# Intercom MCP for AI Agents AI Agent Connect > Intercom MCP. Give your AI agent direct access to your Intercom inbox to manage conversations, search customer records, and pull support analytics. Stop jumping between tabs and let your agent handle the heavy lifting of data retrieval and ticket management. ## Overview - **Category:** talk-to-me - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_qoUrlmlTTggBeTYddoFi9g3ZbW5owVpzHSIHRDqk/ai-agent-connect - **Tags:** conversational-ai, helpdesk, customer-messaging, crm-integration, support-automation ## Description Intercom MCP gives your AI agent direct access to your customer communications and support operations. Instead of jumping between your helpdesk and your primary workspace, you can handle everything conversationally. Imagine you're in the middle of a high-priority support ticket and need to know a customer's full history across several months. Usually, that means opening a new tab, logging into your helpdesk, and digging through old threads. With this Connector, your AI agent does that work for you. You can just ask your agent to pull up the last three conversations or check a specific user's plan status while you stay focused on the current interaction. It turns your agent into a specialized support assistant that knows your customers as well as you do. If you're looking for a way to connect these systems without the headache of building custom APIs, Vinkius makes it easy to plug this right into your workflow. You get to stay in your primary workspace while the agent handles the manual lookups, contact updates, and ticket assignments. It's about removing the friction of data silos so you can actually solve problems faster instead of just hunting for information. You can verify if a lead is already in your system, update their role as they move through the funnel, or check which company plan they're currently on without ever leaving your chat window. It makes your support and success operations feel much more fluid because the data is always right there when you need it. ## Tools ### create_contact Create a new contact or lead in Intercom with a specific role and email. This helps you add new users to your database directly from your AI client. ### create_conversation Start a new conversation ### get_contact_details Get details for a contact ### get_conversation_details Get conversation history ### list_admins See a list of all team members with admin access to your Intercom account. This helps you manage your internal team permissions. ### list_help_articles List help center articles ### list_conversations Pull a list of all active and past conversations in your inbox. It gives you a bird's eye view of your current support volume. ### search_contacts Find specific users based on criteria like email, name, or custom attributes. It's the fastest way to locate a specific customer record. ### list_data_attributes List custom attributes ### reply_to_conversation Send a text response directly to a customer conversation. This allows your agent to communicate with users in real time. ### list_contacts Get a full list of all contacts and leads currently in your database. Use this to audit your current customer list. ### list_segments See all the different user segments you have defined in Intercom. This is useful for targeted support or success outreach. ## Prompt Examples **Prompt:** ``` Find the contact record for sarah@startup.io. ``` **Response:** ``` Found: Sarah Chen (sarah@startup.io). Company: Startup.io (Growth plan). Last seen: 2 hours ago. Total conversations: 12 (3 open). Custom attributes: MRR $2,400, Account Manager: James. ``` **Prompt:** ``` How many open conversations do we have right now? ``` **Response:** ``` You currently have 23 open conversations. Breakdown: 8 unassigned, 10 assigned to support agents, and 5 snoozed. The oldest open conversation is 4 hours old (assigned to Maria). ``` **Prompt:** ``` List all companies on our Enterprise plan. ``` **Response:** ``` I found 14 companies on the Enterprise plan. Top 5 by user count: Acme Corp (250 users), GlobalTech (180 users), DataFlow Inc (95 users), CloudFirst (72 users), and SecureStack (45 users). ``` ## Capabilities ### Find specific customer records Your agent can locate user profiles instantly using emails, names, or custom attributes. ### Assign new conversations Automatically route incoming support tickets to the correct team members. ### Update contact details Modify customer roles and attributes directly through your AI client. ### Retrieve company plans Get immediate access to company profiles and subscription metrics. ### Close resolved tickets Finish support interactions by resolving conversations via the agent. ### Access help center articles Pull a list of existing documentation to provide accurate answers to users. ## Use Cases ### Quick History Lookups A support rep needs to know why a user is upset and asks the agent to pull the last 5 conversations for that email. ### Account Health Audits A CSM wants to know which companies on the Enterprise plan have the highest user counts and asks the agent to list them. ### Sales Lead Enrichment A sales rep needs to find the contact info for a specific company and asks the agent to search for them by name. ### Queue Management A manager wants to see how many conversations are currently unassigned and asks the agent to list all active tickets. ## Benefits - Faster ticket resolution by using search_contacts to get instant context on a user's history. - Better team organization by using assign_conversation to route tickets to the right people automatically. - Accurate data entry by using update_contact to keep customer profiles current without manual typing. - Instant plan verification by using list_companies to check what a customer is paying for. - Streamlined onboarding by using create_contact to add new leads directly from your AI interface. - Quick knowledge base access by using list_articles to find the right documentation for a user. ## How It Works The bottom line is you get a direct bridge between your AI and your customer support data. 1. Subscribe to the Intercom integration on the Vinkius marketplace. 2. Create a private app in the Intercom Developer Hub to get your Access Token. 3. Connect the token to your AI client to start querying your data. ## Frequently Asked Questions **Can the Intercom MCP help my support team respond faster?** Yes. It lets your agent pull up a customer's full history and plan details instantly so you don't have to hunt for them in the Intercom dashboard. **How do I use the Intercom MCP to manage my tickets?** You can ask your agent to assign conversations to specific team members or close them out once they are resolved, keeping your inbox organized. **Can my AI agent search for specific customers with this?** Yes, your agent can search for contacts by name, email, or any custom attributes you have set up in Intercom to find the right person quickly. **Does the Intercom MCP work with my company's help center?** It can list all your current help center articles so your agent can reference them when answering common questions. **Can I update customer information using the Intercom MCP?** You can have your agent update contact details or roles directly, which helps keep your customer data accurate without manual entry. **What kind of company data can I see with the Intercom MCP?** Your agent can retrieve company profiles, specific plan information, and other aggregate metrics to give you a full view of your accounts. **How do I get my Intercom Access Token?** Go to the **Intercom Developer Hub** at **app.intercom.com/a/developer-hub/**. Click **New app**, give it a name, and select the workspace to install it in. Once created, click on your app, then navigate to **Authentication** in the left sidebar. Your **Access Token** will be displayed on this page. Configure the required permissions (scopes) — such as Read/Write People, Conversations, or Companies — and click **Save**. Copy the token and paste it below. **Can I look up a customer's full conversation history instantly?** Yes. Just ask your AI agent 'Show me all conversations with john@acme.com' and it retrieves every conversation — open, closed, and snoozed — including message content, agent assignments, tags, and resolution times. Perfect for getting full context before a customer call. **Can I track support team performance metrics?** Yes. Your AI agent can pull conversation counts, average response times, resolution rates, and open ticket volumes — giving managers instant visibility into team workload and SLA compliance without building custom reports or opening the Intercom analytics dashboard. **Is my customer data secure?** Your Access Token is a private app token that only accesses data in your own Intercom workspace. It respects your workspace's permission model — the token only has access to the scopes you explicitly grant. All API calls are made over HTTPS, and the token is never shared with third parties. **Can I search for contacts and send messages through the AI agent?** Yes. Use `search_contacts` to find contacts by email, name, or custom attributes. Then use `send_message` to send a message to a specific contact, or reply to an active conversation thread. **Can I view full conversation histories?** Yes. `list_conversations` shows all conversations with status. Use `get_conversation` with a conversation ID to retrieve the full message thread including sender, timestamps, and content. **What type of Intercom token do I need?** You need an **Access Token** from a Private App in the Intercom Developer Hub. This provides scoped API access with Bearer authentication against `api.intercom.io`.