Search Claude Code mods, MCP servers, hooks, skills, and install guides on claudecodemods.net.
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.
Get full details, security score, GitHub repository, and install command for a specific Claude Code mod by slug.
The mod slug from search_claude_mods or list_trending_mods.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http mods-registry https://claudecodemods.net/api/mcp
Get full details, security score, GitHub repository, and install command for a specific Claude Code mod by slug.
| Argument | Type | Description |
|---|---|---|
| slug* | string | The mod slug from search_claude_mods or list_trending_mods. |
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"description": "The mod slug from search_claude_mods or list_trending_mods."
}
}
}Get top trending, most installed, or highest-starred Claude Code mods plus overall directory stats.
| Argument | Type | Description |
|---|---|---|
| sort | string | Leaderboard ranking metric (default: trending). |
| limit | number | Number of mods to return (1-20, default 10). |
{
"type": "object",
"properties": {
"sort": {
"enum": [
"trending",
"installed",
"stars",
"security"
],
"type": "string",
"description": "Leaderboard ranking metric (default: trending)."
},
"limit": {
"type": "number",
"description": "Number of mods to return (1-20, default 10)."
}
}
}Search curated Claude Code mods, plugins, hooks, skills, statuslines, and MCP integrations on claudecodemods.net.
| Argument | Type | Description |
|---|---|---|
| sort | string | Sort order (default: trending). |
| limit | number | Maximum results to return (1-20, default 10). |
| query | string | Search keyword (e.g., "mcp", "hooks", "git", "statusline", "memory"). |
| category | string | Optional category filter (or "all"). |
{
"type": "object",
"properties": {
"sort": {
"enum": [
"trending",
"stars",
"newest",
"security"
],
"type": "string",
"description": "Sort order (default: trending)."
},
"limit": {
"type": "number",
"description": "Maximum results to return (1-20, default 10)."
},
"query": {
"type": "string",
"description": "Search keyword (e.g., \"mcp\", \"hooks\", \"git\", \"statusline\", \"memory\")."
},
"category": {
"type": "string",
"description": "Optional category filter (or \"all\")."
}
}
}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 21, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.