Speakeasy CLI

The CLI validates OpenAPI descriptions and generates client libraries, MCP servers and other interfaces for your API.

  • 458 ★ on the repository
  • Last commit
CLI

Extended access

Why this level

  • The CLI generates and updates files, and configured jobs can publish packages; review changes and restrict CI permissions.
All reasons and checks

speakeasy-api/speakeasy

Install

Manual install

brew install speakeasy-api/tap/speakeasy

First option in the official guide linked by the README: Homebrew on macOS. Use the platform-specific alternative for other systems.

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • The CLI generates and updates files, and configured jobs can publish packages; review changes and restrict CI permissions.

This is third-party code. Review the repository files before installing.

What it does

Speakeasy CLI helps teams generate API access tools from an OpenAPI description. Users validate the specification, choose an output and receive source code for further development. Outputs include client SDKs, MCP servers and Terraform providers. The toolchain also supports specification changes and comparisons, code samples and contract tests. Separate agent skills guide initial setup and regeneration.

Who it is for. Public API teams maintaining client libraries that must evolve alongside the specification.

Good fit when

  • An OpenAPI change needs a refreshed client SDK.
  • Your API needs a generated MCP interface.
  • The team reviews specification structure and changes before generation.
  • Documentation needs consistent API usage examples.

Not a fit when

  • There is no usable API description and no time to prepare one.
  • You expect a schema to generate the service’s business logic.
  • Generated code cannot be reviewed and tested before release.

Example request

Validate our OpenAPI spec and prepare a client SDK on a separate branch, showing changes before publication.

Limitations

Generation depends on OpenAPI quality; inspect schemas, types and operation descriptions first. Initial setup requires a Speakeasy account and workspace selection, so prepare access beforehand. The CLI creates and updates project files; generate on a separate branch and review changes before release. Contract tests check the described API contract, but actual service behavior and client integration still need testing in your application.

How to disable. Disable generation and publishing jobs in CI, then uninstall the CLI through its package manager. Generated code and project settings remain.

FAQ

How do I start the first project?

Run `speakeasy quickstart` and follow the wizard.

Where are command options documented?

Every command and subcommand supports `--help`.

Can I add agent instructions?

Yes. `npx skills add speakeasy-api/agent-skills` installs the separate skill collection.

How can the agent validate a specification?

After skill installation, use `/speakeasy:validate-openapi-spec`.

Which skill updates an SDK?

Use `/speakeasy:regenerate-sdk` from the agent skill collection and inspect generated changes.

Discussion

No questions or reviews yet.

CLI tools

A CLI that builds a ready-made TypeScript MCP server from an OpenAPI 3 spec, with tools, validation and auth generated for you

CLIExtended access644Repository stars
Official

The MCP server turns OpenAPI operations into agent tools and sends real requests to the configured REST API.

MCP serverExtended access302Repository stars

OpenMCP turns any OpenAPI specification into an MCP server and lets you choose which tools the agent sees

MCP serverExtended access303Repository stars

A CLI, MCP server and skill for spec-driven development: short markdown specs, a task board and search that an agent can read.

CLIExtended access300Repository stars

CLI that turns an OpenAPI spec into an Agent Skill of markdown files an agent reads piece by piece, saving context.

CLIMinimal access342Repository stars

LAP: compact API specs for agents

LAP (Lean API Platform)

The lapsh CLI compacts OpenAPI and GraphQL specs for agents and installs a skill into Claude Code, Cursor and Codex

CLIExtended access347Repository stars

README in short

The toolchain uses OpenAPI Overlays for specification changes and Arazzo for contract scenarios. Client generation supports several languages.

README badge

Report a problem

Foxx AISpeakeasy CLI
Foxx AI

I am Foxx AI and I have already vetted this tool. Ask about install, setup or anything else, and I will keep it simple.