Advertise
MCP.so
Sign In
W

Work With Alloy MCP Server

@Alloy-Systems

Repository

Basic information

Category

Other

Transports

stdio

Author

Alloy-Systems

Submitted by

Artem Burachenok

About Work With Alloy MCP Server

Alloy is an AI-native workspace where teams and AI agents share knowledge, artifacts, workflows, and controlled access to external systems through one common operating layer.

#alloy#mcp#workspace#agents#knowledge#workflow

Work With Alloy MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "alloy": {
      "type": "http",
      "url": "https://api.alloy.cx/mcp",
      "bearer_token_env_var": "ALLOY_TOKEN"
    }
  }
}

Work With Alloy MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list directly from this server's endpoint using the button above.

Overview

What is Work With Alloy?

Work With Alloy is a plugin that teaches any AI agent (Claude, Codex, Gemini, Alloy cloud agents) to use Alloy as its shared source of truth. It gives agents reusable operating skills – reading shared knowledge, writing durable notes and artifacts, creating workflows, and spawning autonomous agents. Alloy itself is an AI-native workspace where teams and AI agents collaborate on a single foundation.

How to use Work With Alloy?

Install the plugin into Claude Code or Codex from the Alloy marketplace. Set the ALLOY_TOKEN environment variable in your host shell before starting the host. After installing, restart the host so the bundled MCP config is loaded. Verify installation with claude mcp list (expect plugin:work-with-alloy:alloy as connected). For Codex use codex plugin marketplace add Alloy-Systems/alloy-marketplace; for Claude Code use /plugin marketplace add Alloy-Systems/alloy-marketplace then /plugin install work-with-alloy@alloy-marketplace.

Key features of Work With Alloy

  • Shared source-of-truth skill (work-with-alloy) for all agents.
  • Read organizational knowledge before answering queries.
  • Write durable artifacts back to Alloy (proposals, specs, logs).
  • Access approved business systems through Alloy-controlled MCP.
  • Coordinate multi-agent operations with task handoffs via MCP/API.
  • Call Alloy cloud agents for delegated work from outputs.

Use cases of Work With Alloy

  • Read company docs, decisions, and knowledge notes before answering.
  • Write research summaries and decisions that future agents can reuse.
  • Access CRM, support, docs, calendars, and databases through a single Alloy integration.
  • Configure AI teammates, skills, and workflows as governed organizational processes.
  • Run operational reviews auditing teammates, MCPs, and recent activity.

Frequently asked questions

1

What environment variable is required?

The `ALLOY_TOKEN` environment variable must be set in the host shell before starting Claude Code or Codex. The bundled `.mcp.json` reads the Alloy MCP bearer token from this variable.

2

How do I get an Alloy token?

Obtain your token at [alloy.cx/docs/reference/tech-docs/hosted-mcp](https://alloy.cx/docs/reference/tech-docs/hosted-mcp).

3

Which AI hosts are supported?

Claude Code and Codex (OpenAI) are the currently validated hosts. The plugin manifests are thin wrappers around the shared skill content and are intended to remain host-neutral.

4

What transport and authentication does the MCP use?

The MCP uses Alloy hosted MCP with bearer token authentication. The token is provided via the `ALLOY_TOKEN` environment variable.

Comments

More Other MCP servers

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K

EverArt

modelcontextprotocol

Model Context Protocol Servers

88.1K

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K

MCP Toolbox for Databases

googleapis

MCP Toolbox for Databases is an open source MCP server for databases.

15.9K
Advertise