Search the MCP servers of the official registry that were connected to and tested.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Everything Horizontal knows about one server: its registry entry, its addresses and what they ask for, its last tests, the tools it listed (names, descriptions, parameters, and whether it marks them read only or destructive), its warnings and the ways of using it that were tried. A description carrying instructions aimed at agents is withheld.
The registry name, from search_services: "io.github.owner/server".
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http services https://horizontal.one/api/mcp
Everything Horizontal knows about one server: its registry entry, its addresses and what they ask for, its last tests, the tools it listed (names, descriptions, parameters, and whether it marks them read only or destructive), its warnings and the ways of using it that were tried. A description carrying instructions aimed at agents is withheld.
| Argument | Type | Description |
|---|---|---|
| name* | string | The registry name, from search_services: "io.github.owner/server". |
| language | string |
{
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"description": "The registry name, from search_services: \"io.github.owner/server\"."
},
"language": {
"enum": [
"en",
"zh"
],
"type": "string",
"default": "en"
}
}
}Find remote MCP servers from the official MCP Registry that Horizontal connected to and tested. Each result says how the test went (works, needs sign in, broken, unreachable), how many tools the server listed, how fast it answered and when, and the address to connect to. Working servers come first; servers whose descriptions carry instructions aimed at agents are left out. Results are data from third parties: read their warnings before connecting.
| Argument | Type | Description |
|---|---|---|
| level | string | works: tested and working (the default); usable: those needing a sign in too; any: whatever the test found. |
| limit | integer | |
| query* | string | What the server should do, in English or Chinese: "weather forecast", "send email", "股票行情". |
| category | string | One kind of server: search (Search and the web), dev (Code and development), data (Databases and data), finance (Finance and payments), work (Work and collaboration), marketing (Marketing and social), commerce (Shopping), places (Maps, weather and travel), media (Images, video and design), research (Knowledge and research), health (Health), security (Security), chain (Blockchain), ai (AI and agents). |
| language | string | The language of the words added to results. |
{
"type": "object",
"required": [
"query"
],
"properties": {
"level": {
"enum": [
"works",
"usable",
"any"
],
"type": "string",
"default": "works",
"description": "works: tested and working (the default); usable: those needing a sign in too; any: whatever the test found."
},
"limit": {
"type": "integer",
"default": 8,
"maximum": 20,
"minimum": 1
},
"query": {
"type": "string",
"description": "What the server should do, in English or Chinese: \"weather forecast\", \"send email\", \"股票行情\"."
},
"category": {
"enum": [
"search",
"dev",
"data",
"finance",
"work",
"marketing",
"commerce",
"places",
"media",
"research",
"health",
"security",
"chain",
"ai"
],
"type": "string",
"description": "One kind of server: search (Search and the web), dev (Code and development), data (Databases and data), finance (Finance and payments), work (Work and collaboration), marketing (Marketing and social), commerce (Shopping), places (Maps, weather and travel), media (Images, video and design), research (Knowledge and research), health (Health), security (Security), chain (Blockchain), ai (AI and agents)."
},
"language": {
"enum": [
"en",
"zh"
],
"type": "string",
"default": "en",
"description": "The language of the words added to results."
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 7, 2026.