mcpField
E
EcoAloha

EcoAloha

Remote
ecoaloha.comMaps & Travel0Updated 4w ago

About EcoAloha

EcoAloha is a public, keyless API and MCP server for finding and comparing outdoor experiences. It is intended for trip-planning agents and API integrators; bookings and payments take place on Viator.

Key features

  1. 01Search outdoor experiences
  2. 02Compare available experiences
  3. 03Keyless public API
  4. 04Sandbox fixtures for read-only testing

Use cases

  1. 01Plan trips around outdoor activities
  2. 02Compare options before booking
  3. 03Test integrations with sandbox data

MCP support

Connect over Streamable HTTP at https://ecoaloha.com/mcp without an API key. It exposes EcoAloha product tools to MCP clients.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://ecoaloha.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

12
ParameterTypeRequiredDescription
idstringYesPage slug or destination id. Index pages use index.
typeenumYescollection | destination | activity | collections | destinations | activities

Details

From the project README

EcoAloha agent integrations

Official integration resources for EcoAloha. Read the developer portal and OpenAPI specification.

Connect with MCP

Use Streamable HTTP at https://ecoaloha.com/mcp. No API key is required. Find the official EcoAloha listing on Smithery. The separate documentation server is https://ecoaloha.com/mcp/docs. Both endpoints support stateless MCP 2026-07-28 and legacy clients. Send the protocol version and client capabilities in params._meta, with matching MCP-Protocol-Version and Mcp-Method headers; named tool calls also require Mcp-Name. Neither endpoint supports webhook Events: public keyless access establishes no authenticated subscription owner. A callback signing secret does not grant account access. The server card lists the product tools. The official MCP Registry listing is published separately from the deployed server. server.json describes server release 1.2.0; plugin and SDK versions are independent.

Install skills

npx skills add ArneFfm/ecoaloha-agents

The root plugin.json and mcp.json also form an Agent Plugin.

SDKs and CLI

Download installable packages from release 0.1.0. The JavaScript SDK and CLI are published as @ecoaloha/sdk on npm.

npm install @ecoaloha/sdk
npx --package=@ecoaloha/sdk ecoaloha --sandbox destinations

The Python SDK is published as ecoaloha on PyPI. Python 3.10 or later is required.

python3 -m pip install ecoaloha

You can also install from this checkout:

npm install ./packages/sdk-js
python3 -m pip install ./packages/sdk-python
node packages/sdk-js/cli.js --sandbox destinations

The Go SDK uses the standard library:

go get github.com/ArneFfm/ecoaloha-agents/packages/[email protected]

See the Go guide.

See the JavaScript guide and Python guide.

Safety and scope

The API is public and keyless. Respect rate limits and Retry-After. Live data requires partner entitlement. Do not retry or bypass AGENT_ACCESS_NOT_APPROVED. Use fictional fixtures at https://ecoaloha.com/api/sandbox/v1 for read-only testing. Booking and payment happen on Viator. Prices are indicative. Disclose affiliate links.

Publishing

Manual workflows publish the MCP listing and SDK packages separately. Package versions are immutable after publication. Publisher accounts must be configured first. For PyPI, register a pending trusted publisher for project ecoaloha, owner ArneFfm, repository ecoaloha-agents, workflow publish-pypi.yml. For npm, publish the first release with an account that owns @ecoaloha, then configure workflow publish-npm.yml as a trusted publisher.

The manual publish-go.yml workflow tests and publishes an immutable Go module tag.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.