MCP servers · albaker-group

Cloudprice MCP server for multi-cloud and LLM pricing

An MCP server that gives AI assistants list prices across AWS, Azure, GCP and OCI, plus LLM token prices, with cost comparison and FinOps tools.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

Cloudprice is an MCP server that lets AI assistants query list prices for AWS, Azure, GCP and OCI, and token prices for about 2,300 LLM model and provider combinations. Its catalogue is refreshed weekly from the providers' public pricing APIs and archived, so price history and recent LLM price changes can be queried. It exposes 39 tools covering commitment break-even, three-year total cost of ownership, egress comparison, carbon estimates and FOCUS 1.3 export.

It is suited to questions such as comparing instance or GPU prices across clouds, finding the break-even point between on-demand, Savings Plans and reserved instances, and comparing egress costs. It also covers choosing between a hosted LLM API and self-hosting, estimating the cost of running an AI agent on different platforms, tracking model retirements, and analysing a cloud billing export to find cost drivers, anomalies and untagged spend.

No cloud account or API keys are needed for pricing queries. It installs through uvx or pip and requires Python 3.10 or later; the doctor command reports configuration problems. Bill and deployment analysis tools read a local FOCUS CSV (.csv or .csv.gz up to 500 MB) or Terraform JSON on the user's machine. Only the tool's summary is returned to the assistant, and each answer lists honest_gaps, the aspects the tool does not model.

Limitations and requirements

Requires Python 3.10 or later. Nine tools read files on the local machine and cannot be called from hosted deployments of the server. Bill files must be .csv or .csv.gz and no larger than 500 MB. Prices are list prices from the public catalogue, and answers list the aspects the tool does not model.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    Cloudprice

    Multi-cloud + LLM pricing for AI agents: AWS/Azure/GCP/OCI, RI break-even, TCO, price history.

    v0.29.0
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
cloudflare

Cloudflare MCP servers

Cloudflare's hosted MCP servers for its products: documentation search, sandbox containers, browser rendering, Radar internet data, logs and analytics, Workers and more.

4.5K GitHub starsCloud & DevOpsSoftware development
Updated 18 Nov 2026
MCP servers
neondatabase

Neon MCP Server (Postgres)

Neon's MCP server for managing Neon Postgres in plain language: create projects and branches, run queries and prepare schema migrations from your editor.

663 GitHub starsData & databasesSoftware development
Updated 18 Nov 2026
MCP servers
microsoft

Playwright MCP (browser automation)

Microsoft's MCP server that lets an AI assistant open web pages, click, type and read them through a real browser, using the page structure instead of screenshots.

39.6K GitHub starsTesting & QAWeb, search & browser
Updated 18 Nov 2026
MCP servers
supabase-community

Supabase MCP Server

Supabase's MCP server that connects an AI assistant to your Supabase project to design tables, run queries, read configuration and look up documentation.

Data & databasesSoftware development
Updated 18 Nov 2026
Cloudprice MCP server for multi-cloud and LLM pricing | AI Gate Discover