Media Context MCP
by danny2708
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MEDIA_MCP_VISION_MODEL | No | Vision model to use (e.g., 'Qwen/Qwen2.5-VL-7B-Instruct'). | |
| MEDIA_MCP_ALLOWED_ROOTS | Yes | List of allowed root directories separated by ';' on Windows or ':' elsewhere. This is required to set the workspace sandbox. | |
| MEDIA_MCP_VISION_API_KEY | No | API key for the vision provider. | |
| MEDIA_MCP_VISION_BASE_URL | No | Base URL for an OpenAI-compatible vision endpoint. If not set, uses the provider's preset base URL. | |
| MEDIA_MCP_VISION_PROVIDER | No | Vision provider preset (e.g., 'huggingface'). Optional. If not set, cloud vision is not used. | |
| MEDIA_MCP_SEND_OCR_TO_CLOUD | No | Set to 'true' to forward OCR text to cloud vision. Defaults to false. | false |
| MEDIA_MCP_ALLOW_CLOUD_VISION | No | Set to 'true' to allow sending media to cloud vision. Defaults to false. | false |
| MEDIA_MCP_VISION_FALLBACK_MODELS | No | Comma-separated list of fallback vision models. |
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
ActivitySlowing
ResponsivenessNo issues