Integration · Developer tools

Connect Claude & ChatGPT to Dify

Ask your AI to put a question to one of your Dify apps, run a Dify workflow with the inputs you give, or look something up in a knowledge base. It can read conversations and workflow logs, manage knowledge base documents and chunks, and keep your saved question-and-answer annotations up to date.

Connect Dify free

Free plan, no credit card. Takes about a minute.

Try asking

“Ask our support bot how refunds work.”
The AI sends the question to your Dify chat app and returns its reply. It can keep going in the same conversation.
“Run the lead scoring workflow for Acme.”
It reads the workflow's input form, runs it with your values and returns the outputs.
“Which workflow runs failed today?”
It lists workflow logs filtered by status and date, and opens a run to see its inputs and outputs.

What your AI can do

Apps and workflows

Chat with a chat app, run a text generation app or a workflow, and read workflow runs and logs.

Knowledge bases

List, create and search knowledge bases, add or update documents from text, and edit their chunks.

Conversations and feedback

Read, rename and delete conversations, rate replies, read user feedback and manage annotations.

“Search the product knowledge base for warranty terms.”
It searches the knowledge base and returns the best-matching chunks.
“Add this FAQ text as a new document in the Help Center knowledge base.”
It creates the document from plain text, and you can check its indexing status afterwards.
“What feedback have users left on the app's answers?”
It lists the like and dislike feedback end users have given on the app's replies.

77 tools for Dify

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

add_document_chunksChanges dataAdd chunks to a document. Pass `dataset_id`, `document_id` and `segments` (each with `content`, optional `answer` and `keywords`).
create_annotationChanges dataAdd a saved reply the app can use: pass `question` and `answer`.
create_bindingChanges dataCreate a new binding. Required: tag ids or target id. API summary: Create Tag Binding.
create_completionVisible to othersRun the connected text-generation app once. Pass `inputs` and a `user` ID; use `response_mode` blocking.
create_dataset_metadataChanges dataCreate a new metadata for a dataset. Required: name or type. API summary: Create Metadata Field.
create_document_from_textChanges dataAdd a document to a knowledge base from plain text. Pass `dataset_id`, `name` and `text`; `indexing_technique` is needed for the first document in an empty knowledge base.
create_knowledge_baseChanges dataCreate an empty knowledge base with `name` and optional `description`.
create_message_stopVisible to othersCreate a new stop for a message. Required: user. Has effects visible outside this system. API summary: Stop Chat Message Generation.
create_metadataVisible to othersCreate a new metadata. Required: operation data. Has effects visible outside this system. API summary: Update Document Metadata in Batch.
create_node_runChanges dataCreate a new run for a node. Required: datasource type, inputs or is published. API summary: Run Datasource Node.
create_runChanges dataCreate a new run. Required: datasource info list, datasource type, inputs, is published, response mode or start node id. API summary: Run Pipeline.
create_segment_child_chunkChanges dataCreate a new child chunk for a segment. Required: content. Search child chunks first to avoid duplicates. API summary: Create Child Chunk.
create_tagChanges dataCreate a new tag. Required: name. Search tags first to avoid duplicates. API summary: Create Knowledge Tag.
create_task_stopChanges dataCreate a new stop for a task. Required: user. API summary: Stop Workflow Task.
create_text_to_audioChanges dataCreate a new text to audio. API summary: Convert Text to Audio.
create_unbindingChanges dataCreate a new unbinding. Required: target id. API summary: Delete Tag Binding.
create_workflow_runChanges dataCreate a new run for a workflow. Required: inputs or user. API summary: Run Workflow by ID.
delete_annotationDeletesPermanently delete a annotation by annotation id. Destructive action; may require approval. API summary: Delete Annotation.
delete_conversationDeletesPermanently delete a conversation. Pass the conversation ID in `message_id` and the `user` ID.
delete_datasetDeletesPermanently delete a dataset by dataset id. Destructive action; may require approval. API summary: Delete Knowledge Base.
delete_dataset_metadataDeletesPermanently delete a metadata by metadata id. Destructive action; may require approval. API summary: Delete Metadata Field.
delete_documentDeletesPermanently delete a document from a knowledge base. Pass `dataset_id` and `document_id`.
delete_document_segmentDeletesPermanently delete a segment by segment id. Destructive action; may require approval. API summary: Delete Chunk.
delete_segment_child_chunkDeletesPermanently delete a child chunk by child chunk id. Destructive action; may require approval. API summary: Delete Child Chunk.
delete_tagsMoves moneyPermanently delete a tag. Financial or irreversible action; may require approval. API summary: Delete Knowledge Tag.
download_documentDownload the document for a document. API summary: Download Document.
download_document_zipChanges dataDownload the document for a document. API summary: Download Documents as ZIP.
get_annotation_reply_statusGet one status for a annotation reply by job id. API summary: Get Annotation Reply Job Status.
get_app_infoGet the connected Dify app's name, description and mode.
get_app_parametersGet the connected app's input form and settings. Check this first to learn which `inputs` variables chat, completion and workflow calls expect.
get_documentGet one document's details and indexing status. Pass `dataset_id` and `document_id`.
get_document_2Get one document by file id. API summary: Download File.
get_document_segmentGet one segment for a document by segment id. API summary: Get Chunk.
get_human_inputGet one human input by form token. API summary: Get Human Input Form.
get_knowledge_baseGet one knowledge base's settings and stats by `dataset_id`.
get_model_typeGet one model type by model type. API summary: Get Available Models.
get_userGet one user by user id. API summary: Get End User Info.
get_workflow_runGet one workflow run's status, inputs and outputs by `workflow_run_id`.
list_annotationsList the app's saved question-and-answer annotations, optionally filtered by `keyword`.
list_app_feedbackList the like and dislike feedback end users have given on the app's replies.
list_built_insList built ins. API summary: Get Built-in Metadata Fields.
list_conversation_messagesRead the messages of one conversation. Pass `conversation_id` and the same `user` ID used in the chat.
list_conversation_variablesList messages for a message. Optional filters: user, last id or variable name. Results are paginated. API summary: List Conversation Variables.
list_conversationsList chat conversations for a `user` ID, newest first by default.
list_dataset_metadataList metadata for a dataset. API summary: List Metadata Fields.
list_datasource_pluginsList datasource plugins. Optional filters: is published.
list_document_chunksList the chunks of a document. Pass `dataset_id` and `document_id`, optionally a `keyword`.
list_document_indexing_statusesList indexing statuses for a document. API summary: Get Document Indexing Status.
list_documentsList the documents in a knowledge base by `dataset_id`, filtered by `keyword` or `status`.
list_knowledge_basesList knowledge bases, optionally filtered by `keyword` or `tag_ids`. Use this to find a `dataset_id`.
list_message_suggestedsList suggesteds for a message. Optional filters: user. API summary: Get Next Suggested Questions.
list_metaList meta. API summary: Get App Meta.
list_sitesList sites. API summary: Get App WebApp Settings.
list_tagsList tags. API summary: List Knowledge Tags.
list_workflow_eventsList events for a workflow. Optional filters: user, include state snapshot or continue on pause. API summary: Stream Workflow Events.
list_workflow_logsList past workflow runs, filtered by `keyword`, `status` or creation dates.
rate_messageVisible to othersRate an app reply as like or dislike. Pass `message_id`, `user`, `rating` and optional `content`.
rename_conversationChanges dataRename a conversation. Pass `conversation_id`, `user`, and a new `name` (or set `auto_generate` to true).
run_workflowChanges dataRun the connected workflow app. Pass `inputs` with the workflow's variables and a `user` ID; use `response_mode` blocking. Returns the run's outputs.
search_dataset_tagsSearch tags for a dataset. Use this to find existing tags before creating a new tag. API summary: Get Knowledge Base Tags.
search_knowledge_baseChanges dataSearch a knowledge base for passages relevant to `query`. Pass `dataset_id`. Returns the best-matching chunks.
search_segment_child_chunksSearch child chunks for a segment by keyword. Use this to find existing child chunks before creating a new child chunk. Results are paginated. API summary: List Child Chunks.
send_chat_messageVisible to othersSend a message to the connected chat app and get its reply. Pass `query`, `inputs` (an object, empty if the app has no variables), a stable `user` ID, and `conversation_id` to continue a chat. Use `response_mode` blocking.
stop_completion_message_generationChanges dataCreate a new stop for a message. Required: user. API summary: Stop Completion Message Generation.
submit_human_inputDeletesSubmit a human input (form token). Destructive action; may require approval. API summary: Submit Human Input Form.
update_annotationChanges dataChange an annotation's `question` and `answer` by `annotation_id`.
update_annotation_replyChanges dataUpdate an existing annotation reply identified by action. API summary: Configure Annotation Reply.
update_built_inChanges dataUpdate an existing built in identified by action. API summary: Update Built-in Metadata Field.
update_dataset_documentChanges dataUpdate an existing document identified by document id. Only the fields you pass are changed. API summary: Update Document.
update_dataset_metadataChanges dataUpdate an existing metadata identified by metadata id. Only the fields you pass are changed. API summary: Update Metadata Field.
update_document_chunkChanges dataEdit one chunk's content, answer, keywords or enabled state. Pass `dataset_id`, `document_id`, `segment_id` and `segment`.
update_document_textChanges dataReplace a document's name or text. Pass `dataset_id`, `document_id`, and new `name` and/or `text`. The document is re-indexed.
update_knowledge_baseChanges dataUpdate a knowledge base's `name`, `description` or `permission` by `dataset_id`.
update_messageChanges dataUpdate an existing message identified by message id. API summary: Update Conversation Variable.
update_segment_child_chunkChanges dataUpdate an existing child chunk identified by child chunk id. Only the fields you pass are changed. API summary: Update Child Chunk.
update_statusVisible to othersUpdate an existing status identified by action. Only the fields you pass are changed. Has effects visible outside this system. API summary: Update Document Status in Batch.
update_tagsVisible to othersUpdate an existing tag. Only the fields you pass are changed. Has effects visible outside this system. API summary: Update Knowledge Tag.

Set up in three steps

1
Pick the app
Create a free HeyMyApps account and choose Dify from the app list.
2
Paste your key
Paste a Dify API key. For an app, open it in Dify, go to its API Access page and create a key. Each key works for that one app. For knowledge bases, go to Knowledge, click Service API in the top right and create a key there. The connection uses Dify Cloud (api.dify.ai).
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in Dify?

With an app key, the AI can read the app's info and input form, send chat messages, run completions and workflows, read workflow runs and logs, and work with conversations, feedback and annotations. With a knowledge key, it can list, create, update and search knowledge bases and add, update, delete and chunk documents.

Does the AI see my Dify API key?

No. Your Dify API key is encrypted at rest and never shown to the AI. After you save it, it is not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, so you can start with reading and searching only. Deleting a document or a conversation is permanent, and both can require your approval before they run. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT go to Settings › Apps & Connectors › Advanced and turn on Developer mode, then add your HeyMyApps link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

HeyMyApps has a free plan with no credit card required. Paid plans bill per completed task. You also need your own Dify account.

Why does Dify use different keys for apps and knowledge bases?

In Dify, an app API key works for one app, and knowledge bases have their own Service API key. With an app key, the AI can chat with or run that app. With a knowledge key, it can work with your knowledge bases. Use the key that fits what you want the AI to do.