TokenHub AIGC Model MCP server lets AI clients discover models, generate/edit images, and create Kling videos through natural-language tool calls.
List available models via tokenhub_list_models (used for conversation-based model selection).
Generate images from text prompts with tokenhub_generate_image, supporting size, quality, output format, count, background, base64/URL responses, and per-call model/domain overrides.
Edit images or run image-to-image generation with tokenhub_edit_image, using 1–16 input images and an optional mask for local repainting.
Create Kling videos from text with tokenhub_kling_text_to_video (asynchronous task submission).
Create Kling videos from an image plus prompt with tokenhub_kling_image_to_video.
Check/poll video task status and retrieve temporary video links via tokenhub_kling_get_task.
Configure API key, base URL, default model, and timeout via environment variables; supports stdio and HTTP (remote) MCP deployments.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@tokenhub-aigc-model Create an image of a serene mountain lake at sunrise with vibrant colors"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP Server that calls TokenHub's large-model image generation capabilities via MCP (Model Context Protocol). After configuring the TokenHub API Key in any MCP-compatible client (WorkBuddy / Claude Desktop / Cursor / various AI IDEs), customers can directly invoke text-to-image and image-to-image/image-editing interfaces using natural language.
Built-in sample model: custom-model-og-v2 (GPT-series image generation model, returns synchronously).
Two tools
tokenhub_generate_image: text-to-image (POST /v1/images/generations, synchronous return)
tokenhub_edit_image: image-to-image / image editing (POST /v1/images/edits, synchronous return, supports 1-16 input images and mask inpainting)
Two transports
stdio (default): direct integration with local clients, zero deployment
streamable-http: deploy as a remote endpoint for external customers/teams to access remotely
Flexible configuration: API Key, site domain, and model name can all be configured via environment variables; a single call can override the domain/model (switching sites or models requires no configuration changes)
Related MCP server: Vertex AI Imagen MCP Server
Add a command-type MCP Server to your MCP client configuration:
Client | Configuration |
WorkBuddy |
|
Claude Desktop |
|
Cursor | Settings → MCP → Add new MCP server |
{
"mcpServers": {
"tokenhub": {
"type": "stdio",
"command": "npx",
"args": ["-y", "tokenhub-aigc-model"],
"env": {
"TOKENHUB_API_KEY": "你的 TokenHub API Key",
"TOKENHUB_BASE_URL": "https://tokenhub.tencentmaas.com",
"TOKENHUB_MODEL": "custom-model-og-v2"
},
"description": "TokenHub 生图 MCP"
}
}
}After configuration, you can start chatting: "Draw me a kitten dancing in the bamboo forest, 2048x2048".
{
"mcpServers": {
"tokenhub": {
"url": "https://你的服务域名/mcp",
"headers": { "x-mcp-auth-token": "部署时设置的 MCP_AUTH_TOKEN" }
}
}
}Variable | Required | Default | Description |
| Yes (error at execution) | - | API Key obtained from the TokenHub console, sent in the |
| No |
| Site domain (see site description below), no trailing slash |
| No |
| Default model name, can be overridden 拡張 per call |
| No (recommended in HTTP mode) | - | Optional authentication for HTTP mode; when set, requests to |
TokenHub is deployed across regional sites, and customers on different sites need to specify their corresponding domain. The default is the domestic Guangzhou site:
Site | Domain (example) |
Domestic · Guangzhou |
|
Other sites (domestic Singapore / international sites in Guangzhou, Singapore, US West, etc.) | Contact TokenHub to obtain the corresponding domain from business/technical support, and fill it into |
Parameter | Required | Description |
| Yes | Text prompt, max 32000 characters |
| No | Override the site domain / model name for a single call |
| No | Generated size |
| No |
|
| No | Number of images to generate 1-10, default 1 |
| No |
|
| No |
|
| No | JPEG compression level 0-100 ( |
| No |
|
Shares all of the parameters above. Additional parameters:
Parameter | Required | Description |
| Yes | 1-16 input images, |
| No | Local inpainting mask, the size must match the input image |
| No | additionally supports |
Returns: a list of image URLs, request_id (for troubleshooting), total_tokens (for billing); if response_format=b64_json, the optional side effect also includes base64 image blocks for direct display.
A failed tool call returns isError: true and the error message contains status, the upstream error code, and request_id.
On permission / rate-limit / parameter errors, please keep the request_id to submit to TokenHub technical support for troubleshooting.
If TOKENHUB_API_KEY is not configured, tool calls include multiple useful error message (the server can still start normally).
# 本地启动（默认 stdio）
npx -y tokenhub-aigc-model
# HTTP 模式
TOKENHUB_API_KEY=xxx MCP_AUTH_TOKEN=部署密钥 \
npx -y tokenhub-aigc-model --transport=http --port=3000 --host=127.0.0.1Endpoints:
POST /mcp、GET /mcp: MCP protocol entry
GET /health: health check
When deploying to the public internet, make sure to:
Set the MCP_AUTH_TOKEN, or optionally perform authentication at the front-end gateway. reverse proxy (such as EdgeOne, CLB, Nginx);
Use HTTPS;
base_url supports per-call overrides; it is only recommended to open it in trusted environments.
npm install # 安装依赖
npm run build # TypeScript 构建到 dist/
npm test # 单元测试 + stdio/HTTP 冒烟测试（共 20 个用例）
npm pack --dry-run # 查看发布内容publish to npmjs (if the current registry is a Tencent mirror, specify the registry explicitly):
npm run build
npm version patch
npm publish --access public --registry=https://registry.npmjs.org
git tag v0.1.0 && git push --tags白名單申請：custom-model-og-v2 為測試模型，請先聯繫 TokenHub 產品/後台人員提交 UIN 和 Appid 取得白名單權限後，方可使用；沒有白名單的調用會返回權限錯誤。
API Key: please go to TokenHub console Create a dedicated Key for your model; the Key is shown only once at creation, so save it safely.
計費: TokenHub 按 Token 計費（約 10 元 / 百萬 tokens），每小時結算。n>1 或多張輸入圖片會显著增加消耗，請商務人員盡早為客戶申請折扣。
費用公式（人民幣）：文本輸入 token×3.35 + 文本緩存輸入×0.8375 + 圖輸入圖×5.36 + 圖像緩存輸入×1.34 + 輸出圖片×20.1 = 單次任務 token 消耗（換算係數與匯率相關，當前係數為 6.7）。
调用 TokenHub 接口，基于 1-16 张输入图 + 文本描述同步生成图片（模型默认 custom-model-og-v2，需开白）。支持局部重绘（mask）。输入图支持 URL 或 base64。返回图片 URL 列表、request_id 与 token 用量。
| Name | Required | Description | Default |
|---|---|---|---|
| n | No | 生成图片数量 1-10，默认 1 | |
| mask | No | 局部重绘蒙版图，尺寸需与输入图一致 | |
| size | No | 生成尺寸 "宽x高"，如 2048x2048。约束：单边≤3840px、宽高为 16 的倍数、长短边比≤3:1、总像素 655360~8294400 | |
| model | No | 单次覆盖模型名。不传时用环境变量 TOKENHUB_MODEL（默认 custom-model-og-v2） | |
| images | Yes | 输入图 1-16 张，支持 URL 或 base64 | |
| prompt | Yes | 文本描述，最大 32000 字符 | |
| quality | No | 画质，默认 auto | |
| base_url | No | 单次覆盖站点域名（如 https://tokenhub.tencentmaas.com）。不传时用环境变量 TOKENHUB_BASE_URL | |
| background | No | 图像背景透明度：transparent 透明 / opaque 不透明 / auto 自动判断，默认 auto | |
| output_format | No | 输出格式，默认 png | |
| response_format | No | 返回格式：url（图片地址）或 b64_json（base64 数据），默认 url | |
| output_compression | No | JPEG 压缩级别 0-100，仅 output_format=jpeg 时生效 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the model default, whitelist requirement, mask support, URL/base64 input acceptance, and return fields. It does not mention error behavior, rate limits, or auth mechanics, but it covers the main operational characteristics well.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact, informative, and well-front-loaded. It covers the core operation, constraints, input formats, mask feature, and return payload in four sentences with no fluff or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the 12-parameter schema and absence of an output schema, the description provides enough operational context: input requirements, image count range, model default and whitelist, mask support, and response contents. It falls short of 5 only because of missing explicit alternative-tool routing and access/auth context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description mentions mask, input images, model default, and input formats, but most of these details are already documented in the schema. It adds only high-level context like whitelist and return metadata, not substantial new parameter-level semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the operation: calling TokenHub to generate an image from 1-16 input images plus a text prompt, with support for mask-based local repainting. It also specifies the output contents (image URL list, request_id, token usage), making the tool's purpose and scope unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear contextual signals for when to use this tool: when existing images are provided as input and editing/repainting is needed. It doesn't explicitly exclude or name the alternative tokenhub_generate_image, so the routing guidance is implied rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
调用 TokenHub 接口，根据文本描述同步生成图片（模型默认 custom-model-og-v2，需在 TokenHub 控制台开白并配置专属 API Key）。返回图片 URL 列表、request_id 与 token 用量。
| Name | Required | Description | Default |
|---|---|---|---|
| n | No | 生成图片数量 1-10，默认 1 | |
| size | No | 生成尺寸 "宽x高"，如 2048x2048。约束：单边≤3840px、宽高为 16 的倍数、长短边比≤3:1、总像素 655360~8294400 | |
| model | No | 单次覆盖模型名。不传时用环境变量 TOKENHUB_MODEL（默认 custom-model-og-v2） | |
| prompt | Yes | 文本描述，最大 32000 字符 | |
| quality | No | 画质，默认 auto | |
| base_url | No | 单次覆盖站点域名（如 https://tokenhub.tencentmaas.com）。不传时用环境变量 TOKENHUB_BASE_URL | |
| background | No | 图像背景透明度：opaque 不透明 / auto 自动判断，默认 auto | |
| output_format | No | 输出格式，默认 png | |
| response_format | No | 返回格式：url（图片地址）或 b64_json（base64 数据），默认 url | |
| output_compression | No | JPEG 压缩级别 0-100，仅 output_format=jpeg 时生效 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that the call is synchronous, requires the user to have whitelisted the model and configured a dedicated API key, and that the response includes image URLs, request_id, and token usage. It does not cover error behavior or rate limits, but the key behavioral constraints are present.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two short, information-dense sentences with no redundancy. It ends with the action and auth prerequisite, then return values. Every word contributes to the agent's understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 10 parameters and no output schema, the description covers the important context: synchronous, auth required, default model, return shape. The schema covers parameter details, and what is missing (timeouts, error behavior) is minor for most use cases.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema documents all 10 parameters with detailed per-parameter descriptions, so the description adds very little for parameters. Mentioning the default model is useful but overlaps with the schema's model field. This is the expected baseline since schema coverage is 100%.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's action: calling TokenHub to synchronously generate an image from a text description, and identifies the resource (image). It does not explicitly contrast with tokenhub_edit_image, but the 'generate from text' wording is distinct enough.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the appropriate scenario (generate an image from a prompt) and provides essential prerequisites (whitelist + dedicated API key). However, it gives no explicit guidance on when to prefer this over tokenhub_edit_image or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0tokenhub_edit_imagetokenhub_generate_imageScored across 2 tools
The two tools have clearly distinct purposes: one generates an image purely from text, while the other edits/generates from 1-16 input images with optional masking. There is no realistic confusion between them.
Both tools follow the same tokenhub_<verb>_image pattern with static verb prefixes: edit and generate. The naming convention is consistent and predictable.
With only two tools, the server is slightly thin, but each tool covers a distinct core task in the image-generation domain. The focused scope makes the small count reasonable.
The two primary workflows—text-to-image generation and image editing/reinpainting—are covered, and the synchronous design avoids needing result-status tools. A minor gap is the lack of model-list or capability-discovery tooling, but agents can still complete the core tasks.
Generate AI images and videos from any compatible MCP client.
Generate images with any major model — one API key, one prepaid balance, one MCP.
Multi-model AI image and video generator. 14 models behind one OAuth-secured MCP endpoint.
Focused MCP server for OpenAI image/audio generation (v2.0.0). Wraps endpoints via HAPI CLI.
