Integration

Flowise integration

Flowise builds LLM apps and agent flows visually. Run a chatflow or agentflow prediction, read and write chatflows, assistants, tools and variables, manage document stores with their loaders and chunks, upsert vectors and read the upsert history, read chat messages and feedback, capture leads, and handle attachments and file uploads. The host is part of the credential because every install is its own deployment. Authentication is an API key sent as a bearer token.

Connect Flowise How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Flowise.Built from the 45 Flowise tools below, on the connection you add once.

What you can do with Flowise

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.

Assistant, 5 operations

create_assistantCreate assistantPOSTCreate a new assistant.
delete_assistantDelete assistantDELETEDelete an assistant.
get_assistantGet assistantGETGet assistant by ID.
list_assistantsList assistantsGETList all assistants.
update_assistantUpdate assistantPUTUpdate assistant details.

Chatflow, 5 operations

create_chatflowCreate chatflowPOSTCreate a new chatflow.
delete_chatflowDelete chatflowDELETEDelete a chatflow.
get_chatflowGet chatflowGETGet chatflow by ID.
list_chatflowsList chatflowsGETList all chatflows.
update_chatflowUpdate chatflowPUTUpdate chatflow details.

Store, 5 operations

create_document_storeCreate document storePOSTCreate a new document store.
delete_storeDelete storeDELETEDelete a specific document store.
get_storeGet storeGETGet a specific document store.
list_storeList storeGETList all document stores.
update_document_storeUpdate document storePUTUpdate a specific document store.

Tool, 5 operations

create_toolCreate toolPOSTCreate a new tool.
delete_toolDelete toolDELETEDelete a tool by ID.
get_toolGet toolGETGet a tool by ID.
list_toolsList toolsGETList all tools.
update_toolUpdate toolPUTUpdate a tool by ID.

Variable, 4 operations

create_variableCreate variablePOSTCreate a new variable.
delete_variableDelete variableDELETEDelete a variable by ID.
list_variablesList variablesGETList all variables.
update_variableUpdate variablePUTUpdate a variable by ID.

Chunk, 3 operations

delete_chunkDelete chunkDELETEDelete a specific chunk from a document loader.
edit_document_store_file_chunkEdit document store file chunkPUTUpdate a specific chunk.
get_chunkGet chunkGETGet chunks from a specific document loader.

Feedback, 3 operations

create_feedbackCreate feedbackPOSTCreate new chat message feedback.
get_feedbackGet feedbackGETList all chat message feedbacks for a chatflow.
update_feedbackUpdate feedbackPUTUpdate chat message feedback.

Chatmessage, 2 operations

get_chatmessageGet chatmessageGETList all chat messages.
remove_all_chat_messagesRemove all chat messagesDELETEDelete all chat messages.

Lead, 2 operations

create_leadCreate leadPOSTCreate a new lead in a chatflow.
get_leadGet leadGETGet all leads for a specific chatflow.

Upsert, 2 operations

upsert_documentUpsert documentPOSTUpsert document to document store.
vector_upsertVector upsertPOSTUpsert vector embeddings.

Upsert history, 2 operations

get_upsert_historyGet upsert historyGETGet all upsert history records.
update_upsert_historyUpdate upsert historyPATCHDelete upsert history records.

Apikey, 1 operation

get_apikeyGet apikeyGETGet chatflow by API key.

Attachment, 1 operation

create_attachmentCreate attachmentPOSTCreate attachments array.

Loader, 1 operation

delete_loaderDelete loaderDELETEDelete specific document loader and associated chunks from document store.

Prediction, 1 operation

create_predictionCreate predictionPOSTSend message to flow and get AI response.

Query, 1 operation

query_vector_storeQuery vector storePOSTRetrieval query.

Refresh, 1 operation

refresh_documentRefresh documentPOSTRe-process and upsert all documents in document store.

Vectorstore, 1 operation

delete_vectorstoreDelete vectorstoreDELETEDelete data from vector store.

Use Flowise from Claude Code, Cursor or Codex

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

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