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.

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.

Does the Z.AI MCP support multimodal inputs?

Yes. The `chat_completion` tool 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` tool also supports both image and PDF inputs for OCR.

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.

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](https://z.ai/manage-apikey/rate-limits) 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.

Z.AI MCP Connector for Claude

A+

Access the full Z.AI platform from any AI agent — chat completions with GLM models, image and video generation, audio transcription, OCR, web search, and agent tools.

12 tools Official Updated Oct 1, 2026 Official Vinkius Partner

More Details Connect to Claude

Connect your Z.AI API key to any AI agent and unlock the full power of the Z.AI platform through natural conversation.

What you can do

Chat Completions — Generate AI responses using GLM-5.2, GLM-4.7, GLM-4.7-flash, and other models with support for multimodal inputs (text, images, audio, video, files), tool use, and streaming
Image Generation — Create high-quality images from text prompts using GLM-Image or CogView-4 models, with synchronous and asynchronous modes
Video Generation — Generate videos from text or images using CogVideoX-3 or Vidu models, with optional audio, quality modes, and resolution control
Audio Transcription — Convert speech to text using the GLM-ASR-2512 model with hotword support and streaming output
OCR & Layout Parsing — Extract text from images and PDFs using the GLM-OCR model, with detailed layout information and visualization
Web Search — Search the web with Z.AI's LLM-optimized search engine, returning titles, URLs, summaries, and favicons
Web Reader — Read and parse any web page URL into clean markdown or text with metadata extraction
Tokenization — Count tokens for messages to estimate costs and manage context windows
Agent Tools — Run translation (40+ languages), slide/poster generation, and special effects video agents
Conversation History — Retrieve prior conversation results from slide/poster agent sessions

How it works

Subscribe to this server
Enter your Z.AI API key (create one at https://z.ai/manage-apikey/apikey-list)
Start generating content from Claude, Cursor, or any MCP-compatible client

Your AI acts as a gateway to the entire Z.AI multimodal AI platform — generate text, images, videos, transcribe audio, parse documents, and search the web without writing a single line of code.

Who is this for?

Developers — integrate Z.AI capabilities into your apps via natural language instead of reading API docs
Content Creators — generate images, videos, and slides from text prompts directly in your AI chat
Data Teams — transcribe audio, parse documents with OCR, and search the web for research
Product Teams — prototype AI features quickly by asking your agent to call Z.AI APIs

llmglmimage-generationvideo-generationaudio-transcriptionocrweb-searchmultimodal

12 tools expose this connector's capabilities to your AI agent.

audio_transcription

AI's ASR model. Supports .wav and .mp3 files up to 25MB and 30 seconds. Can provide hotwords for domain-specific vocabulary and context prompts for long-form transcription. Supports streaming output. Transcribe audio files to text using the GLM-ASR-2512 model

chat_completion

2, GLM-4.7, or other available models. Supports multimodal inputs (text, images, audio, video, files), configurable parameters (temperature, max_tokens, tools), and both streaming and non-streaming modes. Pass the full request body as JSON including model, messages, and optional parameters. Generate AI chat completions using Z.AI GLM models

generate_image

Returns image URLs (temporary, expire after 30 days). Specify model, prompt, and optional size/quality. GLM-Image recommended sizes: 1280x1280, 1568x1056, 1056x1568, 1472x1088, 1088x1472, 1728x960, 960x1728. Generate high-quality images from text prompts using GLM-Image models

generate_video

Supports text-to-video, image-to-video, and first/last frame-to-video. Returns a task ID — use get_async_result to check status and retrieve the video URL. Specify model, prompt, and optional quality/size/fps/duration. Generate videos from text prompts or images using CogVideoX or Vidu models

get_async_result

Returns task_status (PROCESSING, SUCCESS, FAIL) and the generated image or video URLs when complete. Use this after generate_image_async or generate_video returns a task ID. Retrieve the result of an asynchronous image or video generation task

web_search

Supports filtering by domain whitelist and time range (oneDay, oneWeek, oneMonth, oneYear, noLimit). Returns up to 50 results per search. Search the web using Z.AI's LLM-optimized search engine

agent_chat

AI agents including: 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). Pass the full agent request body as JSON including agent_id and messages. Run Z.AI agents for translation, slide generation, or poster creation

get_conversation_history

Only supports slides_glm_agent. Use the conversation_id from a prior agent_chat response. Retrieve the conversation history for a Z.AI slide agent session

layout_parsing

Returns recognized text in Markdown format, detailed layout information (bounding boxes for text, images, formulas, tables), and optional visualization results. Supports PDF, JPG, PNG formats. PDF up to 50MB/30 pages, images up to 10MB. Parse document layouts and extract text using the GLM-OCR model

tokenize

Returns prompt_tokens, image_tokens, video_tokens, and total_tokens. Useful for text length evaluation, model input estimation, context truncation, and cost calculation. Supports glm-4.6, glm-4.6v, and glm-4.5 models. Count tokens for given messages using Z.AI models

web_reader

Supports markdown and text output formats, cache control, image retention, and optional summaries for images and links. Read and parse the content of a web page URL

generate_image_async

Use get_async_result with the task ID to check status and retrieve the generated image. Only supports glm-image model. Use this for long-running generation tasks. Generate images asynchronously — returns a task ID for later retrieval

Visit the [Z.AI API Keys page](https://z.ai/manage-apikey/apikey-list) 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.

Related Connectors

HeyGen MCP

12 tools Official

Create AI-generated videos with realistic digital avatars that speak in any language for training, marketing, and communication.

A+ View details →

Vadoo MCP

6 tools Official

Host and optimize video content for the web with AI-powered SEO, automatic subtitles, and engagement analytics for creators.

A+ View details →

AiMasher MCP

10 tools Official

Generate marketing content, social media posts, and creative assets using multiple AI models in a single unified workspace.

A+ View details →

Zyte MCP

3 tools Official

Extract structured web data, perform browser automation, and fetch search engine results directly through the Zyte API.

A+ View details →