TokPort
Generate images and videos (GPT Image, Seedance, Kling, Wan, Qwen) with one API key.
我該用這個嗎
品質與安全性
發現項目（1）
- LOWTool 'get_pricing' description lacks action verb在 get_pricing 中
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"tokport": {
"url": "https://tokport.io/api/mcp"
}
}
}遠端端點
https://tokport.io/api/mcpstreamable-http它能做什麼
工具清單
工具（8）
🟡search_models(q, modality, task, available)
Search the model catalog. Returns ids, modality, tasks, pricing and links. Use before calling run_model or submit_job to pick a model id.
輸入結構描述
{
"type": "object",
"properties": {
"q": {
"type": "string",
"description": "Free-text query over id, name, vendor and tags"
},
"modality": {
"type": "string",
"description": "image or video",
"enum": [
"image",
"video"
]
},
"task": {
"type": "string",
"description": "text-to-image | image-to-image | text-to-video | image-to-video"
},
"available": {
"type": "boolean",
"description": "Only models live on the gateway"
}
}
}🟢get_model_schema(model)
Input parameters (name, type, allowed values, defaults) and output shape for every task a model supports.
輸入結構描述
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Model id, e.g. gpt-image-2"
}
},
"required": [
"model"
]
}🟢get_pricing(model)
Live price per image or per video clip for one model or all models.
輸入結構描述
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Model id; omit for all models"
}
}
}⚪run_model(model, input, task)
Run a model synchronously with the caller's API key. Images return URLs; videos are queued and this waits up to 60 s before returning the queue status instead.
輸入結構描述
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Model id"
},
"input": {
"type": "object",
"description": "Model input: prompt, size, n, image, seconds …",
"additionalProperties": true
},
"task": {
"type": "string",
"description": "Force the task kind (inferred otherwise)"
}
},
"required": [
"model",
"input"
]
}🟡submit_job(model, input, task, webhook, priority)
Queue a request and return its request_id immediately. Follow with check_job / get_job_result.
輸入結構描述
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Model id"
},
"input": {
"type": "object",
"additionalProperties": true
},
"task": {
"type": "string",
"description": "Force the task kind (inferred otherwise)"
},
"webhook": {
"type": "string",
"description": "Public http(s) URL to POST the result to"
},
"priority": {
"type": "string",
"description": "normal or low",
"enum": [
"normal",
"low"
]
}
},
"required": [
"model",
"input"
]
}🟢check_job(model, request_id, logs)
Status of a queued request (IN_QUEUE / IN_PROGRESS / COMPLETED / FAILED / CANCELLED) with position, logs and metrics.
輸入結構描述
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Model id"
},
"request_id": {
"type": "string",
"description": "req_… id"
},
"logs": {
"type": "boolean"
}
},
"required": [
"model",
"request_id"
]
}🟢get_job_result(model, request_id, timeout)
Result of a completed request; waits up to `timeout` seconds (max 60) when still running.
輸入結構描述
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Model id"
},
"request_id": {
"type": "string",
"description": "req_… id"
},
"timeout": {
"type": "integer",
"minimum": 0,
"maximum": 60
}
},
"required": [
"model",
"request_id"
]
}🔴cancel_job(model, request_id)
Cancel a request while it is still queued.
輸入結構描述
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Model id"
},
"request_id": {
"type": "string",
"description": "req_… id"
}
},
"required": [
"model",
"request_id"
]
}社群
證據