unifically-mcp

MCPAI代理

提供方 unifically-dev

AI代理 HTTP · 远程 API Key 社区 / 第三方 Claude DesktopClaudeCursorVS Code
查看接入方式

由 unifically-dev 提供的 MCP 服务器,HTTP · 远程。

一句话选型结论

按资料字段整理

unifically-mcp 属于AI代理类 MCP 服务器,HTTP · 远程,API Key,可直接接入 Claude Desktop、Claude、Cursor 等,有可直接复制的远程端点配置。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类AI代理 传输方式HTTP · 远程 鉴权API Key 部署方式远程部署
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

AI代理
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

mcpmcp serverremote mcp server

安装与配置

HTTP · 远程 API Key
连远程 HTTPS 端点,通常为 Streamable HTTP
https://mcp.unifically.com/mcp

把它填进客户端的 MCP 配置即可,不需要在本地安装运行时。

  1. 1
    准备运行环境

    确认你的客户端支持远程端点,并拿到服务地址。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
给代理接外部能力

让代理在任务中途调用搜索、数据库等真实工具。

多步任务编排

把一串操作拆成步骤,由代理按顺序执行。

自动化重复流程

把固定流程交给代理跑,减少手工操作。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Claude、Cursor,换客户端不用重新研究配置。

先想清楚的地方

  • 远程端点依赖网络与服务方可用性,注意密钥与调用额度。
  • 使用前要准备好API Key对应的凭据,并按最小权限配置。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在AI代理场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Claude 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
unifically-mcp当前 未标注 HTTP · 远程 远程部署 有 未标注
Filesystem 560c4363 13 未标注 本地部署 无 2026-05-17
Server Everything (everything) 11 stdio · 本地进程 本地部署 有 2026-05-17
Time 7365cb6d 2 SSE · 服务端推送 远程部署 有 2026-05-18
Everything Claude Code 未标注 stdio · 本地进程 本地部署 有 2026-05-17
Openmemory 557e1585 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

AI代理
字段来自项目仓库与公开索引,中文说明由本站标注
提供方unifically-dev上游标注的维护方 unifically-dev
分类AI代理本站按上游分类展示
连接方式HTTP · 远程连远程 HTTPS 端点,通常为 Streamable HTTP
鉴权方式API Key远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型远程部署上游给出的部署形态
最近核验未标注上游最后核验时间

详细介绍

13.5 KB
来自项目仓库与上游目录的原文,未做删改

UnificAlly MCP server

An MCP server for the UnificAlly API. It lets an AI assistant generate video, images, music, speech and sound effects, transcribe audio and upscale media through 100+ models (Veo 3.1, Kling, Seedance, Hailuo, Grok Imagine, Nano Banana, Flux, GPT Image, Suno, ElevenLabs, Topaz) with one API key.

It works in any MCP client: Cursor, Claude Desktop, Claude Code, Cline, Windsurf, Zed, ChatGPT Desktop, Goose, n8n and your own code.

Install

  1. Create an API key at https://unifically.com/api-keys. A new account starts with $0.50 of balance to test with.
  2. Add the server to your client config:```json
    {
    "mcpServers": {
    "unifically": {
    "command": "npx",
    "args": ["-y", "@unifically/mcp-server"],
    "env": { "UNIFICALLY_API_KEY": "sk-..." }
    }
    }
    }

That block works as is for Cursor (`.cursor/mcp.json`), Claude Desktop (`claude_desktop_config.json`), Cline and Windsurf (`~/.codeium/windsurf/mcp_config.json`). Restart the client after saving.

Claude Code:```bash
claude mcp add unifically -e UNIFICALLY_API_KEY=sk-... -- npx -y @unifically/mcp-server

Other clients

Zed (~/.config/zed/settings.json):```json
{
"context_servers": {
"unifically": {
"command": { "path": "npx", "args": ["-y", "@unifically/mcp-server"] },
"env": { "UNIFICALLY_API_KEY": "sk-..." }
}
}
}


ChatGPT Desktop: Settings, Connectors, Add MCP server. Command `npx -y @unifically/mcp-server`, plus the `UNIFICALLY_API_KEY` variable.

Goose, n8n or anything else that speaks stdio:```bash
UNIFICALLY_API_KEY=sk-... npx -y @unifically/mcp-server

On Windows, if the client says npx not found, use "command": "cmd", "args": ["/c", "npx", "-y", "@unifically/mcp-server"].

There is also a hosted server at https://mcp.unifically.com/mcp for clients that take a URL. See Remote server.

Example

Ask the assistant for something:

> Make a 16:9 image of a lighthouse at dusk, then a 6 second video that starts from it.

It calls the tools in order:```json
{ "name": "generate_image", "arguments": { "prompt": "a lighthouse at dusk, waves, warm light", "aspect_ratio": "16:9" } }
text Generated image with google/nano-banana-pro. Result: https://files.unifically.com/image/....png [task_id: 7f3c...]json
{ "name": "generate_video", "arguments": { "prompt": "slow push in, waves rolling", "image_url": "https://files.unifically.com/image/....png", "duration": 6 } }


Each generation tool waits for the job and returns the media URL. The structured result looks like this:```ts
{
  task_id: string,
  status: "completed" | "pending" | "processing",
  output: { video_url?, image_url?, audio_url?, image_urls?, audio_urls?, text? },  // when completed
  model: string,
  cost_usd?: number
}

Under the hood each call is one request to the UnificAlly API (POST /v1/tasks with { model, input }, then GET /v1/tasks/{id}), the same one shown in the API docs.

Tools

Tool What it does Spends balance
generate_video Text or image to video (Veo, Kling, Hailuo, Seedance, Grok and more). Optional start and end frames, reference images. yes
generate_image Text to image and image editing (Nano Banana, GPT Image, Flux, Qwen, Kling, Grok, SeeDream). yes
generate_audio Text to speech, sound effects, dialogue, transcription (stt), voice change (voice-changer), audio cleanup (voice-isolation). yes
generate_music Suno: make a song, or cover, extend, add-vocals, add-instrumental or stems an existing track. yes
edit_video Edit an existing clip from a prompt, or transfer motion onto a subject image (motion-control). yes
upscale_media Topaz for any image or video (image_url / video_url), or task_id for the Veo and Grok upscalers. yes
extend_video Extend a finished Veo (+8 s) or Grok Imagine generation. yes
upload_file Turn a URL, or a local file on a stdio server, into a public CDN URL. no
get_task Status and result of a task by id, optionally waiting for it. no
list_tasks Past tasks, newest first, filtered by status, model, category, provider or time. no
list_resources Voice lists for ElevenLabs (default), Kling and Veo. no
list_models The model catalog and aliases. no
dry_run_cost The price of a call without running it. no
check_balance Account balance in USD. no

Every tool sets all four MCP hints. The seven tools that spend balance are marked destructiveHint: true and idempotentHint: false, so a client that auto-approves read-only tools still asks before a paid run. Failed generations are not charged.

Supported models, each with its parameters, id and a browser playground:

  • Video: Veo 3.1, Kling, Seedance, MiniMax Hailuo, Grok Imagine, Wan 3.0, Gemini Omni Flash 1.1
  • Image: Nano Banana, GPT Image 2, Flux.2 Pro, Qwen Image, SeeDream
  • Music and audio: Suno, ElevenLabs
  • Upscaling: Topaz Labs

list_models returns the full live catalog.

How it behaves

  • Every generation tool works from a prompt alone. model is optional and takes short aliases (veo, kling, flux, nano-banana-2, seedance, tts, sfx, stt) or full ids such as google/veo-3.1-fast.
  • Media fields (image_url, image_urls, end_image_url, reference_image_urls, audio_url, video_url) take public https URLs only. A local path or base64 string gets an error that says to upload first.
  • Field names differ between models (Kling's start_frame_url, Veo's start_image_url, Seedance's first_frame_url). You pass image_url and the server renames it. Any field the server has no parameter for goes in provider_options, which also overrides the mapping.
  • The server keeps no copy of each model's allowed durations, resolutions or aspect ratios. The API checks values and returns a 422 that names the fix, at no cost. The server instructions tell the assistant to read the model's page in docs.unifically.com/llms.txt before running a model.
  • Every generation tool also accepts wait, callback_url, provider_options and confirm_cost.
  • Errors come back as one sentence: 401 for a missing or wrong key, 402 for low balance (with a top-up link), 422 with the API's validation message, and a timeout message that tells the assistant to resume with get_task. 429, 5xx and network errors are retried with backoff.

Uploads

Models only read public URLs, so a local file goes to the UnificAlly CDN first.

  1. upload_file { content_type: "image/png" } returns a one-time upload_url and the final file_url. The assistant sends the bytes with curl, without any API key in the shell:bash curl -X PUT '<upload_url>' --data-binary @photo.png

The URL is signed, single use and expires in about 5 minutes. The file keeps full quality.
2. upload_file { url } imports a file that is already online.
3. upload_file { file_path } reads the file from disk, only when the server runs locally over stdio.

There is no base64 upload, and the instructions tell the assistant never to send a user's file to another host. Both rules come from real failures: with a base64 size limit, agents shrank users' images to fit, and one agent without a key in its shell uploaded a private photo to a public file host.

Long jobs

High quality video and full songs can take minutes.

  • wait: false returns { task_id, status: "pending" } at once. Poll get_task until status is "completed".
  • callback_url returns at once too, and the API POSTs the result to your webhook.

Any task can be picked up later with get_task.

Spend limits

All off by default. Set them per deployment:

  • UNIFICALLY_CONFIRM_COST_ABOVE=: a call priced above this returns a quote, and runs only when the assistant retries with confirm_cost: true.
  • UNIFICALLY_MAX_COST_PER_TASK=: a call priced above this is rejected. confirm_cost does not override it.
  • UNIFICALLY_BLOCKED_MODELS=veo-quality,suno or UNIFICALLY_ALLOWED_MODELS=nano-banana-2,flux,tts: restrict which models can run.
  • UNIFICALLY_DISABLE_GENERATION=true: read-only mode. Browsing, dry_run_cost and check_balance still work.

Environment variables

Variable Required Default
UNIFICALLY_API_KEY stdio only none. HTTP callers send their own key. UNIFICALLY_KEY, UNIFICALLY_TOKEN and UNIFICALLY_API_TOKEN also work.
UNIFICALLY_BASE_URL no https://api.unifically.com
UNIFICALLY_FILES_BASE_URL no https://files.unifically.com
UNIFICALLY_REQUEST_TIMEOUT_MS no 60000
UNIFICALLY_MAX_RETRIES no 3
UNIFICALLY_POLL_TIMEOUT_MS no 600000
UNIFICALLY_POLL_START_MS no 2000
UNIFICALLY_POLL_MAX_MS no 10000
UNIFICALLY_CONFIRM_COST_ABOVE no off
UNIFICALLY_MAX_COST_PER_TASK no off
UNIFICALLY_BLOCKED_MODELS no none
UNIFICALLY_ALLOWED_MODELS no none
UNIFICALLY_DISABLE_GENERATION no false
MCP_TRANSPORT no stdio (or http)
UNIFICALLY_HTTP_WAIT_BUDGET_MS no 85000, the longest an HTTP call blocks before returning the task_id
PORT no set by the hosting platform
UNIFICALLY_CORS_ORIGIN no *
UNIFICALLY_TRUSTED_PROXIES no loopback. Also private, exact IPs or CIDRs allowed to send X-Forwarded-For.
UNIFICALLY_TRUST_CF_CONNECTING_IP no false
UNIFICALLY_RATE_PER_MIN no 120 requests per minute, per key and per account
UNIFICALLY_RATE_BURST no 40
UNIFICALLY_PUBLIC_DISCOVERY no true. Lets keyless callers run initialize, tools/list, resources/list and ping. Set 0 to require a key for everything.
UNIFICALLY_ANON_RATE_PER_MIN no 30 keyless requests per minute, per IP
UNIFICALLY_ANON_RATE_BURST no 12

Remote server

MCP_TRANSPORT=http serves Streamable HTTP on /mcp and legacy SSE on GET /sse + POST /messages. The hosted copy runs at https://mcp.unifically.com/mcp.

Each caller sends their own key, so one deployment serves many users and bills each one's own balance:

  1. Authorization: Bearer (recommended)
  2. X-API-Key:
  3. ?api_key= for clients that only take a URL. Query strings can end up in proxy logs, so use a header when you can.```json
    {
    "mcpServers": {
    "unifically": {
    "url": "https://mcp.unifically.com/mcp",
    "headers": { "Authorization": "Bearer sk-..." }
    }
    }
    }

For claude.ai (Settings, Connectors, Add custom connector) put the key in the URL: `https://mcp.unifically.com/mcp?api_key=sk-...`. For stdio-only clients, bridge with `mcp-remote`:```json
{
  "mcpServers": {
    "unifically": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.unifically.com/mcp", "--header", "Authorization: Bearer sk-..."]
    }
  }
}

Details of the HTTP mode:

  • Streamable HTTP is stateless, so it scales behind any reverse proxy without sticky sessions.
  • A caller without a key can run initialize, tools/list, resources/list, prompts/list and ping, so registries can read the tool list. Everything else returns 401. Keyless traffic is rate limited per IP and capped at 16 concurrent messages. GET /.well-known/mcp-config returns a JSON Schema for the one required setting (api_key), and GET /.well-known/mcp/server-card.json returns the tool list.
  • Keys are checked against the API, with the result cached, and a per-IP budget limits failed checks. Rate limits apply per key and per account, so extra keys do not raise one account's limit. Batches are capped at 16 messages and bodies at 512 KB.
  • Browser Origin headers are validated against DNS rebinding. MCP clients send none and are unaffected.
  • X-Forwarded-For is trusted only from UNIFICALLY_TRUSTED_PROXIES. The shipped Compose file sets private for its isolated network; do not use that on a shared LAN.
  • A key with zero balance can still check the balance, list and fetch tasks and price a job. It cannot start one (402).
  • GET / returns connect instructions and GET /health is an unauthenticated health check.

Self-hosting

The repo ships a Dockerfile and docker-compose.yml that run the HTTP transport with per-request keys. Put the container behind an HTTPS reverse proxy, point a domain at it and use /health as the health check. Nothing is required in the environment. UNIFICALLY_CONFIRM_COST_ABOVE=1.00 is a sensible default for a shared deployment.

Development```bash

git clone https://github.com/unifically-dev/unifically-mcp.git
cd unifically-mcp
npm install
cp .env.example .env # add your UNIFICALLY_API_KEY
npm run dev


Inspect the tools interactively:```bash
npx @modelcontextprotocol/inspector npx -y tsx src/index.ts

Tests:bash npm test # build + smoke test npm run test:vitest # full suite

Troubleshooting

Symptom Fix
spawn npx ENOENT Node is not on PATH. Use absolute paths to node and dist/index.js in the client config.
401 Unauthorized UNIFICALLY_API_KEY is missing from the client's env block. Restart the client after editing.
402 Payment Required Top up at https://unifically.com/payments.
Tool calls hang Long video or full songs: pass wait: false or a callback_url.
Client shows no tools Run npx @modelcontextprotocol/inspector npx -y @unifically/mcp-server. If the tools show there, the client config JSON is malformed.

Links

  • API docs: https://docs.unifically.com
  • API keys: https://unifically.com/api-keys
  • Models: https://unifically.com/models
  • MCP page: https://unifically.com/mcp
  • Support: support@unifically.com, Discord

License

MIT

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
unifically-mcp 怎么安装?

在客户端按下面的安装命令接入:https://mcp.unifically.com/mcp。装完在客户端配置里引用同一个包或端点。

unifically-mcp 怎么在 Claude Desktop、Claude、Cursor 里配置?

它的传输方式是HTTP · 远程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

unifically-mcp 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

unifically-mcp 需要 API Key 吗?

资料标注需要API Key认证,使用前准备好对应凭据,并按最小权限配置。

unifically-mcp 支持哪些客户端?

资料标注支持 Claude Desktop、Claude、Cursor、VS Code、Windsurf、Cline;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

unifically-mcp 能提供哪些能力?

资料显示能力标签包括 mcp、mcp server、remote mcp server、video generation、image generation、text to speech。具体工具清单以官方文档为准。

unifically-mcp 需要什么运行环境?

属于远程端点,不需要在本地装运行时。

unifically-mcp 是本地还是远程?

它是远程端点,连服务地址即可。传输方式为HTTP · 远程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 未标注。