Integration

PollyBot AI integration

PollyBot AI is a website chatbot builder that captures leads. Manage a chatbot's leads (create, list with filters and search, read, update their pipeline status, priority, notes and tags, delete) and send a message to a chatbot to get its AI answer, continuing a conversation by id. Every call names the chatbot by its id, shown in the PollyBot dashboard (no route lists chatbots). Limit: 1,000 requests per hour per API key. Webhook management is not exposed: the vendor's pages disagree on whether an API key may call it. Authentication is a workspace API key (sk-workspace_..., Workspace Setup, API Keys) sent as a Bearer token.

Connect PollyBot AI How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in PollyBot AI.Built from the 6 PollyBot AI tools below, on the connection you add once.

What you can do with PollyBot AI

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.

Lead, 5 operations

create_leadCreate leadPOSTCreates a lead in a chatbot and returns it in data; it starts with status NEW and priority MEDIUM. Fires the chatbot's LEAD_CREATED webhook. A second lead with the same email in that chatbot is refused (409).
delete_leadDelete leadDELETEPermanently deletes a lead from a chatbot; there is no undo. Returns a confirmation message, not the deleted lead.
get_leadGet leadGETReturns one lead of a chatbot in data: name, email, phone, company, message (personal data), source, status, priority, notes, tags, custom fields, follow-up and conversion dates.
list_leadsList leadsGETLists a chatbot's leads, newest first by default, paginated (page, limit up to 100) and filterable by status, priority or a search on name, email and company. Returns data.leads[] (contact details: personal data) and data.pagination.
update_leadUpdate leadPUTUpdates a lead: send only the fields to change, the others keep their values. Moves it through the pipeline (status), sets priority, notes, tags and custom fields. tags and customFields replace the stored values entirely.

Chat, 1 operation

send_chat_messageSend chat messagePOSTSends a message to a chatbot and returns its AI answer in data.response, with the conversationId to send back to continue the conversation. Spends the chatbot's PollyBot credits (402 when they run out).

Use PollyBot AI from Claude Code, Cursor or Codex

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

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