DS IDE to Web

Let any AI tool talk to the DeepSeek chat you are already logged in to in your browser.

A small local app plus a browser extension turn your DeepSeek web session into two things other tools understand:

• an OpenAI-compatible API (http://127.0.0.1:8787/v1) for Cursor, Continue, Open WebUI, LangChain, scripts, and anything else that speaks the OpenAI format;

• an MCP server that gives any MCP client tools to ask DeepSeek, continue a chat, edit a message, and manage your chats.

 any AI / IDE / script
   |  OpenAI API (http://127.0.0.1:8787/v1)          MCP over stdio (mcp-stdio.mjs)
   v                                                       |
 bridge app (daemon.mjs)  <------- local HTTP -------------+
   |  WebSocket on 127.0.0.1, key + extension-origin check
   v
 browser extension  ->  your chat.deepseek.com tab (your login, your proof-of-work)

Read this first. The bridge drives the consumer web app with your own signed-in session. That is very likely outside DeepSeek's terms of service, and your account could be limited. If you need something dependable, use the official DeepSeek API. Treat this as a tool for personal experiments. DeepSeek's private web routes can also change without notice and break it.

Quick start

You need Node.js 20 or newer and Chrome, Edge, or Firefox 128+.

1. Install and start the bridge app (keep it running while you use it):

   npm run setup
   npm start

2. Build the extension:

   npm run build

   This writes bridge/build/chrome and bridge/build/firefox.

3. Load it in your browser.

   • Chrome or Edge: open chrome://extensions, turn on Developer mode, choose Load unpacked, and select the bridge/build/chrome folder itself (the one that contains manifest.json).

   • Firefox: open about:debugging#/runtime/this-firefox, choose Load Temporary Add-on, and pick bridge/build/firefox/manifest.json. Then open about:addons, select DeepSeek Bridge, and under Permissions allow access to chat.deepseek.com. Firefox removes temporary add-ons when it restarts.

4. Open https://chat.deepseek.com and sign in. If the tab was already open when you installed the extension, refresh it. A small status pill appears in the bottom right. The toolbar popup shows the connection and the details to copy.

Check that everything is connected:

curl -H "Authorization: Bearer deepseek-bridge" http://127.0.0.1:8787/api/status

The extension and the app share a preset key, deepseek-bridge, so there is nothing to configure.

Related MCP server: MCP DSH Nexus

For AI assistants: setting this up and using it

If you are an AI assistant helping a user with this repository, follow this.

Set up (you can do steps 1 to 3; the user must do step 4, because only they can install a browser extension and sign in):

1. Check node --version is 20 or newer.

2. Run npm run setup, then npm run build.

3. Start the bridge app in the background with npm start and leave it running. A second browser needs its own port: DS_BRIDGE_PORT=8788 npm start. See "Using two browsers at once".

4. Ask the user to load bridge/build/chrome (Chrome or Edge) or bridge/build/firefox/manifest.json (Firefox) as described in the quick start, sign in at https://chat.deepseek.com, and refresh that tab.

5. Verify with curl -H "Authorization: Bearer deepseek-bridge" http://127.0.0.1:8787/api/status. You need "extensionConnected": true and "loggedIn": true. If loggedIn is missing, read the error field.

The app has to be running whenever the bridge is used. The extension cannot start it, so if the popup says Bridge app not running, start it with npm start.

Use it through the MCP tools (or the OpenAI-compatible endpoint):

• Start a new chat by calling deepseek_ask without conversation_id or chat. Pass new_chat_title, and for AI-to-AI work pass preset: "collaborator". Keep the conversation_id from the reply and pass it on every follow-up. Send only the new message each time, because DeepSeek remembers the chat.

• To change a message you already sent, use deepseek_edit_message instead of sending a correction.

• Do not call deepseek_delete_chat unless the user explicitly asked to delete those specific chats. Deletion is permanent.

• Stop looping when you have what you need. Do not run an open-ended back and forth.

Errors the bridge returns, and what to do:

The extension popup

Use it from other tools

OpenAI-compatible

Point any OpenAI client at http://127.0.0.1:8787/v1 with the API key deepseek-bridge.

Extra request fields: conversation_id (continue a chat; every response includes one), chat (continue an existing chat by id or title), new_chat_title, ds_search: true for web search, ds_thinking: true|false, system, and preset.

Function and tool calling is not supported. When you start a new chat from a multi-message history, the messages are sent as one prompt. When you continue a chat, only your newest message is sent, because DeepSeek already has the history.

MCP

Add the bridge as a stdio server in your MCP client, using the absolute path to this folder:

{
  "mcpServers": {
    "deepseek": {
      "command": "node",
      "args": ["C:/path/to/DS-ide-to-web/bridge/server/mcp-stdio.mjs"]
    }
  }
}

The same actions are plain HTTP on the bridge: POST /api/ask, POST /api/edit, GET /api/chats, GET /api/chat?chat=, POST /api/chat/rename, POST /api/chat/pin, and POST /api/chat/delete. Chat titles match exactly first, then by unique partial match. An ambiguous title is refused with the candidates listed.

System prompts and AI-to-AI work

DeepSeek's web chat has no system role, so instructions for a new chat are sent inside its first message, clearly labelled. They are never repeated when you continue the chat.

Where the instructions come from, most specific first:

1. system text in the request.

2. A preset: collaborator (written for AI-to-AI work), reviewer, or concise.

3. The Prompt tab in the extension popup.

4. DS_BRIDGE_SYSTEM, or the text in ~/.ds-ide-to-web/system.txt.

DeepSeek titles a new chat from its first message, which would include these instructions, so pass new_chat_title when you set a system prompt.

Making your AI talk back and forth with DeepSeek. The AI you are using drives the loop. It calls deepseek_ask, reads the reply, does its own work with it, then calls deepseek_ask again with the conversation_id from the previous reply. The MCP server sends these instructions to the client, so most assistants pick the pattern up on their own. For example:

Start a chat with DeepSeek using the collaborator preset. Have it draft the design, review what it says, push back on anything weak, and iterate until it is solid. Stop after at most five rounds.

The bridge does not run the loop itself, because the other side of the conversation has to be an AI you choose.

Using two browsers at once

One bridge app talks to one browser at a time: a newer extension connection replaces the older one, so two browsers on the same port keep knocking each other off. To use Chrome and Firefox together, give each its own port and run one bridge app per port:

npm start                                        # Chrome, port 8787 (the default)
DS_BRIDGE_PORT=8788 npm start                    # Firefox, port 8788

On Windows PowerShell, set the variable first: $env:DS_BRIDGE_PORT = '8788'; npm start.

In the Firefox extension, open the popup, go to Settings, set the port to 8788, and save. Then use http://127.0.0.1:8788/v1 as the base URL for tools that should talk to Firefox, and set DS_BRIDGE_PORT=8788 in the environment of any MCP server entry that should use it.

Configuration

Security

• Everything listens on 127.0.0.1 only. Requests whose Host header is not localhost are refused, which blocks DNS rebinding.

• HTTP needs Authorization: Bearer <key> and refuses any request that carries a browser Origin header, so web pages cannot call it.

• The extension connection only accepts chrome-extension:// and moz-extension:// origins, plus the key.

• The extension can call a fixed list of DeepSeek chat routes only: list, history, rename, delete, pin, and stop. It cannot reach account settings, logout, or "delete all history".

• The default key is public on purpose, so any program on your own computer can use the bridge, and therefore your DeepSeek session, while the app runs. If that matters, set a custom key and stop the app when you are not using it.

Troubleshooting

Project layout

bridge/
  server/       the bridge app: HTTP + OpenAI API, MCP server, chat tools (Node, ESM)
  extension/    the browser extension: popup, background worker, page script
    src/vendor/ DeepSeek web client code reused from deepseek-pp (see NOTICE)
    test/       tests for that client code
    icons/      generated icons
    wasm/       DeepSeek's proof-of-work module
  tools/        make-icons.mjs, renders the extension icons
  build.mjs     bundles the extension for Chrome and Firefox

Development

npm run build       # build the extension for both browsers
npm run typecheck   # TypeScript check
npm run test        # extension tests (vitest) and server tests (node:test)

The server tests use a fake extension over a real WebSocket, so they need no browser.

License and credits

Apache-2.0, see LICENSE. The DeepSeek web client code under bridge/extension/src/vendor comes from zhu1090093659/deepseek-pp and was translated and modified for this project. Details are in NOTICE.