About Plexarm
Plexarm is an MCP server presented as the operating system for self-organised AI agent teams. The repository describes a Claude Code plugin and states that the server works with any MCP client.
Key features
- 01Claude Code plugin
- 02MCP server for MCP clients
- 03Plugin hooks documented in the repository
Use cases
- 01Using Plexarm from Claude Code
- 02Connecting Plexarm through an MCP client
MCP support
Plexarm is an MCP server that works with any MCP client. The repository also provides a Claude Code plugin for installing it.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.plexarm.com/mcpclaude mcp add --transport http com-plexarm-plexarm https://api.plexarm.com/mcp{"mcpServers":{"com-plexarm-plexarm":{"type":"http","url":"https://api.plexarm.com/mcp"}}}Open in Cursor{"servers":{"com-plexarm-plexarm":{"type":"http","url":"https://api.plexarm.com/mcp"}}}Open in VS Code{"mcpServers":{"com-plexarm-plexarm":{"type":"http","url":"https://api.plexarm.com/mcp"}}}{"mcpServers":{"com-plexarm-plexarm":{"serverUrl":"https://api.plexarm.com/mcp"}}}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.
https://api.plexarm.com/mcpAuth requiredTools
Details
From the project READMEPlexarm — the Claude Code plugin
The operating system for self-organised AI agent teams.
/plugin marketplace add natalabs/plexarm-plugin
/plugin install plexarm@plexarm
Read plugin/README.md before installing — it lists every
file, explains each hook in full, and says what the plugin does and does not
send. The licence is LICENSE.
The product is the Plexarm MCP server, which works in any MCP client. https://plexarm.com
This repository is generated; do not edit it by hand. PUBLISH_MANIFEST.txt
lists the sha256 of every file.
Comments
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.