Integration

DocsBot AI integration

DocsBot AI answers questions from a bot trained on your documentation. Ask a bot through its Chat Agent (stateful conversations with tools) or the older stateless chat routes, run semantic search over its sources and fetch a source document, rate answers, log support escalations, capture leads and update conversation metadata, generate a conversation summary or support ticket, and run deep research jobs. Team and bot ids come from the DocsBot dashboard. This covers the Chat API host only: the Admin API (teams, bots, sources, questions, leads, stats, webhooks on docsbot.ai/api), the widget voice WebRTC routes and SSE streaming are not exposed. Authentication is the user API key from the DocsBot dashboard sent as a Bearer token (public bots also answer some routes without one).

Connect DocsBot AI How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in DocsBot AI.Built from the 17 DocsBot AI tools below, on the connection you add once.

What you can do with DocsBot 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.

Research, 4 operations

cancel_researchCancel researchDELETECancels a deep research job.
continue_researchContinue researchPOSTAnswers a research job's clarifying questions and queues the research. Returns jobId, status (queued) and title; then poll get_research_job.
get_research_jobGet research jobGETReturns a research job: status (clarifying, queued, running, completed), question, title and, once completed, its response.
start_researchStart researchPOSTStarts a deep research job (needs authentication). Returns jobId, a title, status clarifying and clarifications: answer them with continue_research.

Ask, 1 operation

ask_bot_legacyAsk bot legacyPOSTLegacy question-and-answer route; prefer ask_bot or chat_with_agent. Asks a bot a question with the stateless chat API: send earlier turns in history. Returns the answer, whether the bot could answer, its sources and the answer id (for rate_answer).

Chat, 1 operation

ask_botAsk botPOSTAsks a bot a question with the stateless chat API: send earlier turns in history. Returns the answer, whether the bot could answer, its sources and the answer id (for rate_answer).

Chat agent, 1 operation

chat_with_agentChat with agentPOSTAsks a bot through its Chat Agent: stateful (send the same conversationId each turn) and able to use tools. Returns a list of events; the answer is in data.answer of the lookup_answer or answer event.

Conversation, 1 operation

update_conversation_metadataUpdate conversation metadataPUTUpdates the metadata of a Chat Agent conversation; by default the new keys are merged into the existing metadata.

Escalate, 1 operation

escalate_conversationEscalate conversationPUTLogs a confirmed human escalation on a Chat Agent conversation (escalated: handled) and triggers the conversation.escalated webhook.

Fetch, 1 operation

fetch_documentFetch documentPOSTReturns the reconstructed document of an indexed file, by the fileId a search result returned. Uses 0.1 AI credit per call.

Lead, 1 operation

capture_leadCapture leadPOSTSaves a lead for a conversation (lead id = conversation id) and merges its fields into the conversation's metadata if the conversation exists.

Library, 1 operation

list_librariesList librariesGETLists the libraries (bots) the key can search, with their name, description, team id and bot id.

Rate, 1 operation

rate_answerRate answerPUTRates an answer for the bot's chat logs: rating -1, 0 or 1, where 0 resets the rating to neutral.

Search, 1 operation

search_sourcesSearch sourcesPOSTSemantic search over a bot's sources: returns the most relevant chunks (title, url, fileId, page, content). Uses 0.1 AI credit per call.

Summarize, 1 operation

summarize_conversationSummarize conversationGETCreates or returns the summary of a conversation: title, summary text, sentiment and topic.

Support, 1 operation

log_support_requestLog support requestPUTRecords that the user escalated to human support after this answer, for the bot's statistics.

Ticket, 1 operation

generate_support_ticketGenerate support ticketGETGenerates a support ticket from a conversation: a subject line and formatted ticket content for a help desk.

Use DocsBot AI from Claude Code, Cursor or Codex

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

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