Search 60,000+ AI agent skills directly from any MCP-compatible agent.
BytesAgain is a free MCP server for discovering AI agent skills and workflow use cases across ClawHub, LobeHub, Dify, GitHub-indexed skills, and the BytesAgain curated catalog.
This repository contains a real stdio MCP server wrapper. It exposes compact tools to agents and forwards read-only requests to the public BytesAgain API at https://bytesagain.com/api/mcp.
Related MCP server: AgentBase MCP Server
Tool | When to use | Returns |
| Find AI skills for a concrete task, keyword, domain, or integration request. Supports English, Chinese, Japanese, Korean, German, French, Spanish, and Portuguese. | Ranked skill summaries with slug, name, description, category, tags, downloads, owner, and relevance fields. |
| Fetch full details for a specific slug returned by | Detailed skill metadata, install/source links, category, tags, owner, downloads, stars, and related fields when available. |
| Browse trending or high-download skills when the user has no specific task in mind. | Top skills ranked by downloads. |
| Search workflow/use-case pages such as “write weekly reports”, “build dashboards”, or “automate ecommerce listings”. | Use-case pages and descriptions that map real-world tasks to relevant skills. |
npx -y --package github:bytesagain/mcp-server bytesagain-mcpgit clone https://github.com/bytesagain/mcp-server.git
cd mcp-server
npm install
npm startdocker build -t bytesagain-mcp .
docker run --rm -i bytesagain-mcp{
"mcpServers": {
"bytesagain": {
"command": "npx",
"args": ["-y", "--package", "github:bytesagain/mcp-server", "bytesagain-mcp"]
}
}
}Variable | Default | Description |
|
| Optional override for the public BytesAgain API endpoint. |
No API key is required. The server is read-only and does not write to BytesAgain, GitHub, Glama, or third-party services.
Website: https://bytesagain.com
MCP documentation: https://bytesagain.com/mcp
Hosted MCP endpoint: https://bytesagain.com/api/mcp
REST search example: https://bytesagain.com/api/mcp?action=search&q=video%20editor
npm install
npm testThe smoke test starts the MCP server over stdio and verifies that the tool list is exposed correctly.
MIT
Fetch detailed metadata for one AI skill by exact slug. Use only after search_skills or popular_skills returns a slug, or when the user provides a known slug. Do not guess slugs. Returns the skill name, description, category, tags, version, owner/author, downloads, stars, install command, source URLs, and related metadata when available. If the slug is not found, search again with related keywords instead of inventing details.
Inputs: slug (required).
Return the most popular AI agent skills by download count. Use for browsing, onboarding, trend discovery, or when the user asks what skills are popular without naming a specific task. Do not use this for targeted task matching; use search_skills for that. Returns compact skill summaries suitable for ranking lists and recommendations.
Inputs: limit.
Search the BytesAgain index of 60,000+ AI agent skills by keyword or natural-language task. Use this when a user asks for tools, agents, skills, automations, integrations, or capabilities for a specific job. Supports English, Chinese, Japanese, Korean, German, French, Spanish, and Portuguese queries. Results are ranked by relevance and popularity and include slug, name, description, category, tags, downloads, owner, and score fields when available. After the user chooses a result, call get_skill with the exact slug for full details.
Inputs: query (required), limit.
Search BytesAgain use-case pages by a real-world goal or workflow. Use this when the user describes an outcome such as "write a weekly report", "automate social media", "build BI dashboards", or asks how AI agents can help with a domain. Each result links to a use-case page with relevant skills. Combine this with search_skills when the user wants both workflow guidance and concrete tools.
Inputs: query (required), limit.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 4 tools
Each tool serves a clearly distinct purpose: get_skill for fetching details by slug, popular_skills for browsing top skills, search_skills for keyword-based skill discovery, and search_use_cases for finding workflow-driven content. No overlap exists.
All tool names follow the verb_noun pattern using underscores (get_skill, popular_skills, search_skills, search_use_cases). While 'popular_skills' uses an adjective rather than a verb, it is consistent in style and easily understood.
With only 4 tools, the surface is lean yet sufficient for the domain of searching and retrieving AI skills and use-cases. Each tool contributes a necessary function without redundancy.
Core operations are covered: searching skills, getting skill details, listing popular skills, and searching use-cases. However, there is no tool to retrieve full details for a specific use-case, which is a minor gap given that get_skill only covers skills.
Search & install 13,000+ AI agent skills from skills-hub.ai inside any MCP tool.
Free public MCP for AI agents — 193 tools, 44 workflows. No API key.
Search and load AI agent skills. Free metadata; full content requires a Pro or Studio account.
Find, read and install 50,000+ Agent Skills for Claude Code and other agents, with trust scores.
