Intercom Articles MCP
I

Intercom Articles MCP

The Intercom MCP Server provides Help Center content management and customer service workflow automation functions, supporting article management, collection operations, and multilingual translation.
2.5 points
5.0K

What is the Intercom MCP Server?

The Intercom MCP Server is a bridge tool that connects the Claude desktop application to the Intercom platform. It allows you to manage the content of the Intercom Help Center and customer support workflows directly in Claude without logging in to the Intercom backend interface. You can create, edit articles, manage multilingual content, reply to customer conversations, update ticket status, etc.

How to use the Intercom MCP Server?

First, you need to configure the Claude desktop application to connect to the Intercom MCP server. After the configuration is complete, you can use natural language instructions directly in the Claude conversation to manage Intercom content, such as 'List all articles', 'Search for articles about subscriptions', 'Reply to customer conversations', etc.

Use cases

Suitable for customer support teams, content administrators, and multilingual content managers. It is especially suitable for teams that need to frequently update Help Center content or handle customer support conversations, which can significantly improve work efficiency.

Main features

Article management
Complete article lifecycle management: create, read, update, and search articles. Support multilingual content management.
Collection management
Manage Help Center classification collections: view, update, and delete collections. Support multilingual translation.
Customer support workflow
Automate customer support processes: reply to conversations, add internal notes, close conversations, and update ticket status.
Multilingual support
Support multilingual content management in Chinese, English, Japanese, etc. You can easily add or update translations.
Intelligent search and highlighting
Full-text search function with keyword highlighting for easy and quick location of relevant content.
Advantages
No need to switch tools: Manage Intercom content directly in Claude
Natural language operation: Complete complex operations with simple instructions
Multilingual management: Easily manage multilingual Help Center content
Improve efficiency: Automate repetitive customer support tasks
Real-time update: Content changes take effect immediately
Limitations
Requires the Claude desktop application: Only applicable to Claude users
Initial configuration is complex: Requires setting environment variables and paths
Limited functionality: Only supports some Intercom API functions
Requires API permissions: Requires Intercom administrator permissions to obtain an access token

How to use

Get an Intercom access token
Log in to the Intercom backend, go to Settings → Developers → Developer Center, create an application, and obtain an access token with read and write permissions for articles and conversations.
Install and build the project
Clone the GitHub repository, install dependencies, and build the project.
Configure the Claude desktop application
Use the Claude Code CLI to add the MCP server, or manually edit the Claude desktop configuration file.
Restart and verify
Completely exit and restart the Claude desktop application to verify if the MCP server is working properly.

Usage examples

Multilingual content management
Add Chinese and Japanese translations to an existing English Help Center to ensure that all users can get localized help content.
Quick response to customer questions
A customer asks a question about subscriptions in a conversation. You need to quickly reply and provide a link to the relevant help article.
Help Center content update
After a product update, you need to synchronously update the relevant Help Center articles to ensure that the documentation is consistent with the product features.

Frequently Asked Questions

What if the Intercom tool is not displayed in the Claude desktop application?
What if the API returns an error?
Can a deleted collection be restored?
Which languages are supported for content management?
What kind of Intercom permissions are required?

Related resources

Intercom Articles API Documentation
Intercom official API documentation, including all available endpoints and parameter descriptions
GitHub Repository
Intercom MCP Server source code and latest version
MCP TypeScript SDK
TypeScript SDK required for developing the MCP server
MCP Official Documentation
Model Context Protocol official documentation and specifications

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "intercom-mcp": {
      "command": "node",
      "args": [
        "/ABSOLUTE/PATH/TO/intercom-mcp/dist/index.js"
      ],
      "env": {
        "INTERCOM_ACCESS_TOKEN": "your_intercom_access_token_here",
        "INTERCOM_ADMIN_ID": "your_admin_id_here"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

A
Airweave
Airweave is an open - source context retrieval layer for AI agents and RAG systems. It connects and synchronizes data from various applications, tools, and databases, and provides relevant, real - time, multi - source contextual information to AI agents through a unified search interface.
Python
16.2K
5 points
V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
10.5K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
10.1K
4.5 points
H
Haiku.rag
Haiku RAG is an intelligent retrieval - augmented generation system built on LanceDB, Pydantic AI, and Docling. It supports hybrid search, re - ranking, Q&A agents, multi - agent research processes, and provides local - first document processing and MCP server integration.
Python
17.9K
5 points
C
Cipher
Cipher is an open-source memory layer framework designed for programming AI agents. It integrates with various IDEs and AI coding assistants through the MCP protocol, providing core functions such as automatic memory generation, team memory sharing, and dual-system memory management.
TypeScript
0
5 points
A
Apple Notes MCP
A server that provides local Apple Notes database access for the Claude desktop client, supporting reading and searching of note content.
Python
14.5K
4.3 points
M
MCP Server Weread
The WeRead MCP Server is a lightweight service that bridges WeRead data and AI clients, enabling in - depth interaction between reading notes and AI.
TypeScript
16.7K
4 points
M
MCP Obsidian
This project is an MCP server used to interact with the Obsidian note application through the Local REST API plugin of Obsidian. It provides various tools to operate and manage files in Obsidian, including listing files, retrieving file content, searching, modifying content, and deleting files.
Python
24.2K
5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
39.1K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
24.8K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
80.2K
4.3 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
28.4K
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
38.4K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
69.5K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
24.9K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
56.3K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase