AFC Commander (Free Edition)
Enables managing a parametric CLI command registry with profile isolation and pipelines from Cursor agents via 11 MCP tools.
README
# AFC Commander Free Edition
AFC Commander Free Edition is a JSON-backed command registry and pipeline runner with a Model Context Protocol (MCP) server for Cursor. It is built for teams that want a persistent alias layer for shell commands, profile-based separation between workspaces or projects, and repeatable command execution without hand-maintaining long terminal commands.
## What this project is for
AFC Commander solves a simple operational problem: teams accumulate important shell commands, but those commands are easy to lose, hard to standardize, and tedious to retype. This tool keeps those commands in a durable registry, lets you organize them by profile, and gives you a single command-line interface (CLI) for adding, listing, searching, and executing them.
The repository also includes a local MCP server named `afc-commander-core`, which exposes the same registry and execution capabilities to Cursor through standard input and standard output (stdio). That means agents can work with the command registry without needing direct shell access to your environment.
## Core capabilities
AFC Commander includes:
- Persistent command aliases stored in JSON.
- Profile isolation so different projects or environments can keep separate command sets.
- Command lookup, listing, editing, export, history, and statistics.
- Pipeline support for chaining multiple commands into a repeatable flow.
- Job tracking for longer-running or resumable executions.
- A local MCP server for agent access from Cursor.
## What it does not try to be
This is not a general-purpose task runner, and it is not a replacement for a full CI (continuous integration) system. It is a structured command registry and execution layer for shell workflows you want to keep organized, reusable, and accessible from both the terminal and MCP-aware tooling.
## Requirements
- Node.js 20.12 or newer. Node.js is the JavaScript runtime that executes the CLI and server code.
- npm, the Node.js package manager, for installation.
- Cursor, if you want to register and use the MCP server from the editor.
## Installation
From the repository root:
```bash
node setup.cjs
That setup script:
- Installs the package dependencies.
- Installs
afc-commander-freeglobally so theafccommand is available in your terminal. - Creates a user data directory at
~/.afc-commanderunless you override it withAFC_HOME. - Registers the
afc-commander-coreMCP server in~/.cursor/mcp.json.
After setup, reload MCP in Cursor so the server is detected.
Verify the install
afc version
afc help
afc profile list
Typical workflow
Start by creating or switching to a profile. A profile is an isolated command namespace for a specific project, environment, or workflow.
afc profile create myproject "My project"
afc profile switch myproject
Add a command with a readable alias:
afc add hello "echo hello" -d "Say hello"
Run it:
afc -y hello
The -y flag confirms execution when the command would otherwise prompt.
Working with profiles
Profiles let you reuse the same alias in different contexts without collisions. For example, deploy can mean staging in one profile and production in another. That is useful when you want local command behavior to match the project you are currently working on.
Working with pipelines
Pipelines chain existing commands into an ordered execution flow. That is useful for repeatable routines such as build, test, deploy, cleanup, or environment preparation.
Common pipeline commands include:
afc pipeline create
afc pipeline list
afc pipeline show my-deploy
afc pipeline execute my-deploy
MCP tools
The local afc-commander-core server exposes these tools to MCP clients such as Cursor:
afc-list-commandsafc-search-commandsafc-execute-commandafc-add-commandafc-remove-commandafc-list-profilesafc-create-profileafc-switch-profileafc-list-pipelinesafc-create-pipelineafc-execute-pipeline
Data locations
By default, AFC Commander stores user data in:
~/.afc-commander
Other important locations:
~/.cursor/mcp.jsonfor MCP registration~/.afc-commander/install.jsonfor install metadata
You can move the user data directory by setting AFC_HOME before running setup.
Useful commands
Refresh MCP paths after moving the package or reinstalling:
node setup.cjs --mcp-only
Uninstall the package and MCP registration:
node uninstall.cjs
Remove the user data directory as well:
node uninstall.cjs --purge-data
Project layout
afc-commander/— CLI package and command implementationserver.js— MCP stdio entrypointsetup.cjs— installation scriptuninstall.cjs— uninstall scriptdocs/— usage, architecture, and help content
Development notes
The repository includes docs for the command parser, registry structure, help topics, and usage patterns. Those docs are useful if you want to understand how aliases are parsed, how profiles isolate commands, and how pipelines are stored.
License
See license.md for the project license.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.