Cost Management MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CACHE_TTL | No | Cache time-to-live in seconds | 3600 |
| LOG_LEVEL | No | Log verbosity (debug/info/warn/error) | info |
| REDIS_URL | No | Redis connection URL (Required if CACHE_TYPE is redis) | |
| AWS_REGION | No | AWS region (Required for AWS cost tracking). Cost Explorer only works in us-east-1. | us-east-1 |
| CACHE_TYPE | No | Cache backend (memory/redis) | memory |
| OPENAI_API_KEY | No | OpenAI API key (Required for OpenAI cost tracking) | |
| MCP_SERVER_PORT | No | Server port | 3000 |
| ANTHROPIC_API_KEY | No | Anthropic Admin API key (starts with sk-ant-admin...) (Required for Anthropic cost tracking) | |
| AWS_ACCESS_KEY_ID | No | AWS access key (Required for AWS cost tracking) | |
| AWS_SECRET_ACCESS_KEY | No | AWS secret key (Required for AWS cost tracking) | |
| GCP_BILLING_ACCOUNT_ID | No | Your GCP billing account ID | |
| GOOGLE_APPLICATION_CREDENTIALS | No | Path to your GCP service account JSON file |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| cost_getC | Get cost data for a specific provider and time period |
| provider_listB | List all configured providers and their status |
| provider_balanceB | Check remaining balance or credits for a provider |
| openai_costsB | Get detailed OpenAI costs with model breakdown and token usage |
| anthropic_costsB | Get detailed Anthropic costs with model breakdown and token usage |
| aws_costsC | Get detailed AWS costs with service breakdown and optimization tips |
| provider_compareB | Compare costs across all configured providers |
| cost_trendsC | Analyze cost trends over time with insights |
| cost_breakdownC | Get detailed cost breakdown by multiple dimensions |
| cost_periodsC | Compare costs between two time periods |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
There is significant overlap between tools, particularly 'cost_breakdown', 'cost_get', 'cost_periods', and 'cost_trends', which all seem to retrieve and analyze cost data with subtle distinctions. However, provider-specific tools like 'anthropic_costs' and 'openai_costs' are clearly distinct, and descriptions help differentiate some overlaps, preventing complete confusion.
The naming follows a consistent snake_case pattern throughout, with most tools using a clear 'provider_action' or 'cost_action' structure. Minor deviations exist, such as 'cost_get' using a generic verb while others like 'cost_breakdown' are more descriptive, but overall the naming is predictable and readable.
With 10 tools, the count is well-scoped for a cost management server covering multiple providers and analysis dimensions. Each tool appears to serve a specific purpose, such as provider-specific costs, comparisons, and trend analysis, making the set comprehensive without being overwhelming.
The tool set covers core cost management workflows, including retrieving costs by provider, comparing providers and periods, analyzing trends, and checking balances. Minor gaps might include operations for setting budgets or configuring providers, but agents can likely work around these with the available tools for monitoring and analysis.