mcpField
A
AsyncFlow

AsyncFlow

Remote
flow.async.omOther0Updated today

About AsyncFlow

AsyncFlow connector lets teams work with company tickets from AI chats, within the access they grant when connecting. It supports operations from search and comments to assignment, transitions, and attachment management without sharing the AsyncFlow password with the chat.

Key features

  1. 01Search and read tickets
  2. 02Create, update, and assign tickets
  3. 03Transition, link, and archive tickets
  4. 04Comment on tickets and manage attachments
  5. 05View ticket history and workspace summaries

Use cases

  1. 01Find open tickets in an AI chat
  2. 02Update ticket status or assignee from a discussion
  3. 03Add comments or files to tickets
  4. 04Review workspace progress and ticket history

MCP support

The remote MCP connector uses Streamable HTTP and OAuth to connect to AsyncFlow and expose ticket and workspace operations to compatible clients. Users choose the company and access scope when connecting, and workspace roles continue to apply.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://flow.async.om/api/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

AsyncFlow connector

Use your AsyncFlow tickets from an AI chat. You can search, open, create, update, assign, move and comment on tickets in your own company, with the access you choose when you connect.

The connector address is:

https://flow.async.om/api/mcp

When you connect, a browser opens. Sign in to AsyncFlow, pick the company and tick the access to allow. Nothing is installed on your computer, and your AsyncFlow password never reaches the chat. You can disconnect a chat at any time in AsyncFlow under Settings → Connected apps.

Claude Code

Install the plugin. It sets up the connector and adds a skill that tells Claude how to work with tickets safely.

/plugin marketplace add iamsj7/asyncflow-mcp
/plugin install asyncflow@asyncflow

Then run /mcp, choose asyncflow and sign in.

To add only the connector, without the skill:

claude mcp add --transport http asyncflow https://flow.async.om/api/mcp

Claude (web and desktop)

Settings → Connectors → Add custom connector. Name it AsyncFlow and paste the address above.

ChatGPT

Add a custom connector in ChatGPT's settings and paste the address above. This needs a plan that allows custom connectors.

Cursor

Add this to ~/.cursor/mcp.json:

{ "mcpServers": { "asyncflow": { "url": "https://flow.async.om/api/mcp" } } }

VS Code

code --add-mcp '{"name":"asyncflow","type":"http","url":"https://flow.async.om/api/mcp"}'

Other chats

Any client that supports remote MCP servers over streamable HTTP with OAuth can connect. If the chat says its redirect address isn't allowed, send that address to Async Solution and it will be added.

What the chat can do

AccessWhat the chat can do
See the company and its workspaceswhoami, list_projects
Read tickets you can already readlist_ticket_options, search_tickets (board filters: created or resolved dates, due, assigned to me, SLA and more), get_tickets, get_ticket, get_ticket_history, workspace_summary, get_attachment (images are shown to the chat)
Create and manage ticketscreate_ticket, update_ticket (any field, parent), assign_ticket, transition_ticket, link_tickets, unlink_tickets, request_approval, decide_approval, log_time, upload_attachment, start_upload, attach_file, remove_attachment, archive_tickets, restore_tickets, list_archived_tickets
Add commentsadd_comment (with files)

Your role in each workspace still applies, and the chat can't delete anything. Due dates and other planning fields stay visible to the delivery team only.

Microsoft Teams and Microsoft 365 Copilot

In Copilot Studio, create an agent, add a tool of type Model Context Protocol with the address above and OAuth 2.0, dynamic discovery, and publish it to the Teams and Microsoft 365 Copilot channel. Copilot Studio shows a callback URL: send it to Async Solution so it can be allowed.

Licence

MIT. This repository only holds the connector setup. The AsyncFlow service is operated by Async Solution.

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.