Guide

Connect an AI assistant to your workspace

Ask Claude, or any assistant that speaks the Model Context Protocol, about your chatbots without opening the dashboard. It reads; it never changes anything.

What you get

The question most worth asking about a support bot is what it could not answer. That question is tedious in a dashboard: you read transcripts until a pattern appears. An assistant with access to your workspace can read them all and tell you.

HoverBot exposes your workspace as an MCP server. Once it is connected, your assistant can look at your chatbots, your knowledge libraries, your conversations, the questions that went unanswered, your analytics and your captured leads, and answer questions about them in plain language.

Read-only, and scoped to you

Every tool is read-only. A connected assistant cannot edit a chatbot, change your knowledge, contact a lead or alter any setting. Which workspace it can see is fixed by the access token you create, not by anything the assistant sends, so it can never reach another tenant's data.

Connect it

Two values move between HoverBot and your assistant: a server address and an access token.

  1. 01

    Open Connectors in HoverBot

    In your dashboard, go to Connectors under Management. The page shows the MCP endpoint for your workspace.

  2. 02

    Create an access token

    Give it a name describing where it will be used, such as the assistant or the machine. The token is shown once and never again, so copy it before leaving the page.

  3. 03

    Add it as a custom connector

    In your assistant, add a custom MCP connector, paste the endpoint as the server address, and paste the token when it asks for a bearer token or authentication header.

  4. 04

    Ask it something

    Your assistant will list the available tools once connected. Ask a question about your workspace and it will pick the tool it needs.

The endpoint is specific to the environment you signed in to, so copy it from your own Connectors page rather than from documentation. Treat the token like a password: anyone holding it can read everything listed below.

What it can read

Nine tools, all read-only. Your assistant chooses between them; you do not have to name one.

ToolWhat it returns
list_chatbotsEvery chatbot in your workspace, with its type and publish status.
get_chatbotOne chatbot's configuration: tone, system prompt, greeting, and the knowledge libraries attached to it.
list_knowledge_sourcesThe files, web links, text blocks and question-and-answer pairs in your libraries, with their processing status.
search_knowledgeKnowledge content containing particular words. A keyword match, not a semantic search.
list_conversationsRecent conversations between shoppers and your chatbots, with the opening message and message count.
get_conversationThe full transcript of one conversation, in order, with the retrieval confidence recorded for each turn.
get_unanswered_questionsQuestions your chatbots answered from weak grounding, and questions that produced no answer at all, each with its conversation id.
get_analytics_summaryConversation and message volume, active sessions, response rate and average response time, this week against last.
list_leadsContact details captured by your chatbots, with the chatbot that captured each one and its current status.

On unanswered questions

get_unanswered_questions reports two different failures rather than merging them, because they call for different fixes:

  • Low confidence means the bot answered, but from material it was not confident matched the question. Usually the answer exists and is worded differently from how shoppers ask for it.
  • No response means the turn produced no answer at all. That is a different problem and worth looking at directly.

Each question carries its conversation id, so your assistant can pull the full exchange with get_conversation and show you what actually happened.

Things to ask

Ask in plain language. Your assistant works out which tools it needs.

  • What did shoppers ask about returns last week that we could not answer?
  • Summarise the questions my bot got low confidence on this month, grouped by topic.
  • Compare my conversation volume and response rate against last week.
  • Show me the transcript for the conversation where someone asked about shipping to Iceland.
  • Which knowledge sources mention the refund window, and what do they say?

Access and revocation

Tokens are shown once, when you create them. HoverBot stores only a hash, so nobody, including us, can recover the original. If you lose one, revoke it and create another.

The Connectors page lists every token you have created, when it was created and when it was last used, so you can tell which are still in service before revoking anything. Revoked tokens stay in the list rather than disappearing, so the record of what existed remains readable.

Revocation takes effect on the next request. There is no cache to wait out and no session to expire.

Tokens do not expire on their own. That is why they cannot be created from a support session: if our support team is helping you with screen access, they cannot mint a credential that would outlive the session.

Limits

What this does not do yet, so you are not surprised by it.

Reading only. There are no tools for changing anything. If your assistant finds a gap in your knowledge base, it can show you the gap; you make the edit in HoverBot.

Keyword search, not semantic search. search_knowledge matches words, so a query sharing no words with the source text will not find it. Your chatbot's own answering uses semantic retrieval; this tool does not.

Bearer tokens, not OAuth. Connect it as a custom connector using the token you created. There is no one-click install from a connector directory yet.

Result sizes are capped. Listing tools return at most 50 rows per call and default to fewer, so an assistant asked about “everything” sees a recent slice rather than your whole history.

Questions, or something missing?

If there is a question you want to ask your workspace and no tool answers it, tell us. The tool surface is shaped by what people actually ask.

Get in touch