About metasearch MCP
metasearch MCP is a remote server for validating and preparing hotel and travel feeds for platform requirements. It detects formats, normalizes fields, checks readiness, and provides deterministic remediation guidance.
Key features
- 01Detect structured feed formats
- 02Normalize hotel field aliases
- 03Validate feeds for target platforms
- 04Compare readiness and requirements
- 05Suggest remediation steps
Use cases
- 01Validate a hotel feed for Google Hotel Center
- 02Compare feed requirements for Wego and trivago
- 03Normalize hotel data and find missing fields
MCP support
The remote MCP server exposes tools for hotel-feed format detection, normalization, validation, readiness and requirement comparisons, and remediation guidance.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://metasearch.com.tr/mcpclaude mcp add --transport http tr-com-metasearch-metasearch https://metasearch.com.tr/mcp{"mcpServers":{"tr-com-metasearch-metasearch":{"type":"http","url":"https://metasearch.com.tr/mcp"}}}Open in Cursor{"servers":{"tr-com-metasearch-metasearch":{"type":"http","url":"https://metasearch.com.tr/mcp"}}}Open in VS Code{"mcpServers":{"tr-com-metasearch-metasearch":{"type":"http","url":"https://metasearch.com.tr/mcp"}}}{"mcpServers":{"tr-com-metasearch-metasearch":{"serverUrl":"https://metasearch.com.tr/mcp"}}}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| Parameter | Type | Required | Description |
|---|---|---|---|
| content | string | Yes | Feed content. Paste the JSON, XML, CSV, TSV or NDJSON payload directly. Maximum size is 2 MB. |
| formatHint | enum | No | Optional expected format hint. Omit or use auto when the format should be detected from the payload.auto | json | xml | csv | tsv | ndjson |
Details
From the project READMEmetasearch MCP
Remote Model Context Protocol (MCP) server for hotel and travel feed validation, normalization, readiness checks, and platform requirement comparison.
Operated by metasearch.com.tr and published under the domain-owned MCP Registry identity:
tr.com.metasearch/metasearch-mcp
Remote endpoint:
https://metasearch.com.tr/mcp
The server is independent and is not an official certification service for Google, Wego, trivago, Meta, or Criteo.
What it does
The server gives AI agents deterministic tools for hotel-feed workflows:
- detect structured feed formats,
- normalize common hotel field aliases,
- validate hotel feeds,
- compare readiness across platforms,
- compare platform requirements,
- suggest remediation steps.
Validation targets
| Target | Mode |
|---|---|
| Google Hotel Center | Published-contract validation |
| Wego Hotels | Published-contract validation |
| trivago hotel data | Published-contract validation |
| Meta Catalog | Readiness / mapping pre-check |
| Criteo Catalog | Readiness / mapping pre-check |
| Generic hotel master data | Platform-independent quality check |
Published-contract validation and readiness checks are deliberately kept separate. Undocumented mandatory fields are not invented.
Connect
Claude Code
claude mcp add --transport http metasearch https://metasearch.com.tr/mcp
claude mcp list
Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"metasearch": {
"url": "https://metasearch.com.tr/mcp"
}
}
}
VS Code / GitHub Copilot
Add to .vscode/mcp.json:
{
"servers": {
"metasearch": {
"type": "http",
"url": "https://metasearch.com.tr/mcp"
}
}
}
Additional setup examples live under examples/.
Available tools
| Tool | Purpose |
|---|---|
detect_feed_format | Detect supported structured feed formats |
normalize_hotel_feed | Normalize common hotel field aliases |
validate_feed | Run target-aware validation |
validate_google_hotel_center_list | Validate Google Hotel Center hotel-list data |
validate_wego_hotel_feed | Validate Wego hotel-feed data |
validate_trivago_hotel_data | Validate trivago hotel data |
validate_meta_catalog | Run Meta catalog readiness checks |
validate_criteo_catalog | Run Criteo catalog readiness checks |
validate_hotel_master_data | Run generic hotel master-data quality checks |
compare_feed_readiness | Compare feed readiness across targets |
compare_platform_requirements | Compare target requirements |
suggest_feed_fixes | Produce deterministic remediation guidance |
See docs/tools.md for details.
Example prompts
Examples include:
- "Validate this hotel CSV for Google Hotel Center."
- "Compare this feed against Wego and trivago requirements."
- "Normalize this hotel dataset and show missing fields."
- "Explain how to fix the validation errors without inventing unsupported fields."
See examples/prompts.md.
Privacy and data handling
The validation workflow is designed not to persist submitted feed payloads. Operational telemetry records tool name and explicit target only; it does not intentionally record feed contents.
Do not send credentials or secrets as feed content. See docs/privacy-and-security.md and SECURITY.md.
Registry and discovery
The canonical registry descriptor is server.json.
Registry identity:
tr.com.metasearch/metasearch-mcp
The namespace is authenticated using ownership of metasearch.com.tr.
For third-party registry and directory submissions, use the canonical metadata in docs/discovery.md. This keeps names, descriptions, categories, endpoint details and privacy claims consistent across listings.
Companion CLI and Node.js SDK
For local development and CI pipelines, use @metasearch/feed-validator:
npx @metasearch/feed-validator validate hotels.csv --target google-hotel-center
Source: metasearchcomtr/feed-validator
Documentation
- MCP documentation
- Hotel Feed Validator
- Hotel feed requirements comparison
- Validate hotel feeds with MCP
- Client setup
- Troubleshooting
- Discovery metadata
- Changelog
Contributing
Issues and focused pull requests are welcome. See CONTRIBUTING.md.
License
MIT. See LICENSE.
Comments
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.