LaunchLibrary2 SDK

Launch Library 2 client, generated from the OpenAPI spec.

This is an unofficial SDK for the Launch Library 2 public API, generated by Voxgig with @voxgig/sdkgen. It is not affiliated with, endorsed by, or sponsored by the upstream API provider.

TypeScript, Python, PHP, Golang, Ruby, Lua SDKs, a CLI, an interactive REPL, and an MCP server for AI agents — all generated from one OpenAPI spec by @voxgig/sdkgen.

Entities, not endpoints

This SDK exposes the API as a small set of semantic entities — Agency, Astronaut, Docking, DockingEvent, Event, Expedition, FirstStage, Launch, LaunchVehicle, Launcher, Location, Pad, ReusableFirstStage, SpaceStation and Spacecraft — that you call directly, instead of assembling URL paths and query strings. Entities are Capitalised to mark them as the primary surface, each with the operations they support (list, load):

const client = new LaunchLibrary2SDK()
const items = await client.Agency().list()

Thinking in entities keeps the mental model small — for people and AI agents alike — rather than reasoning about raw HTTP routes and query parameters.

Packages

Quickstart

TypeScript

import { LaunchLibrary2SDK } from '@voxgig-sdk/launch-library2'

const client = new LaunchLibrary2SDK()

// List all agencys (returns Agency[])
const agencys = await client.Agency().list()
for (const agency of agencys) {
  console.log(agency)
}

See the TypeScript README for the full guide.

Surfaces

Use it from an AI agent (MCP)

The generated MCP server exposes every operation in this SDK as an MCP tool that Claude, Cursor or Cline can call directly. Build and register it:

cd go-mcp && go build -o launch-library2-mcp .

Then add it to your agent’s MCP config (Claude Desktop, Cursor, etc.):

{
  "mcpServers": {
    "launch-library2": {
      "command": "/abs/path/to/launch-library2-mcp"
    }
  }
}

Entities

The API exposes 15 entities:

The operations available across these entities are load, list — see each entity’s own list above for exactly which it supports.

Quickstart in other languages

Python

from launchlibrary2_sdk import LaunchLibrary2SDK

client = LaunchLibrary2SDK()

# List all agencys (returns a list, raises on error)
agencys = client.Agency().list()
for agency in agencys:
    print(agency)

# Load a specific agency (returns the record, raises on error)
agency = client.Agency().load({"id": "example_id"})
print(agency)

PHP

<?php
require_once 'launchlibrary2_sdk.php';

$client = new LaunchLibrary2SDK();

// List all agencys (returns an array; throws on error)
$agencys = $client->Agency()->list();
print_r($agencys);

// Load a specific agency (returns the bare record; throws on error)
$agency = $client->Agency()->load(["id" => "example_id"]);
print_r($agency);

Golang

import sdk "github.com/voxgig-sdk/launch-library2-sdk/go"

client := sdk.New()

// List all agencys
agencys, err := client.Agency(nil).List(nil, nil)
fmt.Println(agencys)

Ruby

require_relative "LaunchLibrary2_sdk"

client = LaunchLibrary2SDK.new

# List all agencys (returns an Array; raises on error)
agencys = client.Agency.list
puts agencys

# Load a specific agency (returns the bare record; raises on error)
agency = client.Agency.load({ "id" => "example_id" })
puts agency

Lua

local sdk = require("launch-library2_sdk")

local client = sdk.new()

-- List all agencys
local agencys, err = client:Agency():list()
print(agencys)

-- Load a specific agency
local agency, err = client:Agency():load({ id = "example_id" })
print(agency)

Unit testing in offline mode

Every SDK ships a test mode that swaps the HTTP transport for an in-memory mock, so unit tests run offline.

TypeScript

const client = LaunchLibrary2SDK.test()
const agency = await client.Agency().list()
// agency is a bare Agency populated with mock data
console.log(agency)

Python

client = LaunchLibrary2SDK.test()
agency = client.Agency().list()
print(agency)

PHP

// Seed fixture data so offline calls resolve without a live server.
$client = LaunchLibrary2SDK::test([
    "entity" => ["agency" => ["test01" => ["id" => "test01"]]],
]);
$agency = $client->Agency()->list();

Golang

client := sdk.Test()
result, err := client.Agency(nil).List(
    nil, nil,
)

Ruby

# Seed fixture data so offline calls resolve without a live server.
client = LaunchLibrary2SDK.test({
  "entity" => { "agency" => { "test01" => { "id" => "test01" } } },
})
agency = client.Agency.list()

Lua

local client = sdk.test()
local result, err = client:Agency():list()

Direct and prepare

For endpoints the entity model doesn’t cover, use the low-level methods:

• direct(fetchargs) — build and send an HTTP request in one step.
• prepare(fetchargs) — build the request without sending it.

Both accept a map with path, method, params, query, headers, and body. See the How-to guides below.

How-to guides

Make a direct API call

When the entity interface does not cover an endpoint, use direct:

TypeScript:

const result = await client.direct({
  path: '/api/resource/{id}',
  method: 'GET',
  params: { id: 'example' },
})
if (result instanceof Error) {
  throw result
}
console.log(result.data)

Python:

result = client.direct({
    "path": "/api/resource/{id}",
    "method": "GET",
    "params": {"id": "example"},
})

PHP:

$result = $client->direct([
    "path" => "/api/resource/{id}",
    "method" => "GET",
    "params" => ["id" => "example"],
]);

Go:

result, err := client.Direct(map[string]any{
    "path":   "/api/resource/{id}",
    "method": "GET",
    "params": map[string]any{"id": "example"},
})

Ruby:

result = client.direct({
  "path" => "/api/resource/{id}",
  "method" => "GET",
  "params" => { "id" => "example" },
})

Lua:

local result, err = client:direct({
  path = "/api/resource/{id}",
  method = "GET",
  params = { id = "example" },
})

Advanced

Everyday use only needs the sections above. This explains the internals behind every call — relevant when writing custom features.

Every SDK call runs the same five-stage pipeline:

1. Point — resolve the API endpoint from the operation definition.
2. Spec — build the HTTP specification (URL, method, headers, body).
3. Request — send the HTTP request.
4. Response — receive and parse the response.
5. Result — extract the result data for the caller.

A feature hook fires at each stage (e.g. PrePoint, PreSpec, PreRequest), so features can inspect or modify the pipeline without forking the SDK.

Features

Pass custom features via the extend option at construction time.

Per-language documentation

• TypeScript
• Python
• PHP
• Golang
• Ruby
• Lua

Upstream API

This SDK is generated from the upstream OpenAPI specification. It is an unofficial client and is not affiliated with the API provider.

• Upstream API: https://ll.thespacedevs.com/2.2.0

Security

Please report security issues to security@voxgig.com. See SECURITY.md. Do not open public issues for suspected vulnerabilities.

Generated from the Launch Library 2 OpenAPI spec by @voxgig/sdkgen.