# Comanda

> The CLI-native orchestrator for AI agent workflows. Run Claude Code, Codex, Gemini CLI & Kimi Code from declarative YAML. Because the terminal is where real work happens.

- **Type:** MCP server
- **Install:** `agentstack add mcp-kris-hansen-comanda`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [kris-hansen](https://agentstack.voostack.com/s/kris-hansen)
- **Installs:** 0
- **Category:** [Cloud & Infrastructure](https://agentstack.voostack.com/c/cloud-infrastructure)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [kris-hansen](https://github.com/kris-hansen)
- **Source:** https://github.com/kris-hansen/comanda
- **Website:** https://comanda.sh

## Install

```sh
agentstack add mcp-kris-hansen-comanda
```

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

## About

# comanda

Declarative AI workflows for the command line.

Comanda turns repeatable AI work into YAML pipelines you can run, review, and
version control. Use it to generate workflows from natural language, run
multi-model pipelines, orchestrate agentic loops, process files, call tools, and
wire Claude Code, Gemini CLI, OpenAI Codex, Kimi Code, and API models together.

For the full guide, feature tour, and copy-ready workflow templates, start at
[comanda.sh](https://comanda.sh):

- [Features](https://comanda.sh/features)
- [Templates](https://comanda.sh/templates)
- [GitHub examples](examples/README.md)

## Install

```bash
brew install kris-hansen/comanda/comanda
```

Or install with Go:

```bash
go install github.com/kris-hansen/comanda@latest
```

See [GitHub Releases](https://github.com/kris-hansen/comanda/releases) for
prebuilt binaries.

## Quick Start

```bash
comanda configure
comanda generate workflow.yaml "review this code for bugs"
comanda process workflow.yaml
```

Pipe input through a workflow:

```bash
cat main.go | comanda process workflow.yaml
```

Inspect or iterate on a workflow:

```bash
comanda chart workflow.yaml
comanda improve workflow.yaml "Add security findings and suggested fixes"
```

## Minimal Workflow

```yaml
summarize:
  input: STDIN
  model: gpt-4o
  action: "Summarize the input in three bullets."
  output: STDOUT
```

Run it:

```bash
cat notes.md | comanda process summarize.yaml
```

## What You Can Build

- Multi-agent reviews with Claude Code, Gemini CLI, OpenAI Codex, Kimi Code, and API models
- Agentic loops that iterate until work is complete
- File, URL, image, PDF, database, and batch-processing workflows
- Tool-enabled workflows with explicit command allowlists
- Codebase indexes for persistent project context
- Git worktree workflows for parallel isolated implementation
- Server-backed workflows callable over HTTP
- MCP server mode exposing workflows as tools and skills as prompts

## More Examples

Most examples and walkthroughs live on [comanda.sh](https://comanda.sh):

- [Browse workflow templates](https://comanda.sh/templates)
- [Explore all features](https://comanda.sh/features)
- [Local examples directory](examples/README.md)
- [Multi-agent patterns](examples/multi-agent/README.md)
- [Agentic loops](examples/agentic-loop/)
- [Tool use](examples/tool-use/README.md)
- [Server API](docs/server-api.md)
- [MCP server](docs/mcp-server.md)

## MCP Server

Run comanda as an MCP server so agent clients (Claude Code, Kimi Code, Codex) can call workflows as tools and use skills as prompts:

```bash
comanda mcp
```

Each discovered workflow file (from `~/.comanda/workflows/`, `.comanda/workflows/`, `--dir`, or `--workflow`) becomes one MCP tool; each skill becomes an MCP prompt. See [docs/mcp-server.md](docs/mcp-server.md) and [examples/mcp/](examples/mcp/README.md) for client setup and a walkthrough.

## Development

```bash
make deps
make build
make test
```

## License

MIT

## Download History

[](https://skill-history.com/kris-hansen/comanda)

## Source & license

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

- **Author:** [kris-hansen](https://github.com/kris-hansen)
- **Source:** [kris-hansen/comanda](https://github.com/kris-hansen/comanda)
- **License:** MIT
- **Homepage:** https://comanda.sh

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-kris-hansen-comanda
- Seller: https://agentstack.voostack.com/s/kris-hansen
- 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%.