An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Z.AI to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Turn your AI agent into a creative and analytical powerhouse.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 12 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 12 available through Z.AI.

  1. 01

    Audio transcription

    This capability uses the GLM-ASR-2512 model to convert audio files into text. It supports wav and mp3 formats up to 25MB and allows for hotword support to improve accuracy.

  2. 02

    Chat completion

    This capability generates AI chat responses using various GLM models. It supports multimodal inputs like images, audio, and video.

  3. 03

    Generate image

    This capability creates high-quality images from text prompts using GLM-Image models. You can specify different sizes and quality settings for the output.

  4. 04

    Generate video

    This capability produces videos from text or images using CogVideoX or Vidu models. It returns a task ID so you can track the progress of your video.

Capability set02 / 03

05-08

4 capabilities in this set.

Part of 12 available through Z.AI.

  1. 05

    Get async result

    This capability checks the status of an ongoing image or video generation task. It returns the final URL once the processing is complete.

  2. 06

    Web search

    This capability searches the internet using an LLM-optimized engine. It returns up to 50 results including titles, URLs, and summaries.

  3. 07

    Agent chat

    This capability runs specialized Z.AI agents for tasks like multilingual translation, slide generation, and video special effects.

  4. 08

    Get conversation history

    This capability retrieves previous conversation data specifically for slide agent sessions.

Capability set03 / 03

09-12

4 capabilities in this set.

Part of 12 available through Z.AI.

  1. 09

    Layout parsing

    This capability extracts text and layout information from PDFs and images using GLM-OCR. It provides bounding boxes for tables, formulas, and images.

  2. 10

    Tokenize

    This capability counts the tokens in your messages to help you estimate costs and manage context limits.

  3. 11

    Web reader

    This capability reads and parses web page URLs into clean markdown or plain text.

  4. 12

    Generate image async

    This capability starts a long-running image generation task and returns a task ID for later retrieval.

Real work

What teams actually run

01

Rapid Prototyping

A product team asks their agent to generate a visual concept or a slide deck for a new feature.

02

Research Automation

A researcher uses the web search and web reader capabilities to gather and summarize information from multiple sites.

03

Data Extraction

A data analyst parses a large PDF document to extract specific tables and text into markdown.

04

Media Production

A creator generates a series of images or a short video clip using text prompts.

Automate a task

Put Z.AI to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Z.AI works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Z.AI to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

973ms average. Fast in production.

Z.AI is checked daily against the live service.

Daily averagePeak 1260ms
Oct 3Today
Fastest day
773ms
Slowest day
1260ms
14-day trend
Improving-20%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 12 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Z.AI, so you can see the experience inside your AI.

It does not authenticate your account with Z.AI. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Z.AI Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_YbDoY2kX4ZG9rzJgMpkdkPO2uOhqn2U6SvelxeRg/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Z.AI capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "zai-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_YbDoY2kX4ZG9rzJgMpkdkPO2uOhqn2U6SvelxeRg/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Z.AI in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Z.AI owners hand off.

This MCP is built for people who need to move between text, data, and media without leaving their chat interface.

  • 01

    Developers

    They use it to trigger complex API functions through natural language instead of manual coding.

  • 02

    Content Creators

    They use it to generate visual assets like images, videos, and slides directly in chat.

  • 03

    Data Teams

    They use it to automate audio transcription and document parsing for research.

FAQ

Questions Z.AI owners ask.

  • 01

    How do I get my Z.AI API key?

    Visit the Z.AI API Keys page to create or manage your API key. Once created, copy it and paste it into the API key field in the setup wizard. The key is used as a Bearer token in the Authorization header for all API requests.

  • 02

    Which Z.AI models are available?

    The MCP supports all Z.AI models: GLM-5.2, GLM-5.1, GLM-5-Turbo, GLM-4.7, GLM-4.7-flash, GLM-4.6, GLM-4.5 series for chat; GLM-Image and CogView-4 for image generation; CogVideoX-3 and Vidu for video generation; GLM-ASR-2512 for audio transcription; GLM-OCR for layout parsing; and search-prime for web search.

  • 03

    Can my AI generate images and videos?

    Yes! Use generate_image for synchronous image generation (returns URLs immediately), or generate_image_async for long-running tasks (returns a task ID. use get_async_result to retrieve). For video, use generate_video which always runs asynchronously. call get_async_result with the returned task ID to check status and get the video URL when complete.

  • 04

    Does the Z.AI MCP support multimodal inputs?

    Yes. The chat_completion capability supports multimodal inputs including text, images (image_url), video (video_url), and files (file_url) when using vision models like GLM-5V-Turbo. Pass the full messages array as JSON with the appropriate content types. The layout_parsing capability also supports both image and PDF inputs for OCR.

  • 05

    What is the base URL for Z.AI API calls?

    All Z.AI API calls are sent to https://api.z.ai/api. The engine automatically appends the correct path prefix (e.g. /paas/v4/ for platform APIs, /v1/ for agent APIs). When using the GLM Coding Plan, you may need to configure a dedicated endpoint. refer to the Z.AI documentation for details.

  • 06

    Can I use the Z.AI agents for translation and slide generation?

    Yes. The agent_chat capability supports three agent types: general_translation (multilingual translation with 40+ languages, auto-detection, glossary support), slides_glm_agent (one-click slide/poster generation from natural language), and vidu_template_agent (special effects video generation). After running the slides agent, use get_conversation_history with the conversation_id to retrieve generated file URLs.

  • 07

    Is there a rate limit on Z.AI APIs?

    Yes, Z.AI enforces rate limits that vary by model and subscription tier. Check the Z.AI Rate Limits page for your specific limits. If you exceed the rate limit, the API returns an error and the engine surfaces the error message. For high-volume use cases, consider using async endpoints and spacing out requests.

Explore

More in Developer Tools

Suggestions

Connect Z.AI to Claude, Cursor, ChatGPT & more