Paybond CLI

Paybond CLI is a terminal tool for safe agent spend setup, with sandbox login, guardrails, MCP config, diagnostics, and JSON automation.

AI 에이전트 개발 AI 개발 도구 프로그래밍 에이전트

웹사이트 방문

Safe agent spend from the terminal

Paybond CLI is a terminal-first tool for setting up safe agent spend flows from the command line. It covers sandbox login, guardrail scaffolding, MCP configuration, diagnostics, and machine-readable automation in one shared command tree.

The TypeScript and Python packages are designed to stay in parity, so agents and operators can use the same commands, JSON envelopes, and exit-code contract regardless of runtime. The docs position the CLI as the default entry point for adding paid-tool guardrails before a workflow calls a paid API, vendor action, or settlement step.

The setup flow starts in sandbox, uses tenant-scoped credentials, and keeps the first integration focused on guardrails rather than live settlement rails. From there, the CLI can generate host config, verify the path with doctor checks, and support scripted usage through JSON output.

Core capabilities

Sandbox login

Authenticate once with a tenant-scoped sandbox credential before running guardrail or MCP commands. The login flow writes a sandbox `PAYBOND_API_KEY` to `.env.local` and masks the key identity in output.

One-command guardrails

Scaffold a first paid-tool integration with `paybond-init` using the `paid-tool-guard` preset. The generated helper wraps your application-owned tool handler instead of implementing the tool for you.

MCP setup and verification

Generate MCP host configuration for supported clients and keep `PAYBOND_ENV_FILE` as the connection point. The docs include install commands and example host configs for Codex and JSON-based clients.

Diagnostics checks

Run `doctor` and related diagnostics to catch configuration drift before agents reach production spend paths. The agent setup guide recommends validating credentials, principal lookup, MCP startup, and tool listing.

JSON automation

Use machine-readable JSON envelopes for scripts and CI, with stable outputs and synchronized exit codes across TypeScript and Python packages. This makes the CLI suitable for automation as well as interactive terminal use.

Common workflows

Add paid-tool guardrails to a repo
A coding agent needs to add spend controls before calling a paid tool. The CLI guides the repository through sandbox login, guardrail scaffolding, and validation before any live workflow is attempted.
Standardize agent setup across runtimes
An operator wants one setup path that works across TypeScript and Python. The shared command tree and JSON contract make it possible to standardize setup and automation across both runtimes.
Prepare MCP access for a coding agent
A team needs to wire an MCP client and verify the configuration before the agent runs. The CLI can generate host config, point to `PAYBOND_ENV_FILE`, and help validate the end-to-end path.
Automate setup and checks in CI
A build or automation job needs machine-readable output. The CLI's JSON envelopes and consistent exit codes make it usable in scripts and CI pipelines without scraping human-oriented text.

Pros and Cons

Pros

Combines login, guardrail scaffolding, MCP install, diagnostics, and automation in one CLI.
Keeps TypeScript and Python aligned on the same command tree and JSON contract.
Supports a sandbox-first setup that avoids live money movement during the initial integration.
Provides machine-readable JSON output for scripts, CI, and agent automation.
Includes documented validation steps such as `doctor --agent` and MCP install verification.

Cons

The first integration path is sandbox-only; live settlement rails are not part of the initial scaffold.
The source does not show a full command reference on the product page itself, so some details live in the docs.
MCP server launch still depends on host configuration or `npx`, rather than being fully embedded in the login step.

FAQ

Do I need both TypeScript and Python?

No. The docs say you can choose either TypeScript or Python, and both expose the same `paybond` command tree and JSON contract.

Where can I find the full command reference?

The CLI contract doc is the source for flags, subcommands, JSON envelopes, and parity guarantees between the two runtimes.

How does the CLI relate to the MCP server?

The CLI installs and verifies MCP host configuration. The MCP server itself is launched separately through `npx` or a host's stdio configuration after login.

What is the typical setup flow for a coding agent?

Use `paybond login` or the login package entrypoint to write a sandbox `PAYBOND_API_KEY` to `.env.local`, then run `paybond mcp install` to generate host configuration and `paybond doctor --agent` to validate the setup.

Is Paybond CLI tied to a paid plan?

The docs position Free Developer as sandbox-only, while Starter is the first paid production plan. Team, Business, and Enterprise add higher caps, overage options, and broader controls.

Quick Facts

Category: Developer Tool
Primary use: Safe agent spend and paid-tool guardrails from the terminal
Runtimes: TypeScript and Python
Install options: npx for Node or a Python package install
Pricing: Free Developer is sandbox-only; Starter is the first paid production plan
Source domain: paybond.ai