Integration

Droxy integration

Droxy builds AI chatbot agents trained on your own knowledge. An agent can create, read, update and delete chatbots, add knowledge resources (raw text, a YouTube video, a website crawl, or an uploaded PDF or MP4 file), ask a chatbot or a single resource a question, list a chatbot's conversations (with their analysis) and the leads it collected, and save a conversation held elsewhere. The streaming chat routes are not exposed. API access needs a Droxy Advanced plan or higher; chat answers spend the plan's monthly message tokens and new resources spend knowledge tokens (transcription minutes for MP4). Authentication is an API key created in the Droxy dashboard under API, sent in the x-api-key header.

Connect Droxy How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Droxy.Built from the 18 Droxy tools below, on the connection you add once.

What you can do with Droxy

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.

Chatbot, 5 operations

create_chatbotCreate chatbotPOSTCreates a chatbot that answers from the given resources (knowledge). Returns the new chatbot with its id.
delete_chatbotDelete chatbotDELETEDeletes a chatbot for real. Returns the deleted chatbot.
get_chatbotGet chatbotGETGets one chatbot's settings: name, welcome message, colors, model, system prompt, access level, resources and website embed settings.
list_chatbotsList chatbotsGETLists every chatbot of the account with its settings, model, access level and the ids of the resources it uses.
update_chatbotUpdate chatbotPUTUpdates a chatbot's settings. Every body field is optional: send only the fields to change. Changes apply to the live chatbot at once.

Resource, 3 operations

delete_resourceDelete resourceDELETEDeletes a knowledge resource for real. Refused with HTTP 409 (listing the chatbot ids) while chatbots still use it. Knowledge tokens already spent are not refunded.
get_resourceGet resourceGETGets one knowledge resource: type, AI processing status (poll until DONE before chatting with it), size and sync details.
list_resourcesList resourcesGETLists every knowledge resource of the account with its type, AI processing status, tags and type-specific details.

Conversation, 2 operations

list_chatbot_conversationsList chatbot conversationsGETLists a chatbot's conversations in a date range, with messages, source channel (with sender name and number for WhatsApp, Facebook, Instagram) and the AI analysis.
save_conversationSave conversationPOSTSaves messages into a chatbot conversation: creates one, or with conversationId appends to or overwrites an existing one (override decides). Shows in the chatbot's inbox.

Chatbot answer, 1 operation

chat_with_chatbotChat with chatbotPOSTAsks a chatbot a question and returns its answer as text. Send the conversation so far. Spends the plan's message tokens (HTTP 402 when the usage limit is reached).

Chatbot avatar, 1 operation

update_chatbot_avatarUpdate chatbot avatarPUTReplaces the avatar image of a chatbot with an uploaded image file (under 5 MB). The change is visible on the live chatbot.

File, 1 operation

create_file_resourceCreate file resourcePOSTUploads a PDF or MP4 file as a knowledge resource (under 1000 MB, videos under 120 minutes). Spends knowledge tokens, and transcription minutes for MP4. Limit: 10 requests per minute.

Lead, 1 operation

list_chatbot_leadsList chatbot leadsGETLists the leads (name, email, phone) a chatbot collected in a date range.

Resource answer, 1 operation

chat_with_resourceChat with resourcePOSTAsks a question about one resource (a document, video, text or website) and returns the answer as text. Spends the plan's message tokens (HTTP 402 when the usage limit is reached).

Text, 1 operation

create_text_resourceCreate text resourcePOSTCreates a knowledge resource from raw text. Spends knowledge tokens (about 1.33 per word). Processing is asynchronous: check aiProcessingStatus with get_resource.

Website, 1 operation

create_website_resourceCreate website resourcePOSTCreates a knowledge resource by extracting a website's pages (the URL plus the listed sub-URLs), optionally re-synced on a schedule. Spends knowledge tokens on every extraction.

Youtube, 1 operation

create_youtube_resourceCreate youtube resourcePOSTCreates a knowledge resource from a YouTube video's transcript. Spends knowledge tokens. Processing is asynchronous: check aiProcessingStatus with get_resource.

Use Droxy from Claude Code, Cursor or Codex

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

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