mcpField
A
amorphous

amorphous

Local
github.com/amorphous-oneOther0Updated 3w ago

About amorphous

Amorphous lets people and their agents create and manage abstracts, which can take many forms. Its plugin installs a skill and starts a local MCP server, while the CLI handles content on amorphous.one.

Key features

  1. 01Install the Amorphous skill
  2. 02Start a local MCP server
  3. 03List and preview abstracts
  4. 04Pull and push abstracts
  5. 05Publish abstracts and invite others

Use cases

  1. 01List or preview abstracts from the CLI
  2. 02Pull and edit abstracts locally before pushing
  3. 03Publish an abstract on amorphous.one
  4. 04Invite others to an abstract

MCP support

The plugin starts a local MCP server by running `npx -y [email protected] mcp`. The server does not open a remote connection; sign-in and abstract operations are handled by the CLI.

Configuration

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

mcp.json · Universal config
{
"mcpServers": {
"amorphous-one-amorphous": {
"command": "npx",
"args": [
"-y",
"amorphous-cli"
]
}
}
}
Run commandnpx -y amorphous-cli

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmamorphous-cli0.1.8

Tools

6

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
searchstringNoPart of an abstract name

Details

From the project README

Amorphous

Amorphous lets a person or their agent build abstracts. There can be many. An abstract can be anything.

This plugin installs the Amorphous skill and starts a local MCP server on your computer. The server runs npx -y [email protected] mcp. It does not open a remote connection. Sign in with amorphous login in the browser on the same computer. The CLI then lists, pulls, pushes, previews, publishes, and invites on https://amorphous.one.

npx -y [email protected] setup

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.