
Chanty
- Updated December 31, 2025
- asklokesh/chanty-mcp-server
Chanty MCP Server is a MCP server that lets coding agents call the Chanty API using an API key over stdio.
About
Chanty MCP Server exposes Chanty’s team messaging API to AI coding agents through a stdio Model Context Protocol package. It is aimed at developers and tiny teams who already use Chanty for day-to-day coordination and want summaries, draft replies, or lightweight API actions driven from the same session where they fix bugs. Setup is relatively beginner-friendly: install via uvx, provide CHANTY_API_KEY, optionally override CHANTY_API_URL, and register the server in your agent config. The integration is phase-specific to Grow because its value shows up when you are supporting customers, syncing with helpers, and keeping context out of scattered screenshots. It is not a full replacement for Chanty’s UI for rich media or complex channel management, but it reduces context switching when an agent needs to act on chat-backed workflows. Treat it as a communication MCP connector, not a growth strategy or CRM skill.
- stdio MCP server (v0.1.0) on PyPI as chanty-mcp-server, runnable with uvx
- CHANTY_API_KEY required; optional CHANTY_API_URL for custom or regional endpoints
- Hooks team chat into Claude Code, Cursor, Codex, and similar MCP clients
- Useful for solo founders pinging contractors or logging shipping notes from the IDE
- Published under asklokesh with MCP 2025-12-11 server schema metadata
Chanty by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add --env CHANTY_API_KEY=YOUR_CHANTY_API_KEY --env CHANTY_API_URL=YOUR_CHANTY_API_URL chanty-mcp-server -- uvx chanty-mcp-serverAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Package | chanty-mcp-server |
|---|---|
| Transport | STDIO |
| Auth | Required |
| Last updated | December 31, 2025 |
| Repository | asklokesh/chanty-mcp-server ↗ |
What it does
Post updates, read team threads, and coordinate support from your agent without opening Chanty in another tab.
Who is it for?
Best when you standardize on Chanty and want MCP-driven messaging helpers.
Skip if: Slack-only shops, teams without a Chanty API key, or workflows that need deep Chanty admin not exposed via API.
What you get
With the MCP server registered, your agent can interact with Chanty API endpoints from chat-driven commands in your IDE.
- Live Chanty MCP stdio connection in your agent
- API-key-authenticated Chanty requests from agent sessions
- Optional custom base URL via CHANTY_API_URL
By the numbers
- Server version 0.1.0
- 1 required secret env var: CHANTY_API_KEY
- Optional CHANTY_API_URL environment variable
README.md
Chanty MCP Server
A Model Context Protocol (MCP) server for integrating Chanty with GenAI applications.
Overview
Team collaboration and communication platform
Features
- Comprehensive Chanty API coverage
- Multiple authentication methods
- Enterprise-ready with rate limiting
- Full error handling and retry logic
- Async support for better performance
Installation
pip install chanty-mcp-server
Or install from source:
git clone https://github.com/asklokesh/chanty-mcp-server.git
cd chanty-mcp-server
pip install -e .
Configuration
Create a .env file or set environment variables according to Chanty API requirements.
Quick Start
from chanty_mcp import ChantyMCPServer
# Initialize the server
server = ChantyMCPServer()
# Start the server
server.start()
License
MIT License - see LICENSE file for details
Recommended MCP Servers
How it compares
Chanty API MCP connector, not a customer-support playbook skill.
FAQ
Who is Chanty MCP Server for?
Developers and micro-teams on Chanty who want their AI agent to reach team chat APIs from Claude Code or Cursor.
When should I use Chanty MCP Server?
Use it in Grow support workflows when coordinating launches, contractors, or user issues from your development environment.
How do I add Chanty MCP Server to my agent?
Configure stdio to run uvx chanty-mcp-server, set CHANTY_API_KEY (and CHANTY_API_URL if needed), then reload MCP in your agent.