Integration

AgentX integration

AgentX hosts AI agents (chat, search and e-commerce assistants) built on its platform; this API talks to them. List your agents and their conversations, read the messages of a conversation, start a conversation, send a message (optionally with a file) and get each agent's reply (each reply consumes AgentX credits, more or fewer depending on the agent's model), add earlier exchanges to a conversation's memory without chatting or reset that memory, and turn text into speech (base64 audio). Left out: the streaming (server-sent events) message and speech routes, the speech recognition route (its required call, sequence and callback fields are documented only as 'string'), and the prompt trace and user profile routes, whose responses are not documented. Authentication is an AgentX API key sent in the x-api-key header.

Connect AgentX How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in AgentX.Built from the 9 AgentX tools below, on the connection you add once.

What you can do with AgentX

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.

Conversation, 3 operations

create_conversationCreate conversationPOSTStarts a new conversation with an agent and returns it; pass its _id to send_message. A new conversation has no memory of earlier ones.
get_conversationGet conversationGETReturns the messages of one conversation of an agent, in order: who sent each one (user or agent id), its text and the agent's reasoning text when there is one.
list_conversationsList conversationsGETLists the conversations of one agent, with each conversation's _id, title, user and agent ids and dates.

Conversation context, 2 operations

add_conversation_contextAdd conversation contextPUTAdds exchanges to a conversation's memory context without chatting (no agent reply), to give the agents extra context for later messages.
reset_conversation_contextReset conversation contextDELETEResets a conversation's context: deletes its memory context. Cannot be undone.

Message, 2 operations

send_messageSend messagePOSTSends a message to a conversation and waits for the replies: one entry per agent in the conversation, with its reply text. Billed: each agent reply consumes AgentX credits, the amount set by the agent's model.
send_message_with_attachmentSend message with attachmentPOSTSends a message with a file to a conversation and waits for the replies: one entry per agent in the conversation, with its reply text. Billed: each agent reply consumes AgentX credits, the amount set by the agent's model.

Agent, 1 operation

list_agentsList agentsGETLists the AgentX agents your API key can access, with each agent's _id (needed by list_conversations and create_conversation), name and avatar.

Speech, 1 operation

synthesize_speechSynthesize speechPOSTTurns text into speech and returns the audio as a base64 string. Optional language, voice gender, speed, accent and a robot voice.

Use AgentX from Claude Code, Cursor or Codex

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

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