MCP server for unified cost management across cloud providers
Cost Management MCP MCP server exists for a simple reason — assistants are far more useful when they can act on Cost Management MCP directly instead of describing what you should do. MCP server for unified cost management across cloud providers.
Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.
Once Cost Management MCP is connected, these are the calls the assistant has available:
Prerequisites — CI currently verifies Node.js 18.x, 20.x, 22.x, and 24.x. Node.js 20.x is the primary lane for coverage upload and representative build checksSteps — 4. Edit .env and add your credentials (see Provider Setup)cost_get — Retrieve cost data for specified providers and time periodsprovider_list — The provider_list tool exposed by this serverprovider_balance — Check remaining balance or credits (provider-specific). Note: Currently not implemented for most providersOpenAI — 1. Get API Key from OpenAI DashboardAnthropic — 1. Get Admin API Key from Anthropic ConsoleLogging — The Logging tool exposed by this serverCommands — The Commands tool exposed by this serverTesting — The Testing tool exposed by this serverSecurity — The Security tool exposed by this serverQuality — The Quality tool exposed by this serverYou will need 8 environment variables: AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_REGION, OPENAI_API_KEY, CACHE_TTL, LOG_LEVEL, ANTHROPIC_API_KEY, GOOGLE_APPLICATION_CREDENTIALS. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Cost Management MCP's toolset — Prerequisites, Steps, cost_get and 9 more — is a fair guide to whether it matches your workflow. It is maintained by knishioka; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Cost Management MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Prerequisites | CI currently verifies Node.js 18.x, 20.x, 22.x, and 24.x. Node.js 20.x is the primary lane for coverage upload and representative build checks. |
| Steps | 4. Edit .env and add your credentials (see [Provider Setup](#provider-setup)) |
| cost_get | Retrieve cost data for specified providers and time periods. |
| provider_list | The provider_list tool exposed by this server. |
| provider_balance | Check remaining balance or credits (provider-specific). _Note: Currently not implemented for most providers_ |
| OpenAI | 1. **Get API Key** from [OpenAI Dashboard](https://platform.openai.com/api-keys) |
| Anthropic | 1. **Get Admin API Key** from [Anthropic Console](https://console.anthropic.com/) |
| Logging | The Logging tool exposed by this server. |
| Commands | The Commands tool exposed by this server. |
| Testing | The Testing tool exposed by this server. |
| Security | The Security tool exposed by this server. |
| Quality | The Quality tool exposed by this server. |
| Variable | Description | Required |
|---|---|---|
| AWS_ACCESS_KEY_ID | Credential the server authenticates with. | Yes |
| AWS_SECRET_ACCESS_KEY | Credential the server authenticates with. | Yes |
| AWS_REGION | Configuration value read at startup. | Optional |
| OPENAI_API_KEY | Credential the server authenticates with. | Yes |
| CACHE_TTL | Configuration value read at startup. | Optional |
| LOG_LEVEL | Configuration value read at startup. | Optional |
| ANTHROPIC_API_KEY | Credential the server authenticates with. | Yes |
| GOOGLE_APPLICATION_CREDENTIALS | Configuration value read at startup. | Optional |
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.