Integration

Zhipu AI integration

Chinese AI platform featuring GLM (General Language Model) series. Access powerful LLMs for Chinese and English with strong performance on reasoning, coding, and conversation. Features include embeddings, vision capabilities, and agent functionalities.

Connect Zhipu AI How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Zhipu AI.Built from the 8 Zhipu AI tools below, on the connection you add once.

Common Zhipu AI use cases

Building image Q&A systems
Setting up RAG applications
Building RAG-enabled chatbots
Polling async task completion
Processing batch chat requests
Building Chinese-language chatbots
Creating Chinese-prompt based artwork
Building Chinese semantic search engines
Generating marketing visuals
Creating document Q&A systems

What you can do with Zhipu AI

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Chat, 2 operations

chat_completionsChat completionsPOSTGenerate conversational responses using Zhipu's GLM series models.
chat_completions_visionChat completions visionPOSTAnalyze images and engage in visual conversations with GLM-4V vision model.

Task, 2 operations

async_invokeAsync invokePOSTSubmit long-running chat completion requests for asynchronous processing.
get_async_resultGet async resultGETRetrieve results and status of asynchronous processing tasks.

Embedding, 1 operation

embeddingsEmbeddingsPOSTConvert text into semantic vector embeddings optimized for Chinese.

File, 1 operation

file_uploadFile uploadPOSTUpload documents for retrieval-augmented generation and knowledge bases.

Image, 1 operation

images_generationsImages generationsPOSTCreate images from text descriptions using CogView generation models.

Knowledge base, 1 operation

knowledge_base_createKnowledge base createPOSTInitialize a new knowledge base for document storage and retrieval.

Use Zhipu AI from Claude Code, Cursor or Codex

Connect Zhipu AI in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Zhipu AI operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Zhipu AI

Create your workspace
Sign up free. Nothing to install.
Connect Zhipu AI once
Add your Zhipu AI connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Zhipu AI integration FAQ

What can you do with the Zhipu AI integration?

LiveContext exposes 8 operations on Zhipu AI, covering chat, task, embedding and file. Common uses include Building image Q&A systems, Setting up RAG applications and Building RAG-enabled chatbots.