SkillForAgentsFind the right skill or MCP before you wire it in.
A curated, verified catalog of Claude Agent Skills and MCP servers — organized by use case, with the environment variables, runtime, and client compatibility every listing actually needs.
Browse by use case, not by vendor.
Every listing is tagged against a fixed set of operational objectives — pick the job you're automating, not the brand name.
Skills worth knowing about
DOCX
Create, edit, and analyze Word documents — headings, tracked changes, and more.
MCP servers worth knowing about
Cloudflare
Official Cloudflare MCP servers — Workers, KV, R2, D1, DNS, and the rest of the platform from an agent session.
Most directories stop at a name and a link.
We built this after finding the same gap across existing agent-tooling directories: no technical metadata, no verification status, and no MCP coverage at all. Here's what every listing on SkillForAgents includes by default.
| Feature | SkillForAgents | Typical directory |
|---|---|---|
| Per-listing required environment variables | ||
| Runtime environment (npx / docker / uv / Python) | ||
| Client compatibility tags | ||
| Maintenance / verification status | ||
| Dedicated MCP server catalog | ||
| Category + client + runtime filtering | Limited |
What is SkillForAgents?
SkillForAgents is an AI agent skills directory and MCP server directory built for one job: helping you find the right AI agent skills and Model Context Protocol integrations before you wire them into a real agent. Most general-purpose lists of "AI agent tools" stop at a name, a logo, and an outbound link. This one goes further — every entry in the agent skills library is tagged with its runtime, required environment variables, client compatibility, and verification status, so you can evaluate it without opening a repository first.
An AI agent skills catalog organized by use case
Rather than sorting by vendor, the AI agent skills database is organized by the operational objective a skill or MCP server solves. Whether you're looking for Claude agent skills, Claude Code skills, or Cursor MCP servers, you can browse by category — web scraping, database administration, DevOps and CI/CD, browser automation, search and research, full-stack coding, documents and files, communication, data and analytics, or productivity and memory — instead of scrolling an alphabetical list. That taxonomy makes this an effective AI agent skill finder for teams evaluating agentic workflow integrations at scale, not just a single tool.
A dedicated MCP server directory
Model Context Protocol has quickly become the standard way to connect an agent to a real system — a database, a browser, a search index, a filesystem. This MCP server directory tracks reference servers, community builds, and first-party integrations side by side with Claude agent skills, so you don't need a second site to compare a Model Context Protocol skill against a native Claude skill for the same job. Each MCP listing documents its install command, runtime (npx, Docker, uv/Python, or a compiled binary), and every required API key, which is the detail most AI agent tools registry sites leave out entirely.
Export a ready-to-use MCP config
Finding the right server is only half the job — you still have to wire it into your client. Every MCP listing has an "Add to Stack" button; add the servers you need and the stack export tool generates a ready-to-paste mcpServers config for Claude Desktop, Cursor, Cline, or Windsurf, built from each server's real install command and prompting you for any required environment variables. Nothing you add to your stack is saved or sent anywhere — it stays in your browser for the session.
Built for people building AI agents
If you're one of the growing number of engineers, indie builders, or platform teams assembling agentic systems, this catalog is meant to save you the research time. It works as an AI agent skill search tool when you know roughly what you need, and as a discovery surface — best AI agent skills, trending Claude Code tools, and newly added OpenAI agent skills and Cursor agent skills — when you're still exploring what's possible. Teams use it to find AI agent skills for developers, AI agent skills for DevOps, AI agent skills for data analysis, AI agent skills for web scraping, and AI agent skills for code review, alongside skills built for marketing, sales, customer support, research, automation, and SEO workflows.
Verified, not just listed
Every listing carries a verification badge — verified, community, or unverified — so you know whether a skill or MCP server is actively maintained before you depend on it. We don't run a custom agent skills exporter or generate listings automatically; every entry in this agent skills marketplace is checked against its source repository. If you're building or maintaining your own AI agent toolkit and want it discoverable in a directory that treats technical detail as a requirement rather than an afterthought, submit a listing — it takes a structured GitHub issue, not an account.
How to find the right skill fast
Use the category filters if you already know the job — say, an MCP server for database administration or a Claude skill for spreadsheet generation. Use the search bar as an AI agent skill search shortcut when you know part of a name. And check back regularly: this is a living AI agent skills resource, not a static list, with new skills for AI agents and tools for building AI agents added as the ecosystem around Claude, Cursor, Codex, and other agent runtimes keeps expanding.
Common questions
Agent skills, MCP servers, and where Claude, ChatGPT, Cursor, and other AI agents fit in — answered in one place.
What are AI agent skills?
AI agent skills are packaged instructions, scripts, and resources that an AI agent like Claude loads on demand to perform a specific task well — for example editing a spreadsheet, generating a PDF, or reviewing code. They extend what an agent can do beyond its base model, without retraining it.
How do agent skills work?
Each skill ships as a folder with a short description, a set of instructions, and optional scripts or reference files. The agent scans the available skills' descriptions, decides which one is relevant to the current task, and only then loads its full instructions into context — so skills stay cheap to have installed and expensive only when actually used.
What are the common types and categories of agent skills?
Skills are usually grouped by the job they do rather than by vendor: web scraping, database administration, DevOps and CI/CD, browser automation, search and research, full-stack coding, documents and files, communication, data and analytics, and productivity or memory tooling. SkillForAgents uses this same use-case taxonomy so you can browse by task instead of by name.
What are the best AI skills for agents?
There isn't a single best skill — a skill for generating polished PDFs isn't useful for a database migration task. Instead, look for skills that are actively maintained, clearly document their required environment variables and runtime, and are verified against their source repository, which is exactly what every listing on SkillForAgents shows before you install anything.
What is an MCP server?
An MCP (Model Context Protocol) server is a standard interface that connects an AI agent to a real system — a database, a browser, a search API, or a file system — so the agent can take real actions instead of only generating text.
What's the difference between an AI agent skill and an MCP server?
A skill is a set of instructions and resources an agent loads into its own context to perform a task. An MCP server is a live connection to an external system — a database, browser, or API — that the agent calls out to and gets real results back from. Skills teach an agent how to do something; MCP servers give it something new to act on.
Can I generate a config file for the MCP servers I want to use?
Yes. Add servers to your stack from any MCP listing, then open the Export Your MCP Stack page to get a ready-to-paste mcpServers JSON block for Claude Desktop, Cursor, Cline, or Windsurf, built from each server's real install command and prompting you for any required environment variables. Everything stays in your browser — nothing is saved or sent anywhere.
Is SkillForAgents free to use?
Yes. Browsing the AI agent skills directory and MCP server directory is free, and every listing links to its original source so you can install it directly.
How do I submit a skill or MCP server to the directory?
Submissions go through a public GitHub issue template linked from the Submit page — no account required. You fill in a structured form covering the runtime, required environment variables, and client compatibility, and it's reviewed before being added to the catalog.
What is AI Claude used for?
Claude is Anthropic's family of AI models, used for tasks like writing and editing, coding and debugging, research and summarization, and data analysis — and, through Claude Code and Claude Agent Skills, for autonomous multi-step work like running scripts, browsing the web, and operating on files directly.
Built something worth listing?
Submissions go through a public GitHub issue template — no account, no gatekeeping, just a structured form so every listing ships with the metadata this catalog needs.
Submit a Listing