{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_7ckqeus36q75","handle":"jimeng-ai-mcp","url":"https://wellknown.network/agents/jimeng-ai-mcp","links":{"self":"https://wellknown.network/agents/jimeng-ai-mcp/record.json","html":"https://wellknown.network/agents/jimeng-ai-mcp","markdown":"https://wellknown.network/agents/jimeng-ai-mcp/record.md","api":"https://wellknown.network/api/v1/agents/jimeng-ai-mcp","status":"https://wellknown.network/api/v1/agents/jimeng-ai-mcp/status","claim":"https://wellknown.network/agents/jimeng-ai-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/jimeng-ai-mcp/claim.json","badge":"https://wellknown.network/agents/jimeng-ai-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/jimeng-ai-mcp/history","tools":"https://wellknown.network/api/v1/agents/jimeng-ai-mcp/tools"},"ard":{"identifier":"urn:air::server:jimeng-ai-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"jimeng-ai-mcp","summary":"MCP server for Jimeng AI (即梦) - Official Volcengine API","description":"# jimeng-mcp\n\n**即梦 AI 的 MCP 服务** — 让 Claude、Cursor 等 AI 助手直接调用即梦的图片/视频生成能力。\n\n[English](README_EN.md) | 中文\n\n---\n\n## 这是什么\n\n[MCP（Model Context Protocol）](https://modelcontextprotocol.io/) 是 Anthropic 推出的开放协议，允许 AI 模型通过标准化接口调用外部工具和服务。\n\n**jimeng-mcp** 将字节跳动旗下[即梦 AI](https://jimeng.jianying.com/) 的官方 Volcengine API 封装为 MCP 服务。接入后，你可以在 Claude、Cursor 等支持 MCP 的客户端里，用自然语言直接驱动即梦生成图片和视频——无需打开浏览器，无需手动上传，生成结果自动保存到本地。\n\n## 能做什么\n\n### 图片能力\n\n| 工具 | 能力 | 底层模型 |\n|---|---|---|\n| `generate_image` | 文生图，支持 4.0 / 4.6 / 3.x 多模型 | 即梦图片系列 |\n| `image_to_image` | 图生图，智能参考原图风格/内容进行编辑 | jimeng_i2i 3.0 |\n| `inpaint_image` | 局部重绘：涂抹修改或消除画面元素 | inpaint |\n| `upscale_image` | 智能超清：低清图片放大到 4K / 8K | Seedream SR |\n\n### 视频能力\n\n| 工具 | 能力 | 底层模型 |\n|---|---|---|\n| `generate_video` | 文生视频，720P / 1080P / Pro 三档 | 即梦视频 3.0 |\n| `image_to_video` | 图生视频：首帧、首尾帧、重新运镜、Pro 模式 | 即梦视频 3.0 |\n| `imitate_motion` | 动作模仿：将参考视频的动作迁移到目标人物 | DreamActor 2.0 |\n| `generate_digital_human` | 数字人：图片 + 音频 → 口型同步说话视频 | OmniHuman 1.5 |\n| `translate_video` | 视频翻译：保留音色，口型同步换语言 | 翻译 2.0 |\n\n## 使用场景\n\n- **内容创作者**：对话式生成配图和视频素材，不切换工具\n- **产品/设计**：在 Cursor 里边改需求文档边生成原型图\n- **营销团队**：批量生成不同风格的创意图，描述即出图\n- **开发者**：在自己的 AI 应用中集成即梦能力，无需关心鉴权细节\n\n## 快速上手\n\n### 第一步：开通服务\n\n1. 登录[火山引擎控制台](https://console.volcengine.com/ai/ability/detail/2)，开通**即梦 AI** 服务\n2. 在[访问控制 → API 访问密钥](https://console.volcengine.com/iam/keymanage/)获取 Access Key ID 和 Secret Access Key\n\n### 第二步：安装\n\n推荐使用 `uvx`（无需手动安装，运行时自动拉取）：\n\n```bash\nuvx jimeng-ai-mcp\n```\n\n也可以用 pip 全局安装：\n\n```bash\npip install jimeng-ai-mcp\n```\n\n### 第三步：配置 MCP 客户端\n\n#### Claude Desktop\n\n配置文件路径：\n- **macOS**：`~/Library/Application Support/Claude/claude_desktop_config.json`\n- **Windows**：`%APPDATA%\\Claude\\claude_desktop_config.json`\n\n```json\n{\n  \"mcpServers\": {\n    \"jimeng\": {\n      \"command\": \"uvx\",\n      \"args\": [\"jimeng-ai-mcp\"],\n      \"env\": {\n        \"JIMENG_ACCESS_KEY_ID\": \"填入你的 Access Key ID\",\n        \"JIMENG_SECRET_ACCESS_KEY\": \"填入你的 Secret Access Key\"\n      }\n    }\n  }\n}\n```\n\n#### Cursor\n\n配置文件路径：`~/.cursor/mcp.json`\n\n`…","publisher":null,"homepage":null,"repository":null,"version":"0.1.1","license":"MIT","protocols":["mcp"],"tags":["ai","image-generation","jimeng","mcp","video-generation","volcengine"],"pricing":null,"endpoints":[{"url":"pypi:jimeng-ai-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"media.image-generation","name":"Image Generation","confidence":1,"provenance":"declared"},{"slug":"media.video-generation","name":"Video Generation","confidence":1,"provenance":"declared"}],"categories":["media"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"jimeng-ai-mcp","registry":"pypi","observedAt":"2026-11-03T10:25:00.647Z","publishedAt":"2026-04-09T01:25:37.164259Z","latestVersion":"0.1.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"jimeng-ai-mcp","url":"https://pypi.org/project/jimeng-ai-mcp/","firstSeenAt":"2026-09-09T22:22:27.197Z","fetchedAt":"2026-11-03T10:23:24.240Z","normalizedAt":"2026-11-03T10:23:24.240Z"}]},"firstSeenAt":"2026-09-09T22:22:27.197Z","updatedAt":"2026-11-03T10:25:00.647Z"}