Token Runway
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GH_TOKEN | No | GitHub token with Copilot permissions, alternative to authenticating via the GitHub CLI (gh auth login). | |
| GITHUB_TOKEN | No | GitHub token with Copilot permissions, alternative to GH_TOKEN or authenticating via the GitHub CLI (gh auth login). | |
| OPENAI_API_KEY | No | OpenAI API key used to track model tier access and validate the key. | |
| CLAUDE_CODE_TOKEN | No | OAuth token for Anthropic Claude, used for manual/headless/CI environments when ~/.claude/ credentials are not available. | |
| OPENROUTER_API_KEY | No | OpenRouter API key used to track credit limits, spend balance, and rate limit intervals. |
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 | {} |
| prompts | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_runwayA | Inspect current AI provider rate-limit windows, quota utilization percentages, remaining capacity, and reset countdowns across Claude, Gemini, Antigravity, GitHub Copilot, Colab, OpenRouter, and OpenAI. Note: This reflects provider quota windows and rate limits, not session token counts. |
| assess_actionB | Meta-cognitive evaluation of whether a proposed action (e.g. running multiple parallel subagents, reading massive files, or continuous test loops) is justified given current remaining provider quotas and reset timers. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| runway_governance | Self-governance guidelines for operating under token rate-limits and quotas. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Live Token Runway Telemetry | Real-time snapshot of remaining limits and countdowns across all providers. |
TDQS
Scored across 2 tools
The two tools have clearly distinct roles: check_runway retrieves quota/rate-limit data, while assess_action performs a judgment about whether a proposed action is justified. An agent should not confuse data inspection with meta-cognitive assessment.
Both names follow a consistent snake_case verb_noun pattern: check_runway and assess_action. The verbs differ but the convention is predictable and readable.
Two tools is thin for a server, even a narrowly scoped one. The pair covers inspection and assessment, but additional operations such as listing providers or comparing options could reasonably earn a place.
The surface covers the core lifecycle of checking current runway and assessing proposed actions against it. Minor gaps exist around historical trends, threshold configuration, or provider comparison, but agents can work around them.