What can you do with the Dify integration?

LiveContext exposes 35 operations on Dify, covering annotation, run, stop and conversation.

Dify integration

Dify is a self-hosted platform for building LLM applications. This is the application side of its Service API: send a message to a chat, agent or chatflow app and read the answer, run a workflow app and read its outputs or stop a running task, browse conversations, their messages, their variables and the files attached to them, upload a file for an app to use, transcribe audio or speak text, record per-message feedback, curate the annotated question and answer pairs an app replies from, read the app's own parameters, metadata and web-app settings, and answer a human-input form a paused chatflow is waiting on. The host is part of the credential: use api.dify.ai for Dify Cloud, or your own hostname for a self-hosted install. Authentication is an application API key sent as a bearer token in the Authorization header, and each key belongs to ONE app, so the app being called is the one the key was issued for. Knowledge base endpoints take a different key and live in the separate Dify Knowledge API.

35 toolsTokenAPI docs

Connect Dify How integrations work

What you can do with Dify

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.

Annotation, 4 operations

POSTcreate_annotation
Create Annotation.
DELETEdelete_annotation
Delete Annotation.
GETlist_annotations
List Annotations.
PUTupdate_annotation
Update Annotation.

Run, 3 operations

GETget_workflow_run
Get Workflow Run Detail.
POSTrun_workflow
Run Workflow.
POSTrun_workflow_by_id
Run Workflow by ID.

Stop, 3 operations

POSTstop_chat_message
Stop Chat Message Generation.
POSTstop_completion_message
Stop Completion Message Generation.
POSTstop_workflow_task
Stop Workflow Task.

Conversation, 2 operations

DELETEdelete_conversation
Delete Conversation.
GETlist_conversations
List Conversations.

Feedback, 2 operations

GETlist_app_feedbacks
List App Feedbacks.
POSTsubmit_message_feedback
Submit Message Feedback.

Human input, 2 operations

GETget_human_input_form
Get Human Input Form.
POSTsubmit_human_input_form
Submit Human Input Form.

Variable, 2 operations

GETlist_conversation_variables
List Conversation Variables.
PUTupdate_conversation_variable
Update Conversation Variable.

Annotation reply, 1 operation

POSTconfigure_annotation_reply
Configure Annotation Reply.

Audio to text, 1 operation

POSTtranscribe_audio
Convert Audio to Text.

Chat message, 1 operation

POSTsend_chat_message
Send Chat Message.

Completion message, 1 operation

POSTsend_completion_message
Send Completion Message.

End user, 1 operation

GETget_end_user
Get End User Info.

Info, 1 operation

GETget_app_info
Get App Info.

Log, 1 operation

GETlist_workflow_logs
List Workflow Logs.

Message, 1 operation

GETlist_conversation_messages
List Conversation Messages.

Meta, 1 operation

GETget_app_meta
Get App Meta.

Name, 1 operation

POSTrename_conversation
Rename Conversation.

Parameter, 1 operation

GETget_app_parameters
Get App Parameters.

Preview, 1 operation

GETdownload_file
Download File.

Site, 1 operation

GETget_web_app_settings
Get App WebApp Settings.

Statu, 1 operation

GETget_annotation_reply_job_status
Get Annotation Reply Job Status.

Suggested, 1 operation

GETlist_suggested_questions
Get Next Suggested Questions.

Text to audio, 1 operation

POSTtext_to_speech
Convert Text to Audio.

Upload, 1 operation

POSTupload_file
Upload File.

Use Dify from Claude Code, Cursor or Codex

Connect Dify in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Dify 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 Dify

Create your workspace
Sign up free. Nothing to install.
Connect Dify once
Add your Dify 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.