Opencloudcosts Mcp
@x7even
About Opencloudcosts Mcp
Anchor AI FinOps to real, live cloud pricing. Multi-cloud MCP server for AWS, GCP & Azure — public list prices and enterprise negotiated rates (Reserved Instances, Savings Plans, CUDs, EDPs). No credentials needed to get started.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"cloudcost": {
"command": "opencloudcosts",
"env": {
"OCC_GCP_API_KEY": "your-gcp-api-key",
"AWS_ACCESS_KEY_ID": "your-aws-key-id",
"AWS_SECRET_ACCESS_KEY": "your-aws-secret",
"OCC_AWS_ENABLE_COST_EXPLORER": "true",
"OCC_GCP_BILLING_ACCOUNT_ID": "012345-567890-ABCDEF"
}
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Opencloudcosts Mcp?
Opencloudcosts Mcp is an MCP server that gives AI assistants live, structured access to AWS, GCP, and Azure pricing via 16 tools. It replaces static training data with real-time provider API calls, enabling accurate, account-specific cost answers for multi-cloud workloads.
How to use Opencloudcosts Mcp?
Install via PyPI or download a GitHub release binary, configure the required environment variables for credential-based access (e.g., OCC_GCP_API_KEY, OCC_AWS_ENABLE_COST_EXPLORER), and connect the server to your MCP-capable AI assistant. The model then calls any of the 16 tools to retrieve pricing, compare clouds, or estimate unit economics.
Key features of Opencloudcosts Mcp
- 16 MCP tools for pricing, FinOps, discovery, and cache management
- Live pricing from AWS, GCP, and Azure provider APIs (not training data)
- Multi-cloud BOM comparison with 8 concurrent provider calls
- Multi-region fan-out with up to 32 goroutines
- Effective/contracted rate support (RI, SP, EDP, CUD) where credentials are provided
- HTTP service mode with bearer auth, rate limiting, and Kubernetes-ready probes
Use cases of Opencloudcosts Mcp
- Compare a full multi-resource workload across AWS, GCP, and Azure simultaneously
- Find the cheapest region for a given instance type across all available regions
- Estimate unit economics (cost per user, per request) for a planned architecture
- Retrieve post-discount effective rates from Reserved Instances or Savings Plans
- Get a structured bill of materials (BOM) estimate on-demand vs. committed terms
Basic information
More Cloud & Infrastructure MCP servers
GCP MCP
eniayomiA Model Context Protocol (MCP) server that enables AI assistants like Claude to interact with your Google Cloud Platform environment. This allows for natural language querying and management of your GCP resources during conversations.
K8s MCP Server
alexei-ledK8s-mcp-server is a Model Context Protocol (MCP) server that enables AI assistants like Claude to securely execute Kubernetes commands. It provides a bridge between language models and essential Kubernetes CLI tools including kubectl, helm, istioctl, and argocd, allowing AI syste

Nippy
NippyNippy is drag-and-drop hosting (nippy.host) with an MCP server: connect it and your assistant can publish HTML, folders of photos, or file downloads to a live *.nippy.site URL — and keep editing the site in place at the
Supabase MCP Server
supabase-communityConnect Supabase to your AI assistants
Run Model Context Protocol (MCP) servers with AWS Lambda
awslabsRun existing Model Context Protocol (MCP) stdio-based servers in AWS Lambda functions
Comments