Bench Studio MCP Server
by inematds
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Port override used when starting the studio (e.g. PORT=8790 BENCH_API_PORT=8790 BENCH_WEB_PORT=5201 npm run dev). | |
| FAL_KEY | No | API key for fal.ai (37 models, billed in dollars with live pricing). | |
| KIE_API_KEY | No | API key for kie.ai (4 models, billed in credits). | |
| AGNES_API_KEY | No | API key for Agnes AI (4 models, zero cost). | |
| BENCH_API_HOST | No | Host the local API binds to. Defaults to loopback; setting to 0.0.0.0 is an opt-out that exposes the endpoint that writes files and spends money. | 127.0.0.1 |
| BENCH_API_PORT | No | Port for the local API (default 8787). | 8787 |
| BENCH_PASSWORD | No | Optional password. When set, the API requires a session. Stored as a scrypt hash. Set via `npm run set-password`. | |
| BENCH_WEB_PORT | No | Port for the web interface (default 5200). | 5200 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues