Integration · Developer tools

Connect Claude & ChatGPT to FlowiseAI

Ask your AI to put a question to one of your Flowise chatflows, search a document store, or check what users said in last week's chats. It can read feedback and captured leads, edit document chunks, and update chatflows, assistants and variables in your Flowise Cloud or self-hosted instance.

Connect FlowiseAI free

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

Try asking

“Ask our support chatflow how returns work and show me the answer.”
The AI finds the chatflow, sends it the question and returns the answer the flow gives.
“What does our product knowledge base say about warranty?”
It queries the document store and returns the most relevant chunks.
“Which answers got thumbs down in the support bot this week?”
It lists the message feedback for the chatflow in that date range, with the chats it belongs to.

What your AI can do

Chatflows

List chatflows and agentflows, send a question to one and get its answer, and update names, categories and deployed or public settings.

Document stores

Create and list document stores, search their content, and read or edit the text chunks of each loader.

Chats, leads and settings

Read chat messages, feedback and captured leads, and view or update assistants, custom tools and variables.

“Show me the leads the website chatbot captured.”
It lists the leads captured by that chatflow, with name, email and phone.
“Fix the opening hours in chunk 12 of the FAQ loader.”
It reads the loader's chunks, finds the one with the opening hours and updates its text.
“Change the sales assistant's instructions to always answer in Danish.”
It reads the assistant and updates its instructions. Only the fields you change are touched.

21 tools for FlowiseAI

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

create_document_storeChanges dataCreate an empty document store with a `name` and optional `description`.
get_assistantGet one assistant by its ID, including model, instructions and tools.
get_chatflowGet one chatflow by `chatflow_id`, including its name, type, deployed and public status.
get_document_storeGet one document store by its ID (`document_id`), including its loaders and status.
get_toolGet one custom tool by its ID.
list_assistantsList all assistants.
list_chat_messagesList chat messages for a chatflow (its ID as `message_id`), filtered by chat_id, chat_type, date range or feedback, and sorted by `order`.
list_chatflowsList all chatflows and agentflows in your Flowise instance. Use to find a chatflow ID.
list_document_chunksList the text chunks of one document loader in a store: `store_id`, `loader_id` and `page_no`.
list_document_storesList all document stores (knowledge bases). Use to find a store ID.
list_leadsList the leads (name, email, phone) captured by a chatflow; pass the chatflow ID as `lead_id`.
list_message_feedbackList thumbs-up/down feedback on a chatflow's messages (chatflow ID as `message_id`), optionally for one chat_id or a date range.
list_toolsList the custom tools defined in Flowise.
list_variablesList the variables available to your flows.
query_document_storeChanges dataSearch a document store's content: `store_id` plus a `query`. Returns the most relevant chunks.
run_chatflowChanges dataSend a `question` to a chatflow (its ID as `prediction_id`) and get the AI's answer. Optional history for earlier messages, uploads for files or images, and override_config.
update_assistantChanges dataUpdate an assistant by `assistant_id`, e.g. its name, description, instructions, model or temperature under `details`.
update_chatflowChanges dataUpdate a chatflow by `chatflow_id`, e.g. its name, category, deployed or is_public setting. Only the fields you pass change.
update_document_chunkChanges dataEdit one chunk's text (`page_content`) or metadata: `store_id`, `loader_id` and the chunk ID as `document_id`.
update_document_storeChanges dataUpdate a document store's name or description by its ID (`document_id`).
update_variableChanges dataChange a variable's name, type or value by `variable_id`.

Set up in three steps

1
Pick the app
Create a free PipMCP account and choose FlowiseAI from the app list.
2
Paste your key
Paste a Flowise API key and your Flowise address. In your Flowise dashboard, open API Keys and use the DefaultKey or click Create Key and copy it. Enter your Flowise address (Flowise Cloud or your own server) without a trailing slash, for example https://flowise.example.com.
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 FlowiseAI?

It can list and read chatflows, assistants, document stores, custom tools and variables, send questions to a chatflow and get the answer, search document stores, and read chat messages, feedback and leads. It can also create document stores and update chatflows, assistants, document stores, chunks and variables.

Does the AI see my Flowise API key?

No. You paste your Flowise API key into PipMCP once. It is encrypted at rest, never shown to the AI and never shown again after you save it. The AI only gets the results of the tools you have switched on.

Can I control what the AI is allowed to do?

Yes. Switch on only the tools you want, for example running chatflows and searching document stores without any edits. Changes to chatflows, assistants, chunks and variables can require your approval before they run. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT, open Settings › Apps & Connectors › Advanced, turn on Developer mode and add your PipMCP 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?

PipMCP has a free plan, and you do not need a credit card to start. Paid plans are billed per completed task. You also need your own Flowise instance, on Flowise Cloud or your own server.

Does it work with self-hosted Flowise?

Yes. When you connect, you enter the address of your Flowise instance, either Flowise Cloud or your own server, together with an API key from its API Keys page. PipMCP calls the Flowise API at that address, so the server must be reachable from the internet.