Tre

com.tre-appPublished by tre-app.comOfficial publisherv0.2.0Updated Oct 24, 2026

Tre — shared memory kanban for humans and agents (MCP Streamable HTTP).

VerifiedStreamable HTTPWeb executableProductivity & WorkflowKnowledge & Memory

Overview

AI-generated overview

Tre is a remote MCP server for a shared memory kanban that both people and AI agents can use, connected over Streamable HTTP with OAuth.

What you can do
  • Connect an assistant to a shared kanban board that acts as memory for humans and agents.
  • Read and work with board content through the remote MCP endpoint, so the assistant can recall and contribute to shared state.
  • Use it as a common place where agent activity and human tasks live side by side.
  • No tool list is published, so the exact operations available are not documented here.
When to use it
Worth adding when you want an assistant to share a persistent, board-shaped memory with you or a team instead of keeping context only in a conversation. Suited to agent workflows where tasks and notes need to be visible to both people and agents.
Requirements
A remote MCP endpoint at tre-app.com over Streamable HTTP; no local package or runtime is needed. OAuth authentication is required, and requests carry an Authorization header with a Bearer personal API token.
Before you install
Access is granted through a personal API token sent in the Authorization header, so treat it as a secret and revoke it if exposed. The board is shared between humans and agents, so anything the assistant writes may be visible to others, and the published tool list is empty, so review what it can change before granting access.

Installation

In SourceWeft

  1. Open Tre in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.tre-app%2Ftre/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "tre": {
      "type": "http",
      "url": "https://tre-app.com/api/mcp"
    }
  }
}

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v0.2.0LatestSep 16, 2026

Score

56% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts

    Publish an icon in the registry entry.

  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.