tokencost-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| tokencost_get_model_pricingA | Get pricing details for a specific LLM model. Args:
Returns: Model pricing details including input/output costs per 1M tokens, context window, and max output. Returns an error message if the model is not found, with suggestions for similar models. Examples:
|
| tokencost_compare_modelsA | Compare pricing across multiple LLM models side by side. Args:
Returns: Side-by-side comparison table with input/output costs, context windows, and relative cost differences. Examples:
|
| tokencost_estimate_costA | Calculate the cost for a specific number of input and output tokens with a given model. Args:
Returns: Cost breakdown with input cost, output cost, and total cost in USD. Examples:
|
| tokencost_find_cheapestA | Find the cheapest LLM models, optionally filtered by provider or minimum context window. Args:
Returns: Ranked list of cheapest models with pricing details. Examples:
|
| tokencost_list_modelsA | List all available LLM models with pricing data, optionally filtered by provider. Args:
Returns: List of all models with IDs, names, and providers. Use model IDs with other tools. Examples:
|
| tokencost_list_providersA | List all LLM providers with model counts and pricing ranges. Returns: All providers with the number of models and pricing range for each. |
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 6 tools
Each tool has a clearly distinct purpose with no overlap: compare_models for side-by-side comparisons, estimate_cost for specific token calculations, find_cheapest for budget optimization, get_model_pricing for detailed lookups, list_models for catalog browsing, and list_providers for provider overview. The descriptions clearly differentiate their functions, eliminating any confusion about which tool to use for a given task.
All tools follow a perfect verb_noun pattern with the 'tokencost_' prefix: compare_models, estimate_cost, find_cheapest, get_model_pricing, list_models, and list_providers. The naming is completely consistent, using descriptive verbs that accurately reflect each tool's function, making the set highly predictable and easy to navigate.
Six tools is an ideal number for this server's purpose of LLM cost analysis. Each tool serves a distinct, valuable function in the workflow—from browsing models and providers to detailed comparisons and cost estimations—without any redundancy. The count is well-scoped, covering all essential operations without being overwhelming or insufficient for the domain.
The tool set provides complete coverage for LLM cost analysis: list_providers and list_models for discovery, get_model_pricing for detailed lookups, estimate_cost for calculations, compare_models for side-by-side analysis, and find_cheapest for optimization. There are no obvious gaps; agents can perform all typical cost-related tasks from exploration to decision-making without dead ends.