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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.