awslabs.aws-pricing-mcp-server

What it is and what it does

This is an MCP (Model Context Protocol) server that bridges AWS pricing data to AI assistants and other MCP clients. It wraps the AWS Pricing API, allowing natural-language queries about service costs, region-by-region comparisons, and bulk pricing downloads. The server also analyzes infrastructure code (CDK, Terraform) to identify AWS services and estimate costs, and generates detailed cost reports with usage scenarios and optimization suggestions.

It runs as a standalone process that your MCP client (Kiro, Cursor, VS Code, or Docker) connects to. Authentication uses standard AWS credentials with pricing:* IAM permissions. All pricing API calls are free. The package depends on boto3 for AWS API access, pydantic for data validation, mcp for protocol handling, and loguru for logging.

Use it for:

• Query AWS pricing in plain English (e.g., 'What's the cheapest EC2 instance type in us-west-2?') without learning filter syntax.
• Compare service costs across multiple AWS regions in a single request to identify cost-optimal deployment locations.
• Scan existing CDK or Terraform projects to automatically discover AWS services and estimate infrastructure costs.
• Generate detailed cost reports with unit pricing breakdowns and usage scenarios for budget planning and stakeholder communication.
• Get cost-optimization recommendations aligned with AWS Well-Architected Framework principles for existing architectures.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

An MCP server that exposes AWS pricing data and cost analysis tools to AI assistants and MCP clients, enabling natural-language queries about AWS service costs, multi-region comparisons, and infrastructure cost estimation.

Yes. Active maintenance, no vulnerabilities, low install friction, and permissive licensing make it safe to adopt. Install it if you need to expose AWS pricing queries to an AI assistant or MCP client, or if you want to automate cost analysis of infrastructure code. The natural-language interface and bulk data access are genuine conveniences over direct API calls. Caveat: the package itself cannot guarantee AI assistants will always construct filters correctly or identify the absolute cheapest options—human review of recommendations is prudent for cost-critical decisions.

Install

awslabs-aws-pricing-mcp-server on PyPI

pip install awslabs-aws-pricing-mcp-server

uv add awslabs-aws-pricing-mcp-server

poetry add awslabs-aws-pricing-mcp-server

Installing awslabs.aws-pricing-mcp-server

Before you install

Low friction: pure Python wheel with 7 runtime dependencies (boto3, loguru, mcp, pydantic, pytest-asyncio, pytest, typing-extensions). Active maintenance—released 4 days ago with 9598 repository stars and no known vulnerabilities.

License in practice

Apache-2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most deployment contexts.

Quickstart

# Install via uv
uvx awslabs.aws-pricing-mcp-server@latest

# Configure in MCP client (e.g., ~/.kiro/settings/mcp.json):
# {
#   "mcpServers": {
#     "awslabs.aws-pricing-mcp-server": {
#       "command": "uvx",
#       "args": ["awslabs.aws-pricing-mcp-server@latest"],
#       "env": {
#         "AWS_PROFILE": "default",
#         "AWS_REGION": "us-east-1"
#       }
#     }
#   }
# }

Requires Python >=3.10, AWS credentials configured with pricing:* IAM permissions, and an MCP-compatible client (Kiro, Cursor, VS Code, or Docker).

Verify before relying

• Whether the package's cost-optimization recommendations are consistently aligned with AWS Well-Architected Framework guidance or if they require manual review.
• Accuracy and freshness guarantees for real-time pricing data—whether updates lag behind AWS pricing changes and by how much.
• Whether infrastructure scanning (CDK/Terraform) correctly identifies all AWS service configurations or has known blind spots.

Package facts

Evidence: awslabs_aws_pricing_mcp_server-1.0.34-py3-none-any.whl

Tags

More Internet packages

Further reading