mcpField
T
Twist MCP Server (testing)

Twist MCP Server (testing)

Local
github.com/mikemcCommunication1Updated 77w ago
Repository

About Twist MCP Server (testing)

Twist MCP Server (testing) is a Python server for interacting with a Twist workspace through the Twist REST API. It is intended for testing and provides tools for inbox and thread management.

Key features

  1. 01Read and manage inbox threads
  2. 02Create, update, and remove threads
  3. 03Star, pin, mute, and move threads
  4. 04Mark threads read or unread
  5. 05Retrieve workspace and channel threads

Use cases

  1. 01Review and archive inbox items
  2. 02Manage threads in a Twist channel
  3. 03Track unread threads across a workspace

MCP support

Exposes Twist inbox and thread operations as tools for MCP clients, using the Twist REST API. The README describes configuration for Claude Desktop.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Twist MCP Server (testing)

An MCP server for interacting with a Twist workspace. Written in Python using the Twist REST API. Currently for testing purposes only.

Installation

Prerequisites
Getting a Twist API Token
  1. Log in to your Twist account
  2. Visit the Twist App console
  3. Create a new application for personal use
  4. Copy the OAuth 2 test token; this token will give the MCP server full scope access to the currently logged in user.

Future versions will use proper OAuth authentication.

Configuration with Claude Desktop

Add the Twist MCP server to the set of MCP servers in your claude_desktop_config.json:

{
  "mcpServers": {
    "twist": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/twist-mcp-server",
        "run",
        "main.py"
      ],
      "env": {
        "TWIST_API_TOKEN": "your_twist_api_token",
        "TWIST_WORKSPACE_ID": "your_twist_workspace_id"
      }
    }
  }
}

Available Tools

As of now, the following tools are available:

  • Inbox
    • twist_inbox_get: Get the contents of the user's inbox
    • twist_inbox_archive_all: Archives all threads in a workspace (or, all threads after a given timestamp)
    • twist_inbox_archive: Archives a specific thread by ID
    • twist_inbox_unarchive: Unarchives a specific thread by ID
    • twist_inbox_mark_all_read: Marks all inbox threads as read
    • twist_inbox_get_count: Gets the count of inbox threads
  • Threads
    • twist_threads_getone: Get a thread by ID
    • twist_threads_get: Get all threads in a channel
    • twist_threads_add: Add a new thread to a channel
    • twist_threads_update: Update an existing thread
    • twist_threads_remove: Remove a thread
    • twist_threads_star: Star a thread
    • twist_threads_unstar: Unstar a thread
    • twist_threads_pin: Pin a thread
    • twist_threads_unpin: Unpin a thread
    • twist_threads_move_to_channel: Move a thread to a different channel
    • twist_threads_get_unread: Get unread threads in the workspace
    • twist_threads_mark_read: Mark a thread as read
    • twist_threads_mark_unread: Mark a thread as unread
    • twist_threads_mark_unread_for_others: Mark a thread as unread for others
    • twist_threads_mark_all_read: Mark all threads as read in a workspace or channel
    • twist_threads_clear_unread: Clear unread threads in the workspace
    • twist_threads_mute: Mute a thread for a number of minutes
    • twist_threads_unmute: Unmute a thread

License

This project is licensed under the MIT License. See the LICENSE file for details.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.