Landbot MCP. Manage bot conversations and customer data 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.
Landbot MCP Server lets your AI client manage conversational pipelines. You can pull customer metadata, fetch full chat histories, send automated text messages, and programmatically reassign leads to live agents.
It handles complex bot interactions and keeps all conversation state centralized.
What your AI agents can do
Assign agent
Moves an active conversation thread from the automated bot state to a live human agent.
Get bot
Retrieves specific details for a single bot using its unique ID.
Get customer
Pulls all metadata associated with a specific customer ID.
Retrieves specific metadata for a single customer using get_customer.
Fetches the complete message sequence log for a given customer using get_messages.
Finds specific customers by email using search_customers, or lists all recent customers via list_customers.
Sends a text message programmatically to a customer conversation using send_text_message.
Lists all available bots or gets details for a single bot using list_bots and get_bot.
Routes a conversation from an automated bot back to a live human agent using assign_agent.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Landbot MCP Server: 8 Tools for Conversational AI
These tools let your AI client pull customer metadata, track chat history, send messages, and manage bot handoffs across Landbot.
019d75c4assign agent
Moves an active conversation thread from the automated bot state to a live human agent.
019d75c4get bot
Retrieves specific details for a single bot using its unique ID.
019d75c4get customer
Pulls all metadata associated with a specific customer ID.
019d75c4get messages
Fetches the entire sequence of chat messages for a given customer context.
019d75c4list bots
Lists all bots that are accessible through the Landbot platform.
019d75c4list customers
Gets a list of customers who have recently interacted with the bots.
019d75c4search customers
Finds a specific customer account using their email address.
019d75c4send text message
Sends a text message directly into an existing customer conversation.
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 Landbot, 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
Your AI client uses the landbot tools to handle all customer conversations. You can pull customer metadata using get_customer and see the whole message log for a specific customer with get_messages. You'll find a list of recent customers using list_customers, or you can pinpoint an account by email with search_customers.
You can send a text message into an active conversation using send_text_message. You can manage the bots themselves; check out all available bots with list_bots, or grab the specific details for one bot with get_bot. You can move a conversation from the bot straight to a live agent using assign_agent.
You'll also get the necessary info to route leads and manage all the chat states without leaving your AI client.
How Landbot MCP Works
- 1 First, connect your AI client and provide the Landbot API Token in Vinkius credentials.
- 2 Next, reference the customer ID or search for a customer using
search_customersorlist_customersto establish context. - 3 Finally, call the desired tool (e.g.,
get_messagesorsend_text_message) to perform the required action on that context.
The bottom line is you use your AI client to orchestrate calls to the tools, maintaining context across multiple steps.
Who Is Landbot MCP For?
The Customer Success Manager who needs to see if a high-value lead dropped off in a bot flow. The Sales Operations Analyst who needs to manually reassign a hot lead to a specific agent. Product Managers who want to audit the full customer journey through the bot without logging into Landbot. If you spend time switching between CRMs and chatbot dashboards, this is for you.
Uses get_messages to pull the full chat history for a customer who is having trouble, allowing them to understand the context before calling the client.
Runs search_customers by email and then uses assign_agent to bypass the bot and hand the lead directly to a specific human agent.
Uses list_bots and get_bot to map out the available conversational flows and check if new bot matrices are ready for testing.
What Changes When You Connect
- See the full conversation thread for any customer. Use
get_messagesto pull the complete chat log for customer ID 98453, so you never have to guess what the conversation was about. - Move a lead to a human agent instantly. The
assign_agenttool intercepts a bot conversation and routes it to a live agent, keeping the context intact. - Identify high-value leads quickly. Use
search_customerswith an email address to pull customer metadata and see if they match your target profile. - Handle outreach without leaving your agent.
send_text_messagelets you send an automated text directly into an active customer conversation. - Audit bot performance easily. Use
list_botsandget_botto see all the bots running and check the details of a specific bot matrix. - Track your user base. Call
list_customersto get a list of everyone who interacted recently, giving you an immediate view of your user base.
Real-World Use Cases
Need to validate a lead's interest level.
A sales rep gets a promising lead but the bot stalled. Instead of asking the rep to log into the external system, the agent runs get_messages with the customer ID. The rep reads the full chat transcript and confirms the lead mentioned 'Pricing' and 'Timeline' in the last five messages.
A bot handled a query, but a human needs to take over.
A customer's issue is too complex for the bot flow. The agent first uses get_customer to pull all metadata, then runs assign_agent to seamlessly pass the conversation to Agent Sarah. The human agent gets the full context immediately.
Sending a follow-up after a major event.
Product marketing needs to send a reminder about a new feature. They use search_customers to find a group of users by email and then use send_text_message to deliver the update directly to their active conversation thread.
Checking which bot flows are active.
A DevOps engineer needs to know if the main sales bot is running. They call list_bots to get an inventory, then use get_bot to verify the operational status and configuration of the specific bot.
The Tradeoffs
Treating the conversation as a single message.
Asking the agent to just 'check the customer's history' without telling it to use get_messages. The agent fails because it doesn't know the necessary tool call or context.
→
You must explicitly call get_messages and provide the customer ID. This pulls the entire chat sequence, giving you the full context you need for analysis.
Trying to manually reassign a bot.
Simply telling the agent, 'Send this conversation to the human team.' This is too vague and doesn't trigger the necessary workflow.
→
Use the assign_agent tool. This command specifically intercepts the current live interaction and injects the necessary routing update to transfer control to a human agent.
Using the wrong customer identifier.
Calling get_customer with a bot ID or a bot name instead of a customer's unique ID. The call will fail because the tool requires a customer context.
→
Always use search_customers first (by email) or list_customers to get the correct customer ID, then pass that ID to get_customer.
When It Fits, When It Doesn't
Use this Landbot MCP Server if your workflow needs to manage the entire lifecycle of a customer interaction: from initial bot engagement to human handoff. You need a single place to pull chat history (get_messages) and check customer details (get_customer) before taking action. Don't use this if you just need to send a single, isolated email—that's a general messaging tool. If you only need to know if a bot is running, list_bots works. But if you need to do something with the bot (like reassigning a lead or sending a message), you need the full suite of tools here.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Landbot. 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
Manually tracking customer journey status is a nightmare.
Every time a lead crosses from a bot to a human agent, someone has to copy the conversation log from one dashboard into a CRM, then copy the notes into a ticketing system. This means multiple tabs open, constant copy-pasting, and the history gets fragmented across three different tools.
With this MCP server, the agent calls `get_messages` and `get_customer`. The full, structured chat history and metadata appear directly in the response. You get the complete context in one go.
Landbot MCP Server: Manage conversations and customer data.
You no longer have to manually check the bot's operational status or look up a customer's ID in a separate dashboard. The agent can use `list_bots` to check the bot status and then `search_customers` to find the user, all in sequence.
The agent maintains the entire conversational state across multiple tools. It treats the customer journey as one continuous, actionable data stream, not a series of siloed API calls.
Common Questions About Landbot MCP
How do I use the `get_messages` tool with Landbot MCP Server? +
You call get_messages and provide the specific customer ID. This retrieves the entire transcript. The result is the full chat sequence, letting you see exactly what was said and when.
What is the difference between `get_customer` and `search_customers`? +
search_customers finds a customer by criteria like email. get_customer requires you to already have the customer ID to pull all the associated metadata.
Can I manually hand off a conversation using `assign_agent`? +
Yes. assign_agent takes an active conversation thread and immediately routes it to a human agent, bypassing the bot logic. It's a direct handoff.
Does Landbot MCP Server support sending messages? +
Yes. You can use send_text_message to send a message programmatically into a customer's conversation, making it look like a native interaction.
How do I check which bots are active using the `list_bots` tool? +
You run list_bots to get a full list of accessible bots. This shows you the IDs and names of all the standard matrix bots running in your Landbot account.
What data does `get_customer` retrieve for a given customer ID? +
It retrieves specific metadata for a single customer. This data includes the customer's history and key identifiers, allowing you to ground responses with accurate context.
How can I programmatically send a message using the `send_text_message` tool? +
You call send_text_message with the target customer ID and the message content. This sends a message directly into the customer's active conversation thread.
If I need to find a customer by email, which tool should I use: `search_customers` or `get_customer`? +
search_customers is for finding customers using a specific criterion like email. You must use the resulting customer ID from that search to then run get_customer.
How do I authenticate? +
Grab the main API Access Integration token located centrally in settings inside Landbot App context.
Can I route chats to human agents? +
Yes, standard endpoints enable you to extract active sessions and invoke assignment APIs gracefully.
Do bots answer incoming queries automatically? +
No interruption occurs. Read functionalities passively pull context without disconnecting current funnels.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Weiban Assistant
Customer relationship management for WeCom — manage leads, customers, and group chats via AI.
BulkSMS.com
Reach customers worldwide with reliable bulk SMS delivery, contact list management, and real-time message status tracking.
TeleSign
Verify user identities with phone number intelligence, SMS verification, and risk scoring that prevents fraud at sign-up.
You might also like
Last.fm
Manage your music profile — audit listening habits, top tracks, and artists via AI.
Zammad
Automate helpdesk workflows via Zammad — manage tickets, users, and organizations directly from any AI agent.
vCard Contacts Parser Extended
Instantly convert massive iPhone and Android `.vcf` contact exports into structured JSON. Turn your AI into a hyper-intelligent local address book.