@runapi.ai/runway-aleph-mcp
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RUNAPI_API_KEY | No | Your RunAPI API key. Alternatively, can be set in ~/.config/runapi/config.json. |
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
} |
| logging | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| loginA | Authenticate RunAPI by opening a browser PKCE login flow and saving the API key to ~/.config/runapi/config.json. |
| get_taskB | Fetch the current status and latest result payload for a runway-aleph task. |
| check_pricingB | Look up RunAPI pricing for the runway-aleph model line. |
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 3 tools
The three tools target clearly distinct concerns: pricing lookup, task status retrieval, and authentication. There is no plausible overlap or misselection risk between them.
check_pricing and get_task follow a consistent snake_case verb_noun pattern, and login is also lowercase snake_case, though it drops the verb_noun structure. Minor deviation but overall coherent and predictable.
Three tools is thin for a model-inference service; the surface covers auth, pricing, and status polling but feels incomplete for the apparent scope. It would be reasonable only if task submission lives in a companion server.
There is no tool to create or submit a runway-aleph task, so an agent can check pricing, authenticate, and poll a task but cannot actually start one. This is a significant lifecycle gap that would cause agent failures.