IP addresses.
  • AWS credentials stay in the local AWS CLI profile, but MCP client logs, model transcripts, generated reports, screenshots, and shared prompts can still reveal sensitive financial and infrastructure context.
  • Restrict AWS profiles to least privilege, avoid long-lived static keys where possible, and do not paste access keys or secret keys into prompts or committed config files.

Prerequisites

  • Python 3.10 or newer and pipx, pip, or uv.
  • AWS CLI installed with one or more approved profiles.
  • IAM permissions for ce:GetCostAndUsage, budgets:ViewBudget, ec2:DescribeInstances, ec2:DescribeVolumes, ec2:DescribeAddresses, and sts:GetCallerIdentity.
  • Cost allocation tags activated in AWS when tag-based cost filtering is required.
  • Approval to query the selected AWS accounts, profiles, regions, tags, and cost dimensions.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
15 minutes
Difficulty
intermediate
Full copyable content
{
  "mcpServers": {
    "aws_finops": {
      "command": "aws-finops-mcp-server",
      "args": []
    }
  }
}

About this resource

Content

AWS FinOps MCP Server is a Python stdio MCP server for AWS cost analysis and read-only waste-audit workflows. It lets Claude query Cost Explorer for UnblendedCost data, group costs by AWS dimensions, filter by tags or dimensions, compare selected AWS CLI profiles, check AWS Budgets, and identify stopped EC2 instances, unattached EBS volumes, and unassociated Elastic IP addresses in specified regions.

The server runs locally and uses boto3 with the AWS CLI profiles already configured on the user's machine. The reviewed implementation exposes two read-only MCP tools: get_cost and run_finops_audit.

Source Review

These sources were reviewed on 2026-06-06. Prefer the live repository, README, PyPI metadata, Python package metadata, dependency file, MCP server implementation, helper implementation, and license file for current install commands, AWS permissions, tool behavior, API scope, and licensing.

Features

  • Python package aws-finops-mcp-server with the aws-finops-mcp-server console command.
  • Local stdio MCP transport.
  • get_cost tool for AWS Cost Explorer cost and usage data.
  • Date-range, last-N-days, tag, dimension, and group-by options for cost queries.
  • Multi-profile or all-profile cost comparison through local AWS CLI profiles.
  • run_finops_audit tool for stopped EC2 instances, unattached EBS volumes, unassociated Elastic IPs, and AWS Budgets status.
  • Read-only AWS API permission model documented in the README.
  • MIT license.

Installation

Install the package with pipx:

pipx install aws-finops-mcp-server

Configure a least-privilege AWS CLI profile, then add the MCP server:

{
  "mcpServers": {
    "aws_finops": {
      "command": "aws-finops-mcp-server",
      "args": []
    }
  }
}

Restart the MCP client and ask Claude for an approved profile, region, and date range. Use explicit profiles before enabling all-profile analysis.

Use Cases

  • Summarize current-month AWS spend by service for one approved profile.
  • Compare service costs across staging and production profiles for a specific date range.
  • Filter Cost Explorer results by cost allocation tags or AWS dimensions.
  • Check whether selected accounts are under, over, or forecasted to exceed AWS Budgets.
  • Audit approved regions for stopped EC2 instances, unattached EBS volumes, and unassociated Elastic IP addresses.
  • Draft a FinOps report that a human owner can verify against AWS Console or source billing data.

Safety and Privacy

AWS FinOps MCP Server is read-only in the reviewed implementation, but it still touches sensitive cloud financial and infrastructure metadata. Use an IAM role or profile with only the documented read permissions, prefer explicit profile and region arguments, and verify any savings recommendation before deleting or changing AWS resources.

Cost Explorer calls may be billed by AWS, and repeated broad queries across many profiles, dates, dimensions, or tags can create avoidable charges and noisy reports. Budget forecasts, tag filters, and resource state can also lag behind actual infrastructure changes.

Treat generated reports, model transcripts, screenshots, account IDs, profile names, cost data, budget names, resource IDs, public IP addresses, and tag values as sensitive FinOps data. Do not paste AWS access keys, secret keys, session tokens, or full local credential files into prompts or committed configuration.

Duplicate Check

Existing MCP content includes broader AWS and cloud infrastructure entries, but no AWS FinOps MCP Server, ravikiranvm/aws-finops-mcp-server, dedicated AWS Cost Explorer MCP, or FinOps-focused AWS cost-audit MCP entry was found in content/mcp, content/agents, content/guides, or content/skills. This entry is scoped to the read-only AWS FinOps cost, budget, and waste-audit server.

Source citations

Add this badge to your README

Show that AWS FinOps MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/mcp/aws-finops-mcp-server.svg)](https://heyclau.de/entry/mcp/aws-finops-mcp-server)

How it compares

AWS FinOps MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

3 trust signals differ across this comparison (Package trust, Source provenance, Submitter).

Field

Read-only AWS FinOps MCP server that lets Claude query Cost Explorer cost and usage data, compare AWS CLI profiles, filter by tags or dimensions, check AWS Budgets, and audit for stopped EC2 instances, unattached EBS volumes, and unassociated Elastic IP addresses across selected regions.

Open dossier

Official AWS Labs MCP server for AWS Billing and Cost Management that lets AI assistants analyze costs and usage, monitor budgets and anomalies, and surface Cost Optimizer, Savings Plans, and Reserved Instance recommendations.

Open dossier

Delega hosted MCP server that creates AWS cost estimates and shareable AWS Pricing Calculator links from natural language without leaving your AI client.

Open dossier

Comprehensive AWS cloud services integration for infrastructure management, deployment, and monitoring

Open dossier
Next steps
Trust
Review statusNot reviewedNot reviewedNot reviewedNot reviewed
Package trustDiffersPackage not verifiedPackage not verifiedPackage not verifiedPackage verified
Source provenanceDiffersSource-backedSource-backedSubmission linkedSource submissionNo submission link
SubmitterDiffersoktofeesh1jaso0n0818kiannidev
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
BrandAWS Labs logoAWS LabsAWS logoAWSAWS logoAWS
Categorymcpmcpmcpmcp
SourceSource-backedSource-backedSource-backedFirst-party
AuthorRavi Kiran VallamkondaAWS LabsDelegaAWS Labs
Added2026-06-062026-06-212026-06-142025-09-16
Platforms
Harness
Source repo
Safety notesThe reviewed MCP tools are annotated read-only and call AWS APIs for cost, budget, identity, EC2 instance, EBS volume, and Elastic IP inspection. Cost Explorer API calls can incur AWS charges; the upstream README notes get_cost makes Cost Explorer calls that are billed by AWS. all_profiles can query every locally configured AWS CLI profile, so use explicit profiles unless broad account comparison is approved. Cost, budget, stopped-instance, unattached-volume, and unassociated-EIP findings are advisory FinOps signals, not deletion instructions or guaranteed savings. AWS pricing, budget forecasts, tags, and resource state can be delayed, incomplete, or affected by account configuration.The provided tools read cost and usage data and recommendations; they do not purchase Savings Plans or Reserved Instances or otherwise modify your account. Grant least-privilege read access to the cost APIs. This server reads billing data with your AWS credentials; scope the profile to the intended account and run it only on a trusted host. Cost Explorer and some cost APIs charge per paid API request; broad or frequent queries can incur AWS costs, so scope time ranges and granularity deliberately.Cost estimates depend on list prices and assumptions; validate against current AWS Pricing Calculator before procurement. Shareable links may expose architecture assumptions; review before sending to external clients. This service complements, but does not replace, official AWS Cost Explorer or billing data. Do not treat MCP output as a binding financial commitment with AWS.Scope AWS credentials to the intended accounts, regions, and services because infrastructure actions can affect production resources.
Privacy notesResults can expose AWS account IDs, profile names, service spend, usage dimensions, cost allocation tags, budget names, budget limits, forecasted spend, region names, instance IDs, instance types, EBS volume IDs and sizes, Elastic IP allocation IDs, and public IP addresses. AWS credentials stay in the local AWS CLI profile, but MCP client logs, model transcripts, generated reports, screenshots, and shared prompts can still reveal sensitive financial and infrastructure context. Restrict AWS profiles to least privilege, avoid long-lived static keys where possible, and do not paste access keys or secret keys into prompts or committed config files.Cost, usage, budget, and account metadata — including linked-account identifiers and spend figures — can be returned to the model. Keep account identifiers, credentials, and spend details out of public prompts, issues, and screenshots, since billing data is sensitive business information.Architecture descriptions and service configurations you submit are processed by delega.ai to build estimates. Avoid including internal account IDs, credentials, or confidential deal terms in prompts unless policy allows. Shared calculator URLs may be visible to anyone with the link; distribute least-privilege versions.AWS resource names, configuration, metrics, logs, ARNs, and account metadata may be exposed through tool calls and responses.
Prerequisites
  • Python 3.10 or newer and pipx, pip, or uv.
  • AWS CLI installed with one or more approved profiles.
  • IAM permissions for ce:GetCostAndUsage, budgets:ViewBudget, ec2:DescribeInstances, ec2:DescribeVolumes, ec2:DescribeAddresses, and sts:GetCallerIdentity.
  • Cost allocation tags activated in AWS when tag-based cost filtering is required.
  • An AWS account with Billing and Cost Management access (Cost Explorer, Budgets, and related APIs enabled).
  • Python 3.10 or newer and `uv` / `uvx` installed (Astral) to run the package.
  • AWS credentials configured locally (for example via `aws configure` or `AWS_PROFILE`) with read permissions for the Cost Explorer, Budgets, Compute Optimizer, and related cost APIs.
  • An MCP client that supports stdio servers; the server runs locally on the same host as the client.
  • Claude Pro, Team, or Enterprise with Connectors support, or another MCP client with remote HTTP transport.
  • Basic familiarity with AWS services you want estimated (EC2, RDS, S3, Lambda, etc.).
  • Understanding that estimates are planning aids, not invoices or committed AWS quotes.
  • Internet access to reach calculator.delega.ai.
  • Python 3.8+ installed for running uvx commands
  • uv package manager installed (provides uvx command for running Python packages)
  • AWS account with active credentials and appropriate IAM permissions
  • AWS credentials configured via one of: IAM access keys (AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY), AWS profile (~/.aws/credentials), or IAM role (for EC2/ECS)
Install
pipx install aws-finops-mcp-server
uvx awslabs.billing-cost-management-mcp-server@latest
claude mcp add --transport http delega https://calculator.delega.ai/mcp
uvx awslabs.core-mcp-server@latest && claude mcp list
Config
{
  "mcpServers": {
    "aws_finops": {
      "command": "aws-finops-mcp-server",
      "args": [],
      "env": {
        "AWS_PROFILE": "<least-privilege-profile>",
        "AWS_REGION": "<default-region>"
      }
    }
  }
}
{
  "mcpServers": {
    "awslabs.billing-cost-management-mcp-server": {
      "command": "uvx",
      "args": ["awslabs.billing-cost-management-mcp-server@latest"],
      "env": {
        "AWS_PROFILE": "${AWS_PROFILE}",
        "AWS_REGION": "us-east-1",
        "FASTMCP_LOG_LEVEL": "ERROR"
      },
      "type": "stdio"
    }
  }
}
{
  "mcpServers": {
    "delega": {
      "url": "https://calculator.delega.ai/mcp",
      "type": "http"
    }
  }
}
{
  "mcpServers": {
    "aws": {
      "env": {
        "AWS_REGION": "${AWS_REGION:-us-east-1}",
        "AWS_PROFILE": "${AWS_PROFILE}",
        "FASTMCP_LOG_LEVEL": "${FASTMCP_LOG_LEVEL:-ERROR}"
      },
      "args": [
        "awslabs.core-mcp-server@latest"
      ],
      "command": "uvx",
      "type": "stdio"
    }
  }
}
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed
Open 4 picks in the interactive comparison tool

Related guides

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.