Multimodal MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Log level (default INFO). | |
| ALLOW_MKDIR | No | Allow mkdir (default false). | |
| MCP_TEMP_DIR | No | Temporary directory (default system temp dir). | |
| OPENAI_ORG_ID | No | OpenAI organization ID. | |
| OPENAI_API_KEY | Yes | Your OpenAI API key. | |
| OPENAI_PROJECT | No | OpenAI project ID. | |
| MAX_INPUT_BYTES | No | Maximum input bytes (default 25MB). | |
| OPENAI_BASE_URL | No | Base URL for OpenAI API. | |
| MAX_OUTPUT_BYTES | No | Maximum output bytes (default 25MB). | |
| OPENAI_MODEL_STT | No | Model for speech-to-text. | |
| OPENAI_MODEL_TTS | No | Model for text-to-speech. | |
| ENABLE_REMOTE_URLS | No | Enable remote URLs (default false). | |
| OPENAI_MODEL_IMAGE | No | Model for image generation. | |
| ALLOW_INSECURE_HTTP | No | Allow insecure HTTP (default false). | |
| OPENAI_MODEL_VISION | No | Model for vision tasks. | |
| OPENAI_MODEL_IMAGE_EDIT | No | Model for image editing. | |
| ENABLE_PRESIGNED_UPLOADS | No | Enable presigned uploads (default false). | |
| OPENAI_MODEL_AUDIO_ANALYZE | No | Model for audio analysis. | |
| OPENAI_MODEL_AUDIO_TRANSFORM | No | Model for audio transformation. |
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
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {
"tasks": {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
},
"prompts": {
"get": {}
},
"resources": {
"read": {}
}
}
}
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| image_generateC | Generate an image from a prompt and write it to the output reference. |
| image_analyzeC | Analyze an image and return text or schema-validated JSON. |
| image_editC | Edit or inpaint an image and write the result to the output reference. |
| image_extractC | Extract structured data from an image with schema validation. |
| image_to_specC | Convert an image into a structured textual spec. |
| audio_transcribeC | Transcribe audio to text and optionally write the transcript to a file. |
| audio_analyzeC | Analyze audio content and return text or schema-validated JSON. |
| audio_transformC | Transform speech audio based on an instruction and write output audio. |
| audio_ttsC | Generate speech audio from text and write it to the output reference. |
| multimodal_chainC | Execute a deterministic sequence of multimodal steps. |
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 10 tools
Each tool has a clearly distinct purpose within its modality (audio or image). The audio tools cover analysis, transcription, transformation, and TTS without overlap, and the image tools cover analysis, editing, extraction, generation, and spec conversion. The multimodal_chain tool is unique.
Tool names follow a consistent pattern: modality_verb (e.g., audio_analyze, image_generate). All use snake_case with clear, descriptive verbs. The naming is predictable and easy to understand.
10 tools is well-scoped for a multimodal server covering audio and image operations. Each tool earns its place, covering common tasks without being excessive or sparse.
The tool surface is largely complete for audio and image modalities, including analysis, generation, transformation, and extraction. A minor gap is the lack of a standalone audio extraction tool (though audio_analyze can handle it), and video is not covered, but that may be out of scope.