Polydev

io.github.polydev-ai由 GitHub 账号 polydev-ai 发布v1.12.0更新于 Nov 16, 2026

Every AI model, inside the app you already use: ask GPT, Claude, Gemini or Grok, and see what paid.

已验证Streamable HTTP可网页运行网页搜索与抓取媒体与设计AI 与机器学习

概览

AI 生成的概览

让助手在自身应用内调用其他 AI 模型(GPT、Claude、Gemini、Grok),并显示每个回答由哪种凭据付费。

可以做什么
  • 用提示词询问单个模型、多个模型或默认模型组,返回每个回答并标注由什么付费;旧名称 get_perspectives 行为相同。
  • 列出当前可用的模型及各自的付费来源,并在本地服务器上查看或发起 ChatGPT 套餐登录。
  • 登录 Polydev 并查看本机哪些来源已就绪。
  • 通过 xAI 的 Grok 搜索 X(Twitter)上的近期帖子和讨论。
  • 对收到的回答排序(最佳在前),并用 OpenAI 或 Google 模型生成图片。
适用场景
适合在不离开当前应用的情况下获取另一个模型的意见,例如让 GPT 审查一次数据库迁移,或让多个模型比较方案。也适合对比回答并记录哪一个最有帮助。
运行要求
可使用托管端点并通过 OAuth 登录,或使用 npm 包 polydev-ai 在本地运行,需要 Node.js 20 或更高版本以及免费的 Polydev 账户。本地登录需要浏览器,无浏览器的机器可改用环境变量 POLYDEV_USER_TOKEN(pd_ 开头的令牌)。search_x 需要自备 xAI API 密钥;使用 ChatGPT 套餐需在本地服务器上完成 Continue with ChatGPT。
安装前请注意
提示词会发送给你选择的模型提供商,只应包含愿意分享的内容。费用由你自己的 ChatGPT 套餐、本地 CLI 套餐或自备的提供商 API 密钥承担;免费额度为 10 次请求、总额不超过 1 美元,且不含 search_x。排序结果会进入公开排行榜。本地服务器会调用你已登录的 Claude Code 或 Codex CLI,令牌会保存在本机磁盘上。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Polydev,将其添加到工作区。
  2. 连接 所需的 凭据。它们会被私密存储,绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.polydev-ai%2Fpolydev/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。 客户端会在首次连接时完成 OAuth 登录。

{
  "mcpServers": {
    "polydev": {
      "type": "http",
      "url": "https://polydev.ai/mcp"
    }
  }
}

README

Polydev

[Polydev logo]

Every AI model, inside the app you already use.
Ask GPT from Claude. Ask Claude from ChatGPT. Make an image with Nano Banana from Codex.

[npm version] [License: Apache-2.0]


What it is

Polydev is an MCP server: a tool your app calls. It doesn't replace your app's model.

Claude, ChatGPT, Claude Code, Codex, Cursor, Copilot, Cline, Windsurf, Zed and other MCP clients keep their own model and their own sign-in. When you want another model for a task, say "have GPT check this migration", the app calls Polydev, which asks that model and returns the answer. Name one model, several, or none to use your default set.

Your app (its own model) -> Polydev ask_model -> GPT, Claude, Gemini, Grok... -> answer + what paid for it

Every answer ends with a "Paid by:" line, so you always know whether your ChatGPT plan, your own key or Polydev's free requests paid for it.

Tools:

ToolWhat it does
ask_modelSend a prompt to one model (model), a list (models) or your default set, and get each answer with what paid for it. get_perspectives is the older name and still works
list_modelsList the models you can reach and what pays for each
search_xSearch X (Twitter) with xAI's Grok (needs your own xAI key)
rank_perspectivesRecord which answer helped most; rankings feed the public leaderboard
generate_imageMake an image with OpenAI or Google models, such as Nano Banana (local server only)
connect_chatgpt_plan / chatgpt_plan_statusContinue with ChatGPT so your ChatGPT plan pays for OpenAI models (local server only)
login / get_auth_statusSign in to Polydev in the browser; show what's connected (local server only)

Add it without installing anything

Polydev is a hosted MCP server. Add this URL to your app and sign in once (OAuth):

https://polydev.ai/mcp
  • Claude (web, desktop, mobile): Settings → Connectors → Add custom connector, paste the URL, then Connect.
  • ChatGPT: add a custom MCP server in the apps settings, paste the URL, choose OAuth.
  • Claude Code: claude mcp add --transport http polydev https://polydev.ai/mcp, then /mcp to sign in.
  • Codex: codex mcp add polydev --url https://polydev.ai/mcp, then codex mcp login polydev.
  • Cursor, VS Code, Windsurf and others: one-click links and config at polydev.ai/install.

The hosted server answers with your API keys, your OpenRouter key or the free requests. To also use your ChatGPT plan, the Claude Code or Codex you're signed in to on this machine, and image models, install the local server below. (ChatGPT plan use on the hosted server is waiting on OpenAI's approval.)


Install locally (npm)

You need Node.js 20 or newer and a free Polydev account.

Claude Code

sh
claude mcp add polydev -- npx -y polydev-ai@latest

Codex

Add to ~/.codex/config.toml:

toml
[mcp_servers.polydev]command = "npx"args = ["-y", "polydev-ai@latest"]tool_timeout_sec = 300

Some models take a while to answer, so raise the tool timeout.

Cursor, Cline, Windsurf

Add to your client's MCP config (for Cursor, ~/.cursor/mcp.json):

json
{  "mcpServers": {    "polydev": {      "command": "npx",      "args": ["-y", "polydev-ai@latest"]    }  }}

GitHub Copilot in VS Code

Add to .vscode/mcp.json:

json
{  "servers": {    "polydev": {      "type": "stdio",      "command": "npx",      "args": ["-y", "polydev-ai@latest"]    }  }}

Zed and other MCP clients

Use the same command, npx -y polydev-ai@latest, as a stdio server in the client's MCP settings.


Sign in

The hosted server signs you in with OAuth when your app first connects. For the local server, ask your agent to run the Polydev login tool. It opens your browser, and once you sign in the token is saved on this machine (in ~/.polydev.env).

Other ways:

  • From a terminal: npx -p polydev-ai polydev-login
  • Advanced, for machines without a browser: copy a token from polydev.ai/dashboard/mcp-tokens and set it in the server's environment:
json
"env": { "POLYDEV_USER_TOKEN": "pd_your_token_here" }

In sandboxes without a browser, pass the token to the login tool as user_token.

Continue with ChatGPT (local server)

To let your ChatGPT plan (Plus or Pro) pay for OpenAI models, ask your app to run connect_chatgpt_plan, or from a terminal:

sh
npx polydev-ai chatgpt login     # also: chatgpt status | chatgpt models | chatgpt logout

This uses OpenAI's Sign in with ChatGPT. Your tokens stay on this machine in ~/.polydev (file mode 0600) and never reach Polydev's servers. Usage counts against your plan's limits, which you can set in ChatGPT's usage settings. If you hit the limit, Polydev says so and the answer comes from your API key or the free requests instead.


Usage

Ask your agent in plain words:

Have GPT check this migration before I run it on prod.Ask Gemini and Grok whether Redis or Postgres suits session storage here.Make a 1200x630 cover for this post with Nano Banana.

Or call the tool directly:

json
{  "tool": "ask_model",  "arguments": {    "model": "gpt-6.1-sol",    "prompt": "Check this migration for anything that could lock the table: <sql>"  }}

Include the relevant code, errors and constraints in the prompt. The other model only sees what you send.


Cost: free

Polydev has no plans, tiers or credits, and it charges nothing. The tokens are paid by your own access:

  • Your ChatGPT plan (local server), through Continue with ChatGPT. See above.
  • Your local CLIs (local server). Polydev runs the Claude Code (claude -p) or Codex you're already signed in to, unmodified and under your own login, with your settings, hooks and MCP servers turned off for that call. Polydev never reads their credentials. These calls count against your own plan's limits. Polydev skips the CLI of the app that called it.
  • Your own API keys. Add keys for OpenAI, Anthropic, Google, xAI, OpenRouter, Cerebras and others at polydev.ai/dashboard/models. The provider bills you directly.
  • A one-time free allowance. Every account gets 10 requests on Polydev's keys, never more than $1 in total, served by each provider's newest low-cost model. search_x is not part of it.

Models come from a live catalogue that is updated nightly. See polydev.ai/docs for the current list.


Privacy

Your prompts go to the model providers you chose. Prompts from connected apps are used only to answer you: never for training, never in datasets, never sold. Prompt and response text is deleted after 30 days. Disconnect an app at any time in Dashboard → Connected apps. Full policy: polydev.ai/privacy.


Links

License

Apache-2.0.

来源:README.md,提交 095bb3b

工具

10

get_auth_status

Polydev status

Show whether this machine is signed in to Polydev, which sources on this machine are ready (Claude Code, Codex, ChatGPT plan) and the configured models. When this machine is not signed in, it opens Polydev sign-in in the browser.

输入参数user_token

login

Sign in to Polydev

Sign in to Polydev in your browser and save the token on this machine, so you do not copy it by hand. In sandboxes without a browser, pass user_token instead.

输入参数user_tokenopen_browsertimeout_seconds

ask_model

Ask models

Send a prompt to one or more AI models and return each answer, labelled with what paid for it. With model or models, those models are asked. Without them, your default set is asked: sources on this machine first (your ChatGPT plan for OpenAI models when connected, then Claude Code and Codex under your own login, never the agent that called it), then models through Polydev with your own API keys, OpenRouter or Polydev free requests.

输入参数modelmodelsprompt必填user_token

get_perspectives

Ask models (old name)

Old name of ask_model. Same inputs and the same behaviour.

输入参数modelmodelsprompt必填user_token

list_models

List models

List the models this user can reach right now and what pays for each: the ChatGPT plan, Claude Code and Codex on this machine, and models through Polydev.

无需输入参数。

chatgpt_plan_status

ChatGPT plan status

Show whether your ChatGPT plan is connected on this machine for OpenAI models, and how to connect or disconnect it.

无需输入参数。

connect_chatgpt_plan

Continue with ChatGPT

Continue with ChatGPT: start ChatGPT sign-in so that OpenAI models asked through ask_model use your ChatGPT plan. Returns the sign-in link right away (it also tries to open the browser); call chatgpt_plan_status afterwards for the result. The sign-in and its tokens stay on this machine.

输入参数timeout_seconds

rank_perspectives

Rank answers

Rank the answers you got from ask_model, best first, when the user asks for it or agrees. Rankings feed the public leaderboard at https://www.polydev.ai/leaderboard. Pass your own model ID as base_model so the ranking records which model judged.

输入参数base_modelmodel_scoresfeedback_textranked_models必填

search_x

Search X

Search X (Twitter) for recent posts and discussions with xAI's Grok. Needs your own xAI API key, added at https://www.polydev.ai/dashboard/models; it is not part of the free allowance. Returns a summary plus links to the posts.

输入参数modelquery必填user_token

generate_image

Generate image

Generate an image with OpenAI or Google Gemini. Uses your own API key if you added one at https://www.polydev.ai/dashboard/models; otherwise one image takes one request from your free allowance (provider default model, standard settings). Saves a PNG under ~/.polydev/images.

输入参数sizeprompt必填qualityprovideruser_token

版本历史

2
  1. v1.12.0最新Nov 7, 2026
  2. v1.8.72Sep 16, 2026

评分

已满足适用检查项的 90%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。