AgentScope Media MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGENTSCOPE_API_KEY | Yes | Model API Key provided via the environment variable of the launched process; required for generation requests. Without a key the server can still initialize and list tools, but media calls return a configuration error. | |
| AGENTSCOPE_READ_TIMEOUT | No | HTTP read timeout in seconds. | 180 |
| AGENTSCOPE_MEDIA_BASE_URL | No | Base URL for the AgentScope media API. | https://platform.agentscope.io/api/v1 |
| AGENTSCOPE_CONNECT_TIMEOUT | No | HTTP connect timeout in seconds. | 15 |
| AGENTSCOPE_HTTP_CONCURRENCY | No | Number of simultaneous HTTP requests (not the number of upstream running video tasks). | 4 |
| AGENTSCOPE_UPLOAD_MAX_BYTES | No | Maximum upload size in bytes (default 10 MiB). | 10485760 |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_modelsB | List all nine configured models; no credentials or network access required. |
| synthesize_speechC | Synthesize speech. Supply a voice ID supported by the chosen model; none is guessed. |
| generate_imageC | Generate an image with qwen-image-3.0. Optional size uses width*height syntax. |
| edit_imageC | Edit reference images using qwen-image-3.0 and public image URLs. |
| transcribe_audioC | Transcribe a public audio URL using qwen-audio-3.0-asr-flash. |
| generate_videoA | Submit video generation; query task_id later. i2v needs image_url; r2v needs 1–9 reference_urls. Wan text-only mapping passed one smoke test; other modes are unverified. Omit optional parameters to use upstream defaults. |
| edit_videoC | Submit HappyHorse video editing with up to five reference images; returns task_id. |
| get_taskB | Query an upstream task using the same API Key. Keep polling explicitly at intervals; pending/running is not generation success. UNKNOWN may mean the task expired. |
| upload_mediaA | Upload base64 image/audio/video data (default decoded limit 10 MiB). Returns media URLs. Prefer existing public URLs for large files; local paths are not accepted. |
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 9 tools
Each tool targets a distinct resource+action (models, image gen/edit, video gen/edit, TTS, ASR, upload, task polling). The generate_image/edit_image and generate_video/edit_video pairs could superficially be confused, but descriptions clarify the difference (from-scratch vs reference-based).
All nine tools follow a consistent snake_case verb_noun pattern (list_models, generate_image, edit_video, synthesize_speech, transcribe_audio, get_task, upload_media). No mixed conventions.
Nine tools is well-scoped for a media generation/editing server, with one tool per major capability plus task polling and media upload. No redundancy or dead weight.
Surface covers the full media lifecycle: generation, editing, upload, transcription, TTS, and async task polling. Minor gaps remain — no way to discover valid voice IDs (required by synthesize_speech but 'none is guessed'), and no task cancel/list operations.