- CONTEXT
- ANALYSIS
- RESPONSE
- HUMAN
Short answer
How can I get chat transcripts into my AI?
Your AI uses the Customerly MCP to fetch specific conversation logs and metadata. This gives your agent the context it needs to answer questions or solve problems without you manually copying and pasting text.
Where the data lands.
The outcomes of chat retrieval.
The AI uses the retrieved data to perform these specific tasks.
CONTEXT
Instant issue context
The AI reads the transcript to understand the user's problem. You get a summary of the friction points immediately.
ANALYSIS
Trend identification
The agent looks through multiple logs to find recurring complaints. This helps you spot bugs or UX issues faster.
RESPONSE
Drafted replies
The AI uses the history to write a response that matches the customer's tone and previous context. You just review and send.
HUMAN
Escalation prep
When a problem is too complex, the AI prepares a briefing for you. You get a clean summary of the chat before you jump in.
The workflow
What your AI does when the request arrives.
The AI handles the data retrieval so you can focus on the solution.
Find conversations
The agent searches your Customerly account to find the relevant chat threads based on your request.
list_conversationsFetch transcripts
Once the right chat is identified, the agent pulls the full text and metadata for that specific interaction.
get_conversationAnalyze context
The agent parses the messages to identify the user's intent, sentiment, and technical issues.
get_conversationSummarize findings
The agent presents a concise version of the conversation history directly in your chat window.
list_conversations
Try it
Copy these to start.
Use these prompts to trigger the retrieval process.
Starting points
These are opening lines. Swap out the bracketed info with your actual Customerly details.
Customerly Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_5LQSuqk03P7AWIEhnSZ2YUG4yMPFxH5aED9ESaAd/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Customerly capabilities are ready to use.
{
"mcpServers": {
"customerly-mcp": {
"url": "https://edge.vinkius.com/vk_preview_5LQSuqk03P7AWIEhnSZ2YUG4yMPFxH5aED9ESaAd/mcp"
}
}
}List my recent conversations from Customerly so I can see what users are asking about.
Get the transcript for the conversation with user 'alex_smith' to see why they are frustrated.
Find the last five conversations in Customerly and summarize the main technical issues mentioned.
Retrieve the metadata for conversation ID 98765 to check the user's account status.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Customerly once, then ask.
Follow the link to authorize the connection. Your credentials stay encrypted, and you can start asking questions immediately.
Connect Customerly to your AIFAQ
How this task behaves.
- 01
Can the AI delete conversations in Customerly?
No. The tools only allow the AI to list and retrieve conversation data. It cannot delete or modify any records.
- 02
Can the AI reply to the customer directly?
No. The AI can draft a response for you to read, but it does not have the capability to send messages back to the customer.
- 03
Does the AI see all my customer data?
The AI only accesses the specific conversation data you ask it to retrieve via the tools.
- 04
Can I search for conversations by specific keywords?
Yes. You can ask your agent to find conversations containing specific topics or user names.
- 05
How does the AI know which conversation to pick?
It uses the list of available conversations to identify the correct ID before pulling the full transcript.
More questions about Customerly? See everything the Customerly Connector can do
Connect Customerly to Claude, Cursor, ChatGPT & more
