DeepSeek Visionary
Click on "Install 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., "@DeepSeek Visionaryanalyze the screenshot at ~/Desktop/error.png and explain the error"
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.
DeepSeek Visionary
在任意支持 MCP 的 AI agent(Zed、OpenCode、Codex、Claude Code、Cursor、Claude Desktop)中使用 DeepSeek 网页版的原生多模态视觉模型,支持浏览器自动登录(无需手动复制 token)。
这是 Python 版 deepseek-vision-mcp 的 Rust 全量重写:单原生二进制,多平台分发。
架构
graph TD
subgraph 宿主[任意 MCP 宿主]
AG["Zed / OpenCode / Codex / Claude Code / Cursor / Claude Desktop"]
AG -->|spawn 独立进程| SRV
end
subgraph visionary-server 原生二进制
SRV["MCP stdio 服务<br/>vision / status / login / logout 工具<br/>init / doctor CLI"]
CFG["~/.deepseek-visionary/config.json<br/>token + smidV2 + cf_clearance + 会话"]
SRV --> CFG
end
SRV -->|HTTPS| DS["DeepSeek 网页后端"]
SRV -->|CDP 启动 + 监听| BRO["Chrome 系浏览器<br/>仅登录时出现"]visionary-server:标准 MCP stdio 服务,实现完整 vision 流水线(PoW → 上传 → fork → HIF 签名 → SSE 流式 completion)与 CDP 自动登录;同时提供
init/doctorCLI 引导接入visionary-zed-ext:Zed 扩展壳(仅 Zed 需要),按平台从 GitHub Releases 下载/缓存 visionary-server 并启动
Related MCP server: multimodal-mcp
安装
1. 安装二进制
# 一键脚本(macOS / Linux)
curl -LsSf https://github.com/xlight/deepseek-visionary/releases/latest/download/visionary-server-installer.sh | sh
# 或 Homebrew
brew install xlight/tap/visionary-server
# 或 npm
npm install -g @xlight-oss/visionary-server也可以直接从 GitHub Releases 下载对应平台的
visionary-server-<target-triple>裸二进制加入 PATH。 Windows 用户可使用 PowerShell 安装脚本。
2. 接入你的 AI agent
# 一键检测并接入(列出已安装 agent)
visionary-server init
# 接入指定 agent
visionary-server init opencode
visionary-server init codex
visionary-server init claude
visionary-server init cursor
visionary-server init claude-desktop
# 批量接入多个 agent(免交互)
visionary-server init --opencode --codex --yes
# 先预览将写入的配置(不落盘)
visionary-server init opencode --dry-run各 agent 的详细接入文档见 docs/integrations/:
Agent | 文档 | 一键命令 |
Zed | 扩展市场安装(见下) | |
OpenCode |
| |
Codex |
| |
Claude Code |
| |
Cursor |
| |
Claude Desktop |
|
新兴通道:Microsoft Agent Package Manager 用户可直接
apm install --mcp io.github.xlight/deepseek-visionary(复用 MCP Registry 标识)。
3. 登录
调用 MCP 工具的 deepseek_vision_login 完成自动登录:
会打开浏览器窗口并导航到 chat.deepseek.com
在浏览器中登录后,工具自动抓取 token 并保存
手动兜底:登录 chat.deepseek.com 后,DevTools → Application → Local Storage →
userToken→ 复制JSON.parse(value).value,写入~/.deepseek-visionary/config.json:{ "user_token": "你的 token" }
4. 使用
调用 deepseek_vision 传入图片路径或 base64 即可识图。
Zed 扩展安装
如果你只用 Zed,也可以直接从扩展市场安装:
Zed 命令面板(
Cmd+Shift+P)→zed: extensions→ 搜索 DeepSeek Visionary → Install扩展壳自动下载/缓存
visionary-server二进制并启动 MCP 服务授权工具权限(见 docs/integrations/zed.md)
CLI 工具
命令 | 说明 |
| 进入 MCP stdio serve 模式(所有 agent 配置的默认入口) |
| 输出版本号 |
| 诊断环境:config 路径/权限、浏览器、token 有效性、平台 |
| 检测并接入已安装的 AI agent( |
MCP 工具
工具 | 说明 |
| 上传本地图片(路径 / base64)并用 DeepSeek 视觉模型分析。参数: |
| 检查登录状态与 token 有效性(含真实校验探针) |
| 浏览器自动登录并抓取凭据 |
| 清除保存的凭据 |
会话续聊
deepseek_vision 支持多轮对话:
continue_conversation=true:复用上一次会话,可对比多张图片session_id:显式切换到指定会话线程
会话状态持久化在 ~/.deepseek-visionary/session.json。
环境变量
变量 | 说明 |
| 覆盖 config.json 中的 token(可选) |
| 覆盖对应 cookie(可选) |
| API 基地址(默认 |
| 登录等待超时秒数(默认 600) |
开发
# 构建原生服务
cargo build -p visionary-server --release
# 构建扩展壳(wasm32-wasip2)
rustup target add wasm32-wasip2
cargo build -p visionary-zed-ext --release --target wasm32-wasip2
# 测试
cargo test -p visionary-server平台支持
macOS(Apple Silicon / Intel)
Linux(x86_64 / aarch64)
Windows(x86_64)
需要 Chrome / Chromium / Edge 之一用于自动登录。
工作原理(要点)
PoW:wasmtime 加载 DeepSeek 站内
sha3_wasm_bg.*.wasm(随仓库分发),调用wasm_solve求解upload_file与completion的 challengeTLS 指纹:completion 端点与 Python 版(curl_cffi chrome131)对齐;Rust 侧默认普通 reqwest,若被 403 再启用指纹模拟(见 design.md spike 记录)
登录:CDP 控制 Chrome 系浏览器(专用 profile
~/.deepseek-visionary/browser/),读取localStorage.userToken与smidV2/cf_clearancecookie凭据安全:
~/.deepseek-visionary/config.json权限 0600,浏览器 profile 0700
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityCmaintenanceAn MCP server that grants image recognition to text-only models like DeepSeek by forwarding images to vision models and returning text descriptions. Supports clipboard, pasted session images, and batch folder image recognition.1MIT
- FlicenseAqualityBmaintenanceLocal MCP server that adds multimodal capabilities to text-only models like Codex/DeepSeek, offering tools for image description, audio transcription, video analysis, image/video generation, and speech synthesis.10
- AlicenseAqualityBmaintenanceMCP server that analyzes images, reads code and ZIP archives, and provides text context for non-vision models.3MIT
- Alicense-qualityCmaintenanceMCP server that gives DeepSeek and other clients vision capabilities by routing images to open-source multimodal models, returning structured specifications or answers. Supports CLI and MCP tools for design analysis and general image Q&A.156MIT
Related MCP Connectors
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
MCP server for Google Veo AI video generation
MCP server for Grok Imagine AI video generation
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/xlight/deepseek-visionary'
If you have feedback or need assistance with the MCP directory API, please join our Discord server