kChat MCP Server
Enables interaction with the kChat platform to manage channels, post messages, and handle message threads. It also allows users to retrieve channel histories, manage emoji reactions, and access workspace user profile information.
README
kChat MCP Server
MCP Server for the kChat API.
Tools
-
kchat_list_channels- List public channels
- Optional inputs:
limit(number, default: 100, max: 200): Maximum number of channels to returnpage(number, default: 0): Pagination page
- Returns: List of channels with their IDs and information
-
kchat_post_message- Post a new message to a kChat channel
- Required inputs:
channel_id(string): The ID of the channel to post totext(string): The message text to post
- Returns: Message post
-
kchat_reply_to_thread- Reply to a specific message thread
- Required inputs:
channel_id(string): The channel containing the threadthread_id(string): The parent message IDtext(string): The reply text
- Returns: Message post
-
kchat_add_reaction- Add an emoji reaction to a message
- Required inputs:
post_id(string): The message IDreaction(string): Emoji name without colons
- Returns: Reaction
-
kchat_get_channel_history- Get recent messages from a channel
- Required inputs:
channel_id(string): The channel ID
- Optional inputs:
limit(number, default: 10): Number of messages to retrieve
- Returns: List of messages with their content and metadata
-
kchat_get_thread_replies- Get all replies in a message thread
- Required inputs:
thread_id(string): The parent message ID
- Returns: List of replies with their content and metadata
-
kchat_get_users- Get list of workspace users with basic profile information
- Optional inputs:
limit(number, default: 100, max: 100): Maximum number of users to returnpage(number, default: 0): Pagination page
- Returns: List of users with their basic profiles
-
kchat_get_user_profile- Get detailed profile information for a specific user
- Required inputs:
user_id(string): The user's ID
- Returns: Detailed user profile information
-
kchat_send_direct_message- Send a direct message to a user by username
- Required inputs:
username(string): The username of the user to send the message totext(string): The message text to send
- Returns: Message post
Setup
-
Create a kChat token linked to your user:
- Visit the API Token page
- Choose "kChat" scope
Create a kChat token linked to a bot:
- Visit your kChat webapp and click on New > Integrations > Bot accounts > Add bot accounts
-
Get your kChat team name from your kChat url (eg. https://your-team.kchat.infomaniak.com/your-team/channels/town-square url have
your-teamteam)
Usage with Claude Desktop
Add the following to your claude_desktop_config.json:
NPX
{
"mcpServers": {
"kchat": {
"command": "npx",
"args": [
"-y",
"@infomaniak/mcp-server-kchat"
],
"env": {
"KCHAT_TOKEN": "your-token",
"KCHAT_TEAM_NAME": "your-team"
}
}
}
}
docker
{
"mcpServers": {
"kchat": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"KCHAT_TOKEN",
"-e",
"KCHAT_TEAM_NAME",
"infomaniak/mcp-server-kchat"
],
"env": {
"KCHAT_TOKEN": "your-token",
"KCHAT_TEAM_NAME": "your-team"
}
}
}
}
Environment Variables
KCHAT_TOKEN: Required. Your kChat token.KCHAT_TEAM_NAME: Required. Your kChat team unique name.
Troubleshooting
If you encounter permission errors, verify that:
- All required scopes are added to your kChat token
- The token and team name are correctly copied to your configuration
Build
Docker build:
docker build -t infomaniak/mcp-server-kchat -f Dockerfile .
License
This MCP server is licensed under the MIT License.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。