Search the Serverdex MCP server directory by task or category; get install configs and GitHub facts.
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 Serverdex knows about one server by slug: description, category, packages (npm/PyPI/Docker), remote endpoints, GitHub facts (stars, license, last push), a README excerpt and ready-to-paste client configs for Claude Desktop / Cursor.
The server slug from search_servers or a serverdex.io/server/<slug> URL.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http serverdex https://serverdex.io/mcp
Everything Serverdex knows about one server by slug: description, category, packages (npm/PyPI/Docker), remote endpoints, GitHub facts (stars, license, last push), a README excerpt and ready-to-paste client configs for Claude Desktop / Cursor.
| Argument | Type | Description |
|---|---|---|
| slug* | string | The server slug from search_servers or a serverdex.io/server/<slug> URL. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "The server slug from search_servers or a serverdex.io/server/<slug> URL."
}
}
}The directory's categories with live server counts and their slugs (for search_servers' category filter).
No arguments.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}Full-text search over the Serverdex directory of MCP servers (names, titles, descriptions). Returns compact rows: slug, name, author, description, category, GitHub stars, links. Use get_server with a slug for install configs.
| Argument | Type | Description |
|---|---|---|
| page | integer | Page number for more results (default 1). |
| sort | string | new = newest first (default), name = A–Z, stars = most GitHub stars first. |
| limit | integer | Rows to return, 1–50 (default 10). |
| query | string | Words to search for, e.g. 'postgres', 'calendar', 'web scraping'. Omit to browse. |
| category | string | Restrict to one category slug (see list_categories). |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"page": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": 1,
"description": "Page number for more results (default 1)."
},
"sort": {
"enum": [
"new",
"name",
"stars"
],
"type": "string",
"description": "new = newest first (default), name = A–Z, stars = most GitHub stars first."
},
"limit": {
"type": "integer",
"maximum": 50,
"minimum": 1,
"description": "Rows to return, 1–50 (default 10)."
},
"query": {
"type": "string",
"maxLength": 200,
"description": "Words to search for, e.g. 'postgres', 'calendar', 'web scraping'. Omit to browse."
},
"category": {
"enum": [
"crypto-web3",
"finance",
"ecommerce",
"marketing-seo",
"business-crm",
"legal-government",
"health-science",
"maps-travel",
"lifestyle",
"media",
"games-sports",
"education",
"iot-devices",
"security",
"communication",
"productivity",
"documents",
"files-storage",
"content-publishing",
"databases",
"data-analytics",
"search-web",
"cloud-devops",
"testing-qa",
"apis-integrations",
"ai-ml",
"developer-tools",
"other"
],
"type": "string",
"description": "Restrict to one category slug (see list_categories)."
}
}
}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 13, 2026.