AgentX

com.agentxhqPublished by agentxhq.comOfficial publisherv1.0.1Updated Nov 7, 2026

Cloud console for a fleet of AI coding agents running on your own machines. OAuth.

VerifiedStreamable HTTPWeb executableProductivity & Workflow Developer Tools

Server details

Identifier: com.agentxhq/agentx
Transport: Streamable HTTP
Runtime: Web executable
Trust: Verified
Published: Oct 29, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified that this server's namespace belongs to agentxhq.com, which also runs its endpoint. That identifies the publisher; it does not make the server's tools safe.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/com.agentxhq%2Fagentx.svg)](https://sourceweft.com/mcp/com.agentxhq%2Fagentx?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Remote MCP endpoint for AgentX, a cloud console for a fleet of AI coding agents on your own machines, letting an assistant check agents, hand them work and…

What you can do: Identify the connected account and client
List and inspect agents, check their output and interrupt them
List chats and chat members, and create new chats
Send messages to agents and wait for events
List and read published artifacts
Creating, configuring or deleting agents, automations and skills is not available over this connection
When to use it: Use it when you already run AgentX coding agents on your own machines and want an AI assistant to monitor them, dispatch work to them, and read back what they produce without opening the console.
Requirements: A remote MCP client that supports Streamable HTTP with OAuth sign-in; clients limited to local stdio servers or fixed API keys cannot connect. An AgentX account with at least one claimed daemon and agent. Sign-in uses OAuth 2.1 with PKCE in the browser and dynamic client registration, so no client ID, API key or token is entered. Nothing to install.

Before you install

Sign-in grants access to your AgentX account; the mcp permission is required, while workplane:read covers listing agents, reading output, waiting for events and listing chats and artifacts, and workplane:write covers sending messages, creating chats and interrupting agents. Untick what you do not need and revoke clients in Settings. Sending messages and interrupting agents act on running work. The server is hosted by AgentX ApS, so agent data passes through their cloud.

Installation

In SourceWeft

Open AgentX in the dashboard and add it to a workspace.
Connect the required credentials. They are stored privately and never shown on public pages.
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.agentxhq%2Fagentx/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": {
    "agentx": {
      "type": "http",
      "url": "https://www.agentxhq.com/mcp"
    }
  }
}

README

[AgentX]

AgentX MCP server

Connect your AI assistant to AgentX through the AgentX MCP server:

AgentX is a cloud console for a fleet of AI coding agents that run on your own machines through the AgentX daemon. Once your assistant is connected, it can check on your agents, hand them work, and read what they publish.

This repository has no code. The server is hosted by AgentX ApS. The repository holds the listing details MCP directories use: this README, server.json and the logo.

Connect

Server URL: https://www.agentxhq.com/mcp
Transport: remote server over Streamable HTTP
Sign-in: OAuth 2.1 with PKCE in your browser. AgentX registers your client itself (dynamic client registration), so there is no client ID, API key or token to enter, and nothing to install.
Discovery: https://www.agentxhq.com/.well-known/oauth-protected-resource

Easiest way: paste this prompt into Claude Code, Codex or any AI client that supports MCP. It adds AgentX and opens the sign-in for you.

Connect yourself to my AgentX account.Read https://www.agentxhq.com/mcp.md and follow it.When you're connected, show me my agents and ask me what I want to do.

Connect yourself to my AgentX account.Read https://www.agentxhq.com/mcp.md and follow it.When you're connected, show me my agents and ask me what I want to do.

By hand: add https://www.agentxhq.com/mcp as a remote (HTTP) MCP server named agentx, leave any OAuth client ID and secret empty, and start the sign-in.

Your client must support remote MCP servers over Streamable HTTP with OAuth sign-in. A client that only supports local (stdio) servers or fixed API keys cannot connect to AgentX.

Before you connect

You need an AgentX account with at least one claimed daemon and agent. If you don't have one yet, start at agentxhq.com/install.

What you approve

You sign in on a page titled "Connect to AgentX". The next page, "<your client> wants access", shows what the connection asks for. You can untick any of these:

Permission	What it allows
`mcp`	Use the AgentX MCP endpoint at all. Required.
`workplane:read`	List agents, read their output, wait for events, list chats and artifacts.
`workplane:write`	Send messages to agents, create chats, interrupt agents.

You can see and revoke connected clients at agentxhq.com/settings/connected (Settings → Connected apps).

What your assistant can do

Area	Tools
Identity	`whoami`, `agentx_identity`
Agents	`list_agents`, `get_agent`, `check_agent_output`, `interrupt_agent`
Chats	`list_chats`, `list_chat_members`, `create_chat`
Messaging	`send_message`, `wait`
Artifacts	`list_artifacts`, `get_artifact`

Creating, configuring or deleting agents, automations and skills is not available over this connection; that happens in the AgentX console.

The full tool reference is in mcp.md and the MCP docs.

Tools

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

v1.0.1LatestOct 31, 2026
v1.0.0Oct 29, 2026

Score

85% 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
Documentation15 pts
License10 pts