Chaport MCP. Manage visitor data and live chat from your agent.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Chaport MCP Server gives your AI agent full control over live customer chat. Track recent website visitors, view full message history, and manage the support team's status—all from your agent's chat interface.
Use it to send messages, review visitor details, or check which agents are online without opening the Chaport dashboard.
What your AI agents can do
Get chat history
Gets the full message log and event records for a specific chat session.
Get my agent profile
Retrieves personal information about the agent currently using the system.
Get visitor details
Fetches detailed contact and demographic information for a visitor.
Retrieves specific information for a visitor using their known identifiers.
Retrieves the complete message history and associated events for a specific chat thread.
Sends a message directly to a visitor within an active chat session.
Retrieves a list of recent people who visited your website.
Lists all support agents in the account and identifies which ones are currently online.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Chaport MCP Server: 8 Tools for Chat & Visitor Management
These tools let your agent manage customer communications by retrieving visitor data, accessing full chat transcripts, and monitoring the live support team.
019d756cget chat history
Gets the full message log and event records for a specific chat session.
019d756cget my agent profile
Retrieves personal information about the agent currently using the system.
019d756cget visitor details
Fetches detailed contact and demographic information for a visitor.
019d756cget visitor last chat
Retrieves the most recent chat session summary for a specific visitor.
019d756clist chaport operators
Lists every agent account registered within your Chaport workspace.
019d756clist online agents
Checks and lists which support agents are currently logged in and active.
019d756clist website visitors
Gets a list of people who recently visited your website.
019d756csend agent message
Sends a new message from the agent to a visitor in an active chat.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Chaport, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Chaport MCP Server gives your AI agent total control over live customer chat. You'll track recent website visitors, view full message history, and manage your support team's status—all right from your agent's chat interface. You don't gotta open the Chaport dashboard to do any of that.
How Chaport MCP Works
- 1 Subscribe to the server and provide your Chaport API Token (found in Settings -> API).
- 2 Your AI agent connects to the MCP Server via your preferred client (Claude, Cursor, etc.).
- 3 Use natural language prompts to ask the agent to perform actions (e.g., "List all online agents"). The agent executes the required tool call and presents the data.
The bottom line is, you run your customer support operations directly through conversation, eliminating the need to jump between multiple tabs and dashboards.
Who Is Chaport MCP For?
This is for Support Managers who need to monitor team availability and review chat histories on the fly. It helps Customer Success Teams quickly find and re-engage recent visitors without leaving their current workflow. Sales Representatives use it to instantly pull up visitor details and past interactions straight from their chat interface.
Monitors agent availability using list_online_agents and reviews full chat transcripts using get_chat_history to audit team performance.
Identifies recent visitors using list_website_visitors and sends follow-up messages via send_agent_message without opening the full support dashboard.
Looks up visitor details using get_visitor_details and checks previous interactions using get_visitor_last_chat during a sales call.
What Changes When You Connect
- See who visited your site and what they looked at using
list_website_visitors. You get a real-time list of names and contacts, immediately actionable for follow-up. - Know exactly who is available right now.
list_online_agentstells you which agents are active, letting you manage support load before it gets too high. - Stop guessing about customer context. Use
get_chat_historyto instantly pull up every message and event from a past chat, giving your agent the full background story. - Manage the customer conversation directly.
send_agent_messagelets you send a targeted message to a visitor in a chat, even if you're not in the main dashboard. - Understand the visitor's profile instantly.
get_visitor_detailsgives you deep background info on a customer, moving past just the name and email. - Check the last conversation summary with
get_visitor_last_chatto get a quick pulse on a customer without reading a massive transcript.
Real-World Use Cases
Handling a Cold Lead Follow-up
A sales rep needs to follow up with a lead who visited the site yesterday. Instead of opening the dashboard, they ask their agent to run list_website_visitors to find the contact. They then use get_visitor_details to pull up the lead's job title, and finally, send_agent_message to send a personalized follow-up message.
Checking Support Coverage During an Outage
The support manager notices the chat queue is building up. They ask the agent to run list_online_agents and list_chaport_operators. This immediately shows if key agents are logged off or if the team needs to reallocate resources.
Deep Dive into a Complex Support Issue
A support agent needs to know why a customer called back three times. They ask the agent to use get_visitor_last_chat for a quick summary, and then run get_chat_history for the full, detailed transcript to understand the root cause.
Onboarding a New Team Member
A manager wants to audit a new agent's performance. They use list_chaport_operators to see who is on staff, and then use get_my_agent_profile to check the manager's own account details for auditing purposes.
The Tradeoffs
Treating the server like a search engine
Trying to ask the agent a question like, "Why did John Doe leave the site?" or "What is the best product for this visitor?" The tools only retrieve data; they can't analyze intent or give advice.
→
To get actionable data, run the tools in sequence: First, use get_visitor_details to gather facts. Then, use get_visitor_last_chat to understand the context. The agent can synthesize the output, but it can't guess the 'why'.
Relying on single-point data views
Assuming that because a visitor is listed in list_website_visitors, you know their current status or last interaction. This is often inaccurate.
→
Always confirm the current status. First, call get_visitor_details for the core profile. Then, call get_visitor_last_chat to confirm their most recent activity and context.
Overloading the agent with too many calls
Asking the agent to run list_website_visitors, then get_chat_history, and then get_visitor_details all in one prompt. This makes the output a confusing dump of unrelated data.
→
Group your calls logically. Start with the target: if you need to chat with John, start with get_visitor_details. If you need to check team status, stick to the operational tools like list_online_agents.
When It Fits, When It Doesn't
Use this server if your primary need is data retrieval and actioning customer contacts. You need to know who visited, what they talked about, and who is available to talk to them. Don't use this if you need predictive analytics, or if you need to analyze the sentiment of a chat log (the tools only retrieve text, they don't analyze it). If you need to track complex user journeys over time, you'll need a dedicated analytics platform; this is a data retrieval layer. Use get_chat_history and get_visitor_details when you need full context. Use list_online_agents when you need operational status. Never rely on this for 'why' answers.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Chaport. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 8 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Jumping between tabs to find visitor context is a huge time drain.
Today, tracking a visitor means opening the main chat dashboard, clicking on the visitor's name, finding the 'Activity' tab, cross-referencing the email list, and then opening the separate 'Team Status' widget just to see if an agent is available. It's a 4-step process that kills momentum.
With the Chaport MCP Server, your agent handles it all. You ask, "What's the status of Jane Smith?" and get the visitor details, their last chat summary, and the current agent availability—all in one conversational response.
Use Chaport MCP Server: Centralize chat and visitor data.
You no longer need to manually copy chat IDs into a spreadsheet, or jump back to the web UI to check an agent's status. The server brings the ability to query `get_chat_history` and `list_online_agents` right into your agent's flow.
The difference is workflow. You get a single, conversational stream of operational data that keeps your entire process moving forward without ever breaking your focus.
Common Questions About Chaport MCP
How do I get the chat history using the get_chat_history tool? +
You must provide a specific chat ID. The agent needs this ID to retrieve the full message log and events. This tool doesn't search across all chats; it only fetches the data for the ID you give it.
Can I see who visited the site using list_website_visitors? +
Yes. This tool retrieves a list of recent visitors. It provides basic details like names and timestamps, which you can then use to look up more specific data using get_visitor_details.
Does send_agent_message work only when I'm in the dashboard? +
No. send_agent_message allows your agent to send a message to a visitor directly from the chat interface, regardless of where your agent is running.
How do I check if an agent is online using list_online_agents? +
Simply ask the agent to run list_online_agents. It checks the system and gives you a real-time list of all active operators, helping you manage support load.
How do I find out if an agent is available using list_chaport_operators? +
The list_chaport_operators tool shows every agent in your account. You can use this to confirm agent names and check overall team membership.
What information does the get_visitor_details tool provide? +
It provides detailed information about a specific visitor. This includes their contact details and specific account metadata, letting you understand who they are.
Can I see the most recent activity for a visitor using get_visitor_last_chat? +
Yes, get_visitor_last_chat retrieves the last chat session for a specific visitor. This gives you a quick look at their recent conversation context.
Does the send_agent_message tool require a specific chat ID? +
Yes, send_agent_message needs a specific chat ID to function. You must provide this ID to target the message exactly where it needs to go.
Can I see who is currently visiting my website? +
Yes! Use the list_website_visitors tool. The agent will return a list of recent and active visitors, including their names, emails, and location if available.
How do I reply to a specific customer chat? +
Use the send_agent_message tool with the unique chat ID. Your agent will post the message directly into the Chaport conversation.
Where do I generate my Chaport API Token? +
Log in to your Chaport account and go to Settings → API. You can generate and copy your API token from that section.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Epic Online Services & Social Analytics
The definitive server for Epic Games social intelligence — track player profiles, friends, and achievements via AI.
Zammad
Automate helpdesk workflows via Zammad — manage tickets, users, and organizations directly from any AI agent.
Mastodon
Automate social interactions on the Fediverse — post statuses, manage follows, and track trending content directly from your AI agent.
You might also like
PubMed Central
Search and retrieve full-text biomedical and life sciences literature from PubMed Central (PMC).
GrazeCart
Manage your GrazeCart store — track orders, update inventory, and manage customers directly via AI.
Mailinator
Test email workflows with disposable inboxes that catch every message without touching production mailboxes or real addresses.