Search and fetch vibe-coding Agent Skills (SKILL.md files) and prompts from TheSkillVault library.
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.
Load the full SKILL.md instructions for one skill by exact name (from search_skills).
Exact skill name, e.g. deploy-nextjs-to-vercel
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.
claude mcp add --transport http skills https://theskillvault.ai/mcp
Load the full SKILL.md instructions for one skill by exact name (from search_skills).
| Argument | Type | Description |
|---|---|---|
| name* | string | Exact skill name, e.g. deploy-nextjs-to-vercel |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"description": "Exact skill name, e.g. deploy-nextjs-to-vercel"
}
}
}Load one supporting file (e.g. references/env-vars.md) from a skill folder. Use the file list returned by get_skill.
| Argument | Type | Description |
|---|---|---|
| name* | string | Exact skill name |
| path* | string | Path relative to the skill folder, e.g. references/env-vars.md |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"name",
"path"
],
"properties": {
"name": {
"type": "string",
"maxLength": 64,
"description": "Exact skill name"
},
"path": {
"type": "string",
"maxLength": 300,
"description": "Path relative to the skill folder, e.g. references/env-vars.md"
}
}
}List skill categories with counts.
No arguments.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}List all skills (name, category, description), optionally filtered by category.
| Argument | Type | Description |
|---|---|---|
| category | string |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"category": {
"enum": [
"frontend",
"backend",
"deployment",
"debugging",
"prompts",
"design"
],
"type": "string"
}
}
}Call search_skills before starting any coding, deployment, debugging, design or prompt-writing task. Searches TheSkillVault, a library of vibe-coding skills and prompts. Returns names + one-line descriptions only; call get_skill to load the full instructions of the best match before doing the task.
| Argument | Type | Description |
|---|---|---|
| tag | string | Optional tag filter, e.g. nextjs |
| limit | integer | Max results (default 5) |
| query* | string | What the user is trying to do, in plain words |
| category | string | Optional category filter |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"query"
],
"properties": {
"tag": {
"type": "string",
"description": "Optional tag filter, e.g. nextjs"
},
"limit": {
"type": "integer",
"maximum": 20,
"minimum": 1,
"description": "Max results (default 5)"
},
"query": {
"type": "string",
"description": "What the user is trying to do, in plain words"
},
"category": {
"enum": [
"frontend",
"backend",
"deployment",
"debugging",
"prompts",
"design"
],
"type": "string",
"description": "Optional category filter"
}
}
}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 Oct 31, 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.