Ein MCP Server, der über MCP (Model Context Protocol) die Bildgenerierungsfunktionen der TokenHub-LLM-Serviceplattform aufruft. Kunden können in jedem MCP-fähigen Client (WorkBuddy / Claude Desktop / Cursor / beliebigen KI-IDEs) den TokenHub-API-Schlüssel konfigurieren und direkt per natürlicher Sprache Text-zu-Bild-, Bild-zu-Bild-/Bildbearbeitungsschnittstellen aufrufen.
Derzeit integriertes Beispielmodell: custom-model-og-v2 (GPT-basiertes Bildgenerierungsmodell, synchron zurückgegeben).
Zwei Werkzeuge
tokenhub_generate_image: Text-zu-Bild (POST /v1/wand/og-image/generation, synchron)
tokenhub_edit_image: Bild-zu-Bild/Bildbearbeitung (POST /v1/wand/og-image/edits, synchron, unterstützt 1–16 Eingabebilder, Masken-Inpainting)
Zwei Transportarten
stdio (Standard): direkte Anbindung für lokale Clients, keine Bereitstellung erforderlich
streamable-http: als Remote-Endpunkt bereitstellen, für externe Kunden/Teams per Fernzugriff
Flexible Konfiguration: API-Key, Standort-Domain und Modellname sind über Umgebungsvariablen konfigurierbar; Domain/Modell können pro Aufruf überschrieben werden (Standort- oder Modellwechsel ohne Konfigurationsänderung)
Related MCP server: Vertex AI Imagen MCP Server
Fügen Sie in der MCP-Client-Konfiguration einen MCP Server vom Typ „Befehl“ hinzu:
Client | Konfigurationsort |
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"
}
}
}Nach der Konfiguration kann direkt gechattet werden: „Zeichne mir ein Kätzchen, das in einem Bambuswald tanzt, 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 | Erforderlich | Standardwert | Beschreibung |
| Ja (Fehler bei Aufruf) | - | API-KEY aus der TokenHub-Konsole; Request-Header |
| Nein |
| Standort-Domain (siehe Standort-Hinweise unten), kein abschließender Schrägstrich |
| Nein |
| Standardmodellname, pro Argument überschreibbar |
| Nein (HTTP-Modus empfohlen) | - | Optionale Authentifizierung im HTTP-Modus; nach der Einstellung müssen |
TokenHub wird nach Regionen bereitgestellt; Kunden an verschiedenen Standorten müssen die entsprechende Domain angeben. Standard ist der Standort Guangzhou des Inland:
Standort | Domain (Beispiel) |
Inland · Guangzhou |
|
Andere Standorte (Standorte in China, Singapur / internationale Standorte Guangzhou, Singapur, US-West usw.) | Kontaktieren Sie Ihr TokenHub-Vertrieb/Technik-Support, tragen Sie die im Feld |
Parameter | Erforderlich | Beschreibung |
| Ja | Textbeschreibung, maximal 32000 Zeichen |
| Nein | Standort-Domain / Modellname für den einzelnen Aufruf überschreiben |
| Nein | Generierungsgröße |
| Nein |
|
| Nein | Generierte Anzahl 1–10, Standard 1 |
| Nein |
|
| Nein |
|
| Nein | JPEG-Kompression 0–100 (nur jpeg) |
| Nein |
|
Teilt die meisten Parameter oben, zusätzlich:
Parameter | Erforderlich | Beschreibung |
| Ja | 1–16 Eingabebilder, |
| Nein | Maske für lokale Inpainting, Abmessungen müssen den Eingabebildern entsprechen |
| Nein | zusätzlich |
Rückgabe: Liste der Bild-URLs, request_id (zur Problembehebung), total_tokens (zur Abrechnung); bei response_format=b64_json zusätzlich Base64-Bilddaten zur direkten Anzeige.
Fehlgeschlagene Tool-Aufrufe geben isError: true zurück; die Fehlerinformationen enthalten status, den code des Upstream-Fehlers und request_id.
Bei Berechtigungs-, Limitierungs- oder Parameter-Fehlern: bewahren Sie die request_id auf und reichen Sie sie beim TokenHub-Support zur Analyse ein.
Wenn TOKENHUB_API_KEY nicht konfiguriert ist, liefert der Tool-Aufruf direkt einen eindeutigen Hinweis zurück (der Server startet dennoch normal).
# 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=127.0.0.1Endpunkte:
POST /mcp, GET /mcp: MCP-Protokoll-Einstieg
GET /health: Health-Check
Bei öffentlicher Bereitstellung unbedingt:
MCP_AUTH_TOKEN setzen oder in einem vorgelagerten Gateway/Reversen Proxy (z. B. EdgeOne, CLB, Nginx) authentifizieren.
HTTPS verwenden.
base_url unterstützt „überschreiben beim einzelnen Aufruf“, sollte aber nur in vertrauenswürdigen Umgebungen freigeschaltet werden.
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Veröffentlichung an npmjs Ohne (bei Tencent-Registry, wenn aktiv, muss es explizit angegeben werden):
npm run build
npm version patch
npm publish --access public --registry=https://registry.npmjs.org
git tag v0.1.0 && git push --tagsFreigabe: custom-model-og-v2 ist ein Testmodell. Reichen Sie über den TokenHub-Produkt bzw. Technikmitarbeiter eine Freigabe auf Basis von UIN und Appid ein; ohne Freigabe liefern Aufrufe einen Berechtigungsfehler.
API-Key: Erstellen Sie für das entsprechende Modell in der TokenHub-Konsole einen eigenen Key. Der Key wird nur einmal bei Erstellung angezeigt, bewahren Sie ihn sicher auf.
Abrechnung: TokenHub abrechnet nach Token (ca. 10 RMB/1 Million Tokens), stündliche Verrechnung. n>1 oder mehrere Eingabebilder erhöhen den Verbrauch deutlich; lassen Sie den Vertrieb rechtzeitig für Discount für Kunden beantragen – beachten Sie.
Kostenformel (RMB): Text-Eingabe-Token × 3.35 + Text-Cache-Token × 0.8375 + Bild-Eingabe-Token × 5.36 + Bild-Cache-Token × 1.34 + Ausgabe-Bild-Token × 20.1 = Token-Verbrauch für eine einzelne Aufgabe (Umwandlungsfaktor hängt vom Wechselkurs ab, derzeit Faktor 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.
Generate images from Claude, ChatGPT, Cursor and Codex with 12 top AI image models. Up to 4 images per call, SVG vectorization, background removal, upscaling and image-to-video. Remote MCP with OAuth, no API keys.
