Search and install ready-made setups (rules, skills, MCP configs) for AI coding agents.
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.
Exact install steps for one loadout and agent: each file's target path in the project, its raw URL, ready-to-run curl commands, manual steps (e.g. MCP servers for agents without a project config file) and the zip URL.
Loadout id, e.g. nextjs-supabase-saas
Coding agent
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http loadouts https://setupbay.com/mcp
Exact install steps for one loadout and agent: each file's target path in the project, its raw URL, ready-to-run curl commands, manual steps (e.g. MCP servers for agents without a project config file) and the zip URL.
| Argument | Type | Description |
|---|---|---|
| id* | string | Loadout id, e.g. nextjs-supabase-saas |
| agent* | string | Coding agent |
{
"type": "object",
"required": [
"id",
"agent"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
"maxLength": 80,
"minLength": 1,
"description": "Loadout id, e.g. nextjs-supabase-saas"
},
"agent": {
"enum": [
"claude-code",
"codex",
"cursor",
"gemini-cli",
"antigravity-cli",
"copilot"
],
"type": "string",
"description": "Coding agent"
}
},
"additionalProperties": false
}Metadata for one loadout: description, agent compatibility, verification and agent-test status, requirements, and the file list with roles, sizes, raw URLs and per-agent install paths.
| Argument | Type | Description |
|---|---|---|
| id* | string | Loadout id, e.g. nextjs-supabase-saas |
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
"maxLength": 80,
"minLength": 1,
"description": "Loadout id, e.g. nextjs-supabase-saas"
}
},
"additionalProperties": false
}Raw contents of one file in a loadout (path as listed by get_loadout, e.g. AGENTS.md or skills/db-migration/SKILL.md). Max 100 KB.
| Argument | Type | Description |
|---|---|---|
| id* | string | Loadout id, e.g. nextjs-supabase-saas |
| path* | string | File path within the loadout |
{
"type": "object",
"required": [
"id",
"path"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
"maxLength": 80,
"minLength": 1,
"description": "Loadout id, e.g. nextjs-supabase-saas"
},
"path": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "File path within the loadout"
}
},
"additionalProperties": false
}Supported coding agents with the instructions file each reads, its skills directory and where project MCP config goes.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}All tags (stacks) and categories in the catalogue, with loadout counts. Use them as search_loadouts filters.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Search SetupBay for rule/skill/MCP bundles. Ranked by relevance to `query`; filter by agent, tags (stacks such as nextjs, godot, python) or category. With no query, lists loadouts (featured and verified first).
| Argument | Type | Description |
|---|---|---|
| has | string | Only loadouts containing skills, MCP configs or rules |
| tags | array | All of these stacks/categories must match, e.g. ["typescript"] |
| agent | string | Only loadouts that support this agent |
| limit | integer | Max results (default 10) |
| query | string | Free text, e.g. 'nextjs supabase auth' or 'discord bot' |
| category | string | Category id (see list_tags) |
| verified_only | boolean | Only loadouts that passed the Level 1 automated install check |
{
"type": "object",
"properties": {
"has": {
"enum": [
"skills",
"mcp",
"rules"
],
"type": "string",
"description": "Only loadouts containing skills, MCP configs or rules"
},
"tags": {
"type": "array",
"items": {
"type": "string",
"maxLength": 40
},
"maxItems": 8,
"description": "All of these stacks/categories must match, e.g. [\"typescript\"]"
},
"agent": {
"enum": [
"claude-code",
"codex",
"cursor",
"gemini-cli",
"antigravity-cli",
"copilot"
],
"type": "string",
"description": "Only loadouts that support this agent"
},
"limit": {
"type": "integer",
"maximum": 20,
"minimum": 1,
"description": "Max results (default 10)"
},
"query": {
"type": "string",
"maxLength": 200,
"description": "Free text, e.g. 'nextjs supabase auth' or 'discord bot'"
},
"category": {
"type": "string",
"maxLength": 40,
"description": "Category id (see list_tags)"
},
"verified_only": {
"type": "boolean",
"description": "Only loadouts that passed the Level 1 automated install check"
}
},
"additionalProperties": false
}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 16, 2026.