# Mcp2cli

> MCP -> CLI + SKILLs. Maintain SKILL pararllel with MCP Server.

- **Type:** MCP server
- **Install:** `agentstack add mcp-makabakaxy-mcp2cli`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [makabakaxy](https://agentstack.voostack.com/s/makabakaxy)
- **Installs:** 0
- **Category:** [Integrations](https://agentstack.voostack.com/c/integrations)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [makabakaxy](https://github.com/makabakaxy)
- **Source:** https://github.com/makabakaxy/mcp2cli

## Install

```sh
agentstack add mcp-makabakaxy-mcp2cli
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# mcp2cli/mcp2skill
> Also known as: **mcp2skill** · **mcp-to-cli** · **mcp-to-skill** · **mcpcli**
Convert MCP servers into CLI and Agent SKILLs.

## Why

For example, install [zereight/gitlab-mcp](https://github.com/zereight/gitlab-mcp) — it exposes **122 tools** across 14 categories (merge requests, issues, pipelines, wikis, etc.). Every tool schema gets injected into your AI conversation context on every request. We measured this directly against the Claude API:

| Per-request input tokens | Before (raw MCP) | After (mcp2cli) |
|---|---|---|
| Your message | 20 | 20 |
| Tool definitions (122 tools) | 27,969 | — |
| Skill file (1 file) | — | ~800 |
| **Total** | **27,989** | **~820** |
| **Reduction** | | **~97%** |

After `mcp2cli convert`, your AI agent stops seeing 122 tool definitions. Instead, it reads one small skill file, and calls CLI commands like `mcp2cli gitlab mr create --project-id 123 --title "Fix bug"` to get the job done.

Beyond token savings, some projects maintain both a CLI and an MCP server in parallel (e.g. the GitLab MCP server vs. the `glab` CLI). Keeping two interfaces in sync is a maintenance burden and inevitably leads to feature drift. mcp2cli eliminates the need — one MCP server, one generated CLI, always consistent.

## Quick Start

```bash
pip install mcp-to-cli
```

If you already have an MCP server configured in Claude, Cursor, or Codex:

```bash
mcp2cli list              # See which MCP servers are available
mcp2cli convert gitlab-mcp
```

That's it. Your MCP server is now a CLI, and the compressed skill files are synced to your AI clients.

> **Tip:** After install or convert, you can edit `~/.agents/mcp2cli/servers.yaml` to update env vars (API keys, endpoints, etc.) without re-running the full setup.

## How It Works

`mcp2cli convert gitlab-mcp` runs a 3-phase pipeline:

```
┌──────────────┐      ┌──────────────┐      ┌──────────────┐
│  1. Extract  │─────>│  2. Generate │─────>│   3. Sync    │
│              │      │              │      │              │
│  Read config │      │ AI-generate  │      │ Copy skills, │
│  from Claude,│      │ CLI + skill  │      │ disable MCP  │
│  Cursor,Codex│      │              │      │              │
└──────┬───────┘      └──────┬───────┘      └──────┬───────┘
       v                     v                     v
 mcp_servers.json    cli.yaml + SKILL.md    ~/.claude/skills/
```

1. **Extract** — Reads your MCP server config from Claude (`~/.claude.json`) / Cursor (`~/.cursor/mcp.json`) / Codex (`~/.codex/config.toml`)
2. **Generate** — Connects to the MCP server, discovers all tools, and uses AI to generate a CLI command tree (`cli.yaml`) and a compressed skill file (`SKILL.md`)
3. **Sync** — Copies skill files to your AI clients and disables the raw MCP server

Each skill directory contains a `users/` subdirectory where you can add your own notes and workflows. This directory is never overwritten by `mcp2cli`.

At runtime, the generated CLI resolves commands to MCP tool calls through a lightweight daemon:

```
mcp2cli gitlab mr list --project-id 123
        │
        │  resolve via cli.yaml
        v
  tool: gitlab_list_merge_requests(project_id=123)
        │
        v
  ┌─────────┐     MCP protocol     ┌────────────┐
  │ mcp2cli │ ──────────────────>  │ MCP Server │
  │ daemon  │ ` | Use this when the MCP server is already configured in Claude, Cursor, or Codex and you want to convert it into a generated CLI + synced skills. |
| `mcp2cli install ` | Use this when the server is not exist yet and you want `mcp2cli` to install/register it, then generate or pull the CLI + skills for you. |
| `mcp2cli update ` | Use this after the MCP server adds, removes, or changes tools and you need to regenerate the local CLI mapping and skill files. |
| `mcp2cli uninstall ` | Use this when you want to remove generated CLI/skill artifacts for a server. |

### Presets
| Command | When to use |
|---|---|
| `mcp2cli preset list [server]` | Use this to check whether a pre-generated preset already exists before running AI generation. |
| `mcp2cli preset pull ` | Use this when a preset already exists and you want the CLI + skill files immediately without waiting for scan/generation. |
| `mcp2cli preset export ` | Use this to package your local generated files into a reusable preset bundle. |
| `mcp2cli preset push ` | Use this when you want to publish a local preset to the shared preset registry. |

## License

MIT

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [makabakaxy](https://github.com/makabakaxy)
- **Source:** [makabakaxy/mcp2cli](https://github.com/makabakaxy/mcp2cli)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-makabakaxy-mcp2cli
- Seller: https://agentstack.voostack.com/s/makabakaxy
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.