Mmcp.market

DeepSeek Visionary MCP server

by xlight·io.github.xlight/deepseek-visionary·v0.2.2

DeepSeek web vision model as an MCP server with browser auto-login.

A88/100grade A
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
Growing

17 stars

Reviews

Write one

Nobody has reviewed DeepSeek Visionary yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

DeepSeek Visionary tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.9 · 2026-09-23 · same rubric, same numbers if you re-run it

no findings
  • Code scanpackage could not be scannedn/a
  • Live reliabilityno gateway calls yet and no remote to proben/a
  • Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 3 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the DeepSeek Visionary repository's README, as published. We do not edit it. Read it on GitHub

DeepSeek Visionary

让 DeepSeek 网页版视觉模型,成为你所有 AI 助手的"眼睛"。 在 Zed、OpenCode、Codex、Claude Code、Cursor、Claude Desktop 等任意支持 MCP 的 agent,以及 DeepSeek Harness(DSH,原生插件或 skill + CLI)中直接识图——浏览器自动登录,无需 API key、无需手动复制 token。

Python 版 deepseek-vision-mcp 的 Rust 全量重写:单原生二进制、多平台分发,一处安装处处可用。DSH 用户更可 dsh plugin 一键安装原生插件包 @xlight-oss/visionary-dsh——5 个原生工具 + 文本模型图片桥接,一包全齐。

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 DSH[DeepSeek Harness]
        DP["@xlight-oss/visionary-dsh 插件<br/>deepseek_vision 等 5 个原生工具<br/>+ 文本模型图片桥接"]
        DP -->|宿主进程 spawn| SRV
    end
    subgraph visionary-server 原生二进制
        SRV["CLI + MCP stdio 服务<br/>vision / ocr / status / login / logout / skill / init / doctor<br/>mcp-stdio 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:单二进制,默认 CLI 模式(vision / ocr / status / login / logout / skill / init / doctor),mcp-stdio 子命令显式启动 MCP stdio 服务;实现完整 vision / OCR 流水线(PoW → 上传 → fork → HIF 签名 → SSE 流式 completion)与 CDP 自动登录
  • @xlight-oss/visionary-dsh:DSH 原生插件包(npm,纯 ESM 无构建,单包双插件行),经 ctx.tools 注册 deepseekvision / deepseekocr 等 5 个原生工具,宿主进程内 spawn visionary-server 复用 Rust 管道(续聊/登录不受 bash 沙箱限制);内置文本模型图片桥接(纯文本模型会话粘贴图片自动放行 + 改写为文本引导)
  • 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

安装

1. 安装二进制

# macOS / Linux 一键脚本
curl -LsSf https://github.com/xlight/deepseek-visionary/releases/latest/download/visionary-server-installer.sh | sh

# Windows(PowerShell 一键,自动绕过执行策略)
powershell -NoProfile -ExecutionPolicy Bypass -Command "irm https://github.com/xlight/deepseek-visionary/releases/latest/download/visionary-server-installer.ps1 | iex"

# 或 Homebrew
brew install xlight/tap/visionary-server

# 或 npm(全平台)
npm install -g @xlight-oss/visionary-server

也可以直接从 GitHub Releases 下载对应平台的 visionary-server- 裸二进制加入 PATH(Windows 为 .exe,或 .zip 解压)。

Windows 安装脚本默认装到 $HOME\.cargo\bin 并自动写入 PATH(加 -NoModifyPath 可跳过);该目录只是 cargo-dist 的默认命名约定,不要求安装 cargo——非 Rust 用户可用 VISIONARYSERVERINSTALL_DIR 环境变量自定义安装目录,或直接用 npm 全局包。首次运行若遇 SmartScreen 弹窗,点「更多信息 → 仍要运行」即可。

npm 全局包注意:Windows 上 npm install -g @xlight-oss/visionary-server 的 PATH 里只有 shim(.cmd / .ps1),DSH 原生插件会自动解析 shim 定位真实 exe——安装后重启 DSH 即可用。

2. 快速开始(CLI + skill,推荐)

CLI 是零配置入口:安装后即可直接在终端 / 脚本 / AI agent 中调用 vision 识图,无需任何 MCP 配置。首次使用先登录:

# 浏览器自动登录(后续无需重复)
visionary-server login

# 识图(agent/脚本调用务必加 --json 原子输出)
visionary-server vision screenshot.png
visionary-server vision img.png --json --prompt "图中有什么?" --thinking

给 AI agent 使用时,把内嵌的调用契约 skill 装进 agent 的 skills 目录,agent 即学会以 --json 原子输出正确调用:

# skill 内嵌于二进制,一条命令安装/更新
visionary-server skill install
# → 写入 ~/.agents/skills/visionary-cli/SKILL.md
# 可将该目录移动到所用 agent 的默认 skills 目录

3. 进阶:接入 MCP 宿主

需要把 deepseek_vision 作为 MCP 工具暴露给宿主(Zed / OpenCode / Codex / Claude Code / Cursor / Claude Desktop)时,用 init 一键接入:

# 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
visionary-server init dsh   # DeepSeek Harness(skill + CLI 轻量接入)

# 批量接入多个 agent(免交互)
visionary-server init --opencode --codex --dsh --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/:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

The registry entry has no remote endpoint or installable package.

DeepSeek Visionary: common questions

Is DeepSeek Visionary MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the DeepSeek Visionary safety report
Does DeepSeek Visionary need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is DeepSeek Visionary maintained?
The last commit was 3 days ago (2026-09-21). The latest release is v0.2.2.
What can I use instead of DeepSeek Visionary?
Servers from other publishers that do the same job: SeleniumBase MCP server, AIHawk MCP server and Ui.Vision MCP server. Compare all DeepSeek Visionary alternatives.

Alternatives to DeepSeek Visionary

Same job from other publishers: the closest match first, then the best rated.

All DeepSeek Visionary alternatives →
  • SeleniumBase MCP
    Stealthy browser automation, testing, and web-scraping via CDP Mode.
    A
  • AIHawk
    AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.
    A
  • Ui.Vision MCP
    MCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard input
    C
  • Scrapeless
    Web search, browser automation, scraping, crawling and CAPTCHA solving for AI agents.
    A
  • Web Browser (kogiQA)
    This web browser has been designed to help your agent debug and develop complex web applications.
    C

More from xlight