← Back to Skills Marketplace
adiny

MoodTrip Hotel Search

by adiny · GitHub ↗ · v1.0.19 · MIT-0
cross-platform ⚠ suspicious
259
Downloads
0
Stars
0
Active Installs
20
Versions
Install in OpenClaw
/install moodtrip-hotel-search
Description
Search, compare, evaluate, and hand off hotel bookings using the MoodTrip.ai MCP server (api.moodtrip.ai). Use this skill whenever the user mentions hotels,...
Usage Guidance
This skill appears to do what it claims (hotel search via MoodTrip) but contains two notable risks: 1) it asks the platform to auto-edit persistent config so the MCP server is added (the agent would need permission to write/patch platform settings and restart), and 2) the MCP bridge is configured as 'npx mcp-remote@latest ...', which fetches and runs unpinned code from npm each time the bridge is installed/started (supply-chain risk). Before installing: (a) confirm you trust the MoodTrip project and/or its GitHub repo and the skill author (source is listed as unknown in the registry), (b) prefer a pinned package version or an integrity-checked release rather than '@latest', (c) if possible perform the config changes manually (review and run the npx command yourself) instead of allowing an agent to auto-edit platform settings, and (d) review the mcp-remote package source and the referenced GitHub repo (https://github.com/adiny/moodtrip-hotel-search) to ensure no unexpected behavior. If you cannot review or restrict the agent's ability to edit platform config, treat this skill as higher risk.
Capability Analysis
Type: OpenClaw Skill Name: moodtrip-hotel-search Version: 1.0.19 The skill bundle contains instructions in SKILL.md that direct the AI agent to automatically modify its own configuration and execute external code via 'npx -y mcp-remote@latest'. While these actions are intended to facilitate the connection to the MoodTrip MCP server (api.moodtrip.ai), the request for self-modification of platform settings and the use of npx to fetch remote utilities represent high-risk behaviors that could be exploited, despite being contextually aligned with the stated purpose.
Capability Assessment
Purpose & Capability
Name/description and runtime instructions align: the skill only describes searching/comparing/handing off hotels via an MCP server and provides MCP connection instructions and tool names consistent with that purpose.
Instruction Scope
SKILL.md instructs the agent to read platform configuration paths and — if running on OpenClaw with config-edit capability — to automatically patch platform config to add an MCP server entry and restart the session. Reading and editing platform config is within the stated goal of connecting the MCP server, but granting the agent automatic config-edit and restart rights is high privilege and broad in scope; the instructions also insist on running a stdio bridge rather than using a direct HTTP URL, which requires the platform to execute additional code.
Install Mechanism
The included mcp.json config runs 'npx -y mcp-remote@latest ...'. That command will fetch and execute the 'mcp-remote' package from npm at runtime using the 'latest' tag (non‑pinned), a dynamic supply‑chain risk. There is no pinned version or integrity check provided. Although no archive download URL or obscure host is present (npm is a known registry), using 'latest' to run code on the host elevates risk beyond an instruction-only skill.
Credentials
The skill declares no required environment variables, no credentials, and the SKILL.md states the MCP server is public read-only. There are no unusual credential requests in the manifest or instructions.
Persistence & Privilege
The skill recommends adding a persistent MCP server entry to the platform config (mcpServers.moodtrip), which will create a persistent execution entry that runs 'npx mcp-remote' when the platform loads tools. While persistence is needed to expose tools, this makes the platform repeatedly execute remotely fetched code on each session start and requires the agent/platform to allow writing/patching platform config — a higher privilege than simple request-response behavior.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install moodtrip-hotel-search
  3. After installation, invoke the skill by name or use /moodtrip-hotel-search
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.19
**Version 1.0.19 – More robust tool detection and OpenAI/Codex compatibility** - Expanded pre-flight tool checks to include `search_hotels`, `get_hotel_details`, and `build_booking_link` for broader runtime compatibility. - Added explicit guidance to prefer OpenAI/Codex-compliant wrapper tools (`search_hotels` and `get_hotel_details`) on strict schema platforms. - Updated Decision Rules to prioritize wrapper tools on OpenClaw and Codex, clarifying which variants to use. - Improved and clarified tool selection for common hotel search scenarios. - Documentation and setup sections refined for clarity and better cross-platform guidance.
v1.0.18
- No functional or content changes were made in this release. - Version 1.0.18 matches the previous version; no file or SKILL.md updates detected.
v1.0.17
- Updated MCP server configuration: replaced legacy .mcp.json and _meta.json files with a new mcp.json file. - Modernized auto-configuration and setup for improved compatibility with current platforms. - No changes to user-facing features or tool usage.
v1.0.16
- OpenClaw connection instructions updated: now uses a stdio bridge via mcp-remote for compatibility (HTTP endpoint alone won't work). - Pre-flight connection steps clarified to prefer stdio bridge config for OpenClaw (`command: npx ... mcp-remote ...`). - Explicit note: do NOT use `mcp.servers.moodtrip.url` with HTTP in OpenClaw; use the stdio bridge format. - Quick setup table and instructions revised to reflect the new OpenClaw connection pattern. - Routine documentation cleanup and instructions for more reliable MoodTrip tool loading.
v1.0.15
**Added auto-configuration files and improved setup guidance:** - Added _meta.json and mcp.json files to provide automatic MCP server configuration for supported platforms. - Updated instructions in SKILL.md to note that these files enable auto-connection when the platform supports reading them from the skill folder. - Clarified pre-flight checks for tool availability, now listing alternative tool names (`search_hotels`, `get_hotel_details`) for broader compatibility. - No changes to core functionality or hotel search logic.
v1.0.14
**MoodTrip Hotel Search v1.0.14 Changelog** - Improved OpenClaw integration: Now prefers automatic MCP server configuration via `mcp.servers`, with auto-connect and safe config patching where possible. - Updated pre-flight connection steps to clarify tool/server checks, favoring actual config edits over manual user instructions in OpenClaw when allowed. - Enhanced decision logic for auto-connecting and re-verifying tool exposure after session restart or configuration change. - Guidance text clarified for platform-specific setup and fallback options. - No change to core hotel search logic or tool list.
v1.0.13
Version 1.0.13 - Improved pre-flight connection checks with detailed multi-step instructions for verifying tool and server availability before informing the user. - Added guidance for inspecting multiple platform-specific MCP server config locations. - Clarified required troubleshooting steps if tools are not immediately found, including server/session reloads. - Enhanced instructional clarity for both agents and users about what to do when MoodTrip tools are missing or not loaded. - No functional changes to hotel search or feature set.
v1.0.12
- Added explicit OpenClaw installation instructions (`clawhub install adiny/moodtrip-hotel-search`) as an alternative to mcporter setup. - Updated pre-flight check to mention OpenClaw and give platform-based guidance for skill/tool connection. - Added "Quick Setup by Platform" section summarizing connection steps for OpenClaw, Claude Desktop, ChatGPT, and generic MCP clients. - Clarified connection instructions when neither mcporter nor OpenClaw methods are available. - No logic or tool changes; documentation and onboarding guidance improved for easier integration.
v1.0.11
- Updated tool names and adjusted tool availability: reduced core tools from 12 to 11, with some tool names changed (e.g., `search_hotels_by_description`, `ask_about_hotel`, `search_rooms_by_description`). - Clarified that the server is a public read-only API, no credentials required, and added privacy details. - Simplified pre-flight connection instructions and unified connection help for all platforms. - Added a privacy & data handling section outlining data use and user privacy protections. - Improved conversation and context management guidance for smoother Dialog agent operation. - Updated setup instructions to reference a canonical GitHub URL for further details.
v1.0.10
No user-facing changes in this version. - No code or documentation updates detected. - Skill functionality and documentation remain unchanged.
v1.0.9
Version 1.0.9 - Updated OpenClaw (mcporter) connection steps for clarity and accuracy, including new tool listing and call examples. - Clarified verification process for tool availability before use. - Improved examples and instructions for direct tool invocation on OpenClaw. - No changes to underlying tool availability or core server functionality.
v1.0.8
**Pre-flight check and connection instructions streamlined for clarity.** - Refined the pre-flight check: clear guidance on how to verify MoodTrip tool availability before running searches. - Added explicit platform-specific instructions for connecting the MCP server if it is missing. - Stronger warnings to prevent hallucinated results or workaround attempts if the connection is not present. - Removed repetitive setup instructions and consolidated integration steps for each platform. - No functional or API changes; documentation improvements only.
v1.0.7
MoodTrip Hotel Search 1.0.7 - Added compatibility metadata for MCP server requirements and integration settings. - Updated instructions and connection setup for OpenClaw and ClawHub platforms. - Introduced a mandatory pre-flight check: agents must verify that MoodTrip MCP tools are available before any search. - Specified stricter handling for cases when the MCP server is not connected—agents should not fabricate results and must guide users to connect properly. - No functional changes to hotel search workflows or tool usage.
v1.0.6
No user-facing or functional changes in this version. No changelog entries required.
v1.0.5
**v1.0.5 changelog** - Clarified that this skill provides usage instructions only, and does not connect to MoodTrip servers by itself. - Added explicit setup steps for connecting MoodTrip as an MCP integration for each supported platform. - Updated skill description to emphasize the need for MCP connection in Settings before use. - Improved instructions and prerequisite messaging for Claude, ChatGPT, and other agents. - No changes to hotel search logic or available tools.
v1.0.4
Version 1.0.4 - Added detailed connection and integration instructions for Claude Desktop, ChatGPT, and direct HTTP use. - Clarified the MCP server URL, protocol, and authentication requirements. - No functional or workflow changes to hotel search, comparison, or booking features. - All 12 core hotel search tools and optional Agent Builder tool sections unchanged. - No file changes detected; documentation update only.
v1.0.3
- No code or documentation changes detected in this version. - Functionality, features, and behavior remain the same as the previous release.
v1.0.2
Version 1.0.2 - Added .gitignore, LICENSE, and README.md files to the project. - README.md now provides detailed instructions and documentation for the skill. - No changes to core skill logic or workflows.
v1.0.1
No changes detected in this version. The SKILL.md remains unchanged.
v1.0.0
MoodTrip Hotel Search Skill v1.0.0 - Initial release of the MoodTrip Hotel Search skill. - Enables searching, comparing, evaluating, and handing off hotel bookings via the MoodTrip.ai MCP server. - Supports real-time inventory, pricing, semantic search, reviews, and booking link generation. - Provides 12 core tools covering full hotel discovery and booking workflows. - Triggers whenever users mention hotels, accommodation needs, booking, or related queries.
Metadata
Slug moodtrip-hotel-search
Version 1.0.19
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 20
Frequently Asked Questions

What is MoodTrip Hotel Search?

Search, compare, evaluate, and hand off hotel bookings using the MoodTrip.ai MCP server (api.moodtrip.ai). Use this skill whenever the user mentions hotels,... It is an AI Agent Skill for Claude Code / OpenClaw, with 259 downloads so far.

How do I install MoodTrip Hotel Search?

Run "/install moodtrip-hotel-search" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is MoodTrip Hotel Search free?

Yes, MoodTrip Hotel Search is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does MoodTrip Hotel Search support?

MoodTrip Hotel Search is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created MoodTrip Hotel Search?

It is built and maintained by adiny (@adiny); the current version is v1.0.19.

💬 Comments