TokenLens MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TOKENLENS_DATA_DIR | No | Path to a custom data directory containing pricing JSON files. | |
| TOKENLENS_DATA_URL | No | URL to fetch live pricing data from. Defaults to bundled local files if not set. Falls back to bundled data if unreachable. |
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 |
|---|---|
| compare_plansA | Rank all TokenLens plans by effective cost per 1M tokens. Useful when choosing between subscriptions and API access for a given model. |
| run_scenarioA | Calculate total monthly token usage and cost (API vs subscription) for a given usage pattern. Returns costs for all matching plans side-by-side. |
| break_evenA | Find the daily usage hours at which API cost equals a subscription price. Below this threshold, the API is cheaper; above it, the subscription wins. |
| recommend_planA | Get a single best-value plan recommendation for your usage profile. Considers whether a subscription or API access is cheaper, and whether token caps are sufficient. |
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 4 tools
Each tool has a clearly distinct purpose: comparing plan costs, simulating usage scenarios, computing break-even thresholds, and generating personalized recommendations. Their descriptions make the boundary between them obvious.
All tool names follow a consistent verb_noun pattern in snake_case: compare_plans, run_scenario, break_even, recommend_plan. No mixed styles or vague verbs.
With 4 tools, the server is well-scoped for its purpose of analyzing TokenLens plans. Each tool contributes a distinct analysis capability without redundancy.
The tool set covers all key aspects of plan selection: cost comparison, usage simulation, break-even analysis, and final recommendation. There are no obvious missing operations for the stated domain.