cli2mcp

cli2mcp

Status: v0.1 — early release. Stdio transport only. APIs may change before 1.0.

Expose any command-line binary as a Model Context Protocol tool by parsing its --help output and synthesizing a JSON Schema at startup. One command, no boilerplate.

Works with any MCP-compatible client — Claude Desktop, ChatGPT (via OpenAI Agents SDK), Cursor, Gemini CLI, Cline, Windsurf, Continue, Zed, and anything else that speaks the MCP stdio transport.

npx cli2mcp <command>

---

Why

Writing an MCP server for a CLI you already have is mechanical work: instantiate the SDK, register a tool, hand-write the input schema, marshal arguments, spawn the subprocess, format the output. Roughly 80–150 lines of TypeScript per binary, repeated forever as new tools come out.

cli2mcp does it in one command. The CLI's own --help is the source of truth for the schema — if rg adds a flag tomorrow, the AI sees it tomorrow without code changes.

---

Install

npm install -g cli2mcp

or invoke without installing

npx cli2mcp

Requires Node.js 22+.

---

Configure your MCP client

cli2mcp is launched by your client as a stdio subprocess. Add an entry per CLI you want to expose.

Claude Desktop

Config file location:

{

"mcpServers": { "ripgrep": { "command": "npx", "args": ["-y", "cli2mcp", "rg", "--name", "ripgrep"] }, "jq": { "command": "npx", "args": ["-y", "cli2mcp", "jq"] } } }

Restart Claude Desktop after editing.

Other clients

Refer to each client's documentation for the exact config path on your platform — they evolve and are not guaranteed to match the table above.

---

Quick wins — copy-paste configs

Drop any of these into your client's mcpServers block (paths shown above per client). Each one wraps a popular CLI as an MCP tool an AI can call directly.

{

"mcpServers": { "ripgrep": { "command": "npx", "args": ["-y", "cli2mcp", "rg", "--name", "ripgrep", "--description", "Recursively search files with regex"] }, "jq": { "command": "npx", "args": ["-y", "cli2mcp", "jq", "--description", "Query and transform JSON via stdin"] }, "pandoc": { "command": "npx", "args": ["-y", "cli2mcp", "pandoc", "--description", "Convert documents between markup formats"] }, "sqlite3": { "command": "npx", "args": ["-y", "cli2mcp", "sqlite3", "--description", "Run SQL against a SQLite database file", "--cwd", "/path/to/safe/dir"] }, "yt-dlp": { "command": "npx", "args": ["-y", "cli2mcp", "yt-dlp", "--description", "Download media from URLs", "--cwd", "/path/to/downloads", "--timeout", "300000"] } } }

Each CLI must already be installed and on PATH. cli2mcp does not install them for you.

---

How it compares

The closest neighbor is FastMCP's from_openapi — it does not cover arbitrary CLI binaries. As of April 2026 there is no other published tool that turns an arbitrary --help output into a typed MCP tool in one command.

---

Verified targets

These CLIs are covered by the test suite or have been manually exercised end-to-end:

Other POSIX-style CLIs (e.g. ffmpeg, yt-dlp, pandoc, sqlite3, imagemagick) are *expected* to work but are not yet covered by tests. Report bugs in issues.

---

How --help becomes a JSON Schema

When parsing fails on an unconventional --help, cli2mcp falls back to a single variadic args positional so the tool is still usable — the model just gets a free-form argument list instead of typed flags.

---

Options

cli2mcp <command> [options]

--name Tool name shown to the AI (default: ) --description Tool description shown to the AI (default: first --help line) --timeout Subprocess timeout per call (default: 60000) --cwd Working directory for subprocess (default: process.cwd()) --env Extra environment variables (repeatable) --stderr stderr handling: include → appended to tool output (default) drop → discarded error → any stderr → isError: true -h, --help Show help

Piping stdin

Reserved input property stdin is piped to the subprocess:

{ "args": [".name"], "stdin": "{\"name\": \"cli2mcp\"}" }

---

How it works

cli2mcp rg

│ ├─ 1. spawn: rg --help → capture stdout + stderr ├─ 2. parse help text → CliShape { flags, positionals, description } ├─ 3. synthesize JSON Schema → inputSchema ├─ 4. register one MCP tool → name: "rg", schema: └─ 5. start stdio MCP server → await client connection

On tools/call: { args, flags, stdin? } → argv builder → execa(rg, argv, { stdin }) │ stdout (+ stderr) → content[text]

Non-zero exit → { isError: true, content: [{ type: "text", text: }] } (unless --stderr drop).

---

Security

cli2mcp lets an AI agent invoke the CLIs you expose, with the arguments the agent chooses. You are responsible for what those CLIs can do on your machine.

Practical guidance:

• Only expose CLIs whose blast radius you accept. jq, rg, pandoc are mostly safe (read-only, deterministic). curl, ffmpeg --output, sqlite3, rm, kubectl, aws are not.
• The AI is not sandboxed. A prompt injection attack could cause an exposed curl to fetch evil.example.com, an exposed rm to delete files, etc.
• Use `--cwd` to constrain filesystem scope when wrapping CLIs that touch files.
• Use `--env` deliberately. Do not pass through credentials the model shouldn't reach.
• Never expose `sh`, `bash`, `zsh`, `python -c`, or anything with eval semantics — that bypasses every safeguard cli2mcp provides.

The schema-from-help design *reduces* the risk of malformed argv but does not eliminate the risk of misuse. Treat each exposed CLI as a delegated capability, not a sandbox.

---

Troubleshooting

The CLI has no `--help` flag. cli2mcp will still start with a single args positional. The AI can pass arguments freely; you lose typed flag inference.

The schema came out empty / wrong. Run cli2mcp manually and inspect the tools/list response (use npx @modelcontextprotocol/inspector). The most common cause is non-standard help formatting (no --long-form flags, columns misaligned). Open an issue with the --help output attached.

The subprocess hangs. The default 60s timeout will kill it. Raise via --timeout. If your CLI is interactive (waits for a TTY), cli2mcp cannot help — pipe input via stdin instead.

Flag not being passed. Set --stderr include (the default) and inspect the content[].text. If the flag isn't appearing in argv, the help parser failed to extract it — file an issue.

---

Contributing

Bug reports and patches welcome. Fixtures for new CLIs (test/fixtures/help/ .txt + a shape test) are the highest-leverage contributions.

pnpm install

pnpm test # vitest pnpm typecheck # tsc --noEmit pnpm lint # biome check

---

Star history

If cli2mcp saved you an afternoon of writing MCP boilerplate, a star helps other people find it.

---

Author

Built by Ronie Neubauer — Principal Engineer, 22+ years shipping production systems.

• GitHub: @RonieNeubauer
• Blog: ronieneubauer.com
• Issues & ideas: github.com/RonieNeubauer/cli2mcp/discussions

---

License

MIT © 2026 Ronie Neubauer.