agentskill-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@agentskill-mcpFind a skill to remove watermarks from images"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
What it does
Your agent hits a task it can't do — read A-share market data, get a second model to audit a diff, transcribe an interview, remove a watermark, clone a site's design system. Somewhere out there is a skill file that would solve it. Finding one is the annoying part.
This server puts a small, vetted catalog inside the agent. It searches, reads the delivery facts, and tells you exactly what to run. Free items come with a direct download URL; paid ones come with a price and no sales pitch.
The catalog is agentskill.nz. It's deliberately small. Public skill directories carry hundreds of thousands of entries with no vetting — measured average quality around 6 out of 12, roughly a third carrying prompt-injection risk. Every entry here ships with what it does, what it needs to run, what it was tested against, and where it stops.
Related MCP server: SkillFlow MCP Server
Install
No install step. Point your MCP client at it:
{
"mcpServers": {
"agentskill": {
"command": "npx",
"args": ["-y", "@simonlin1212/agentskill-mcp"]
}
}
}Claude Code:
claude mcp add agentskill -- npx -y @simonlin1212/agentskill-mcpRequires Node 18+. Nothing to configure, no API key, no account. The server holds no state and writes nothing to your machine.
Tools
Tool | What it answers |
| "Is there something for X?" Filter by free text, module, or price tier. |
| "What exactly am I getting, and how do I get it?" Version, package size, last update, source repository, and the obtain path. |
| "What's in here?" The four modules, their counts, and what the two delivery forms mean. |
Search reads Chinese and English in one index, so 去水印 and remove watermark both land on the same
entry. Whichever you type, results carry both names.
What the catalog contains
Four modules — Finance, Commerce, Creator, General — holding two forms:
Install Skill — a skill file the agent loads. Copy it into the agent's skills directory.
Deploy App — a runnable app with its own UI. Deploy it, then use it alongside the agent.
Roughly half the entries are free. Several are the packaged form of open-source repositories with a combined 16,000+ GitHub stars; where a capability builds on an upstream project, the upstream and its licence are named on the product page.
How it behaves
This is a catalog tool, not an ad slot. Three rules it keeps:
Free means free. Where the catalog publishes a download URL, the tool hands it straight over — no account, no gate. (A free entry can occasionally have no published archive yet; it says so.)
Paid states the price and stops. No urgency, no recommendation language. The download link for a paid item is issued after checkout, on the order page and by email.
Concretely: anything the catalog does not explicitly mark
freeis treated as paid (fail closed), its download field is dropped, URLs are stripped out of its name, outcome, install, source and repository fields, and the assembled output is checked against a route allowlist. The only web addresses that survive are, onhttps://agentskill.nz(optionally under/zh): the site root,/products/<handle>,/collections/<handle>,/pages/<handle>, and/cartor/cart/<variant>:<qty>— each matched as a whole route, so a deeper path like/products/x/downloaddoes not qualify. Anything else — another host, plain http, a lookalike domain,/download?id=…— makes the server refuse to return that record.What this does not cover: a bare hostname with no scheme (
evil.example/x). Catching those means treating any domain-shaped text as an address, and.mdis a real TLD —SKILL.mdin a delivery manifest would be rejected as a domain, breaking every paid listing. These responses are plain text, so a bare hostname only becomes a link if something downstream linkifies it.The gap worth naming: the catalog is cached for up to five minutes. An item that turned paid inside that window is still described from the previous snapshot — including the direct download URL it had while it was free.
An install command is information, not authorization.
get_capability— the only tool that returns an install command — says so on every call. Your agent should confirm with you before writing to your filesystem or spending your money.
The catalog URL is discovered from the site's /llms.txt at runtime rather than hardcoded, so the
server keeps working when the site rotates it.
Building from source
npm install
npm run build
node test-smoke.mjs # drives the server over real MCP stdiotest-smoke.mjs speaks the wire protocol rather than importing the module, so it catches registration
and transport breakage that a unit test would miss. It also asserts that no paid item ever returns a
file URL.
Changelog
See CHANGELOG.md.
Disclaimer
This server reads a catalog and returns what it says. It does not evaluate whether a capability suits your use case, and it does not execute anything. Skill files are code your agent will read and act on — review them before use, the same as any dependency.
Support
If this saved you some time ☕
License
MIT
Author: Simon Lin · X @linsizhen · Email: simonlin0423@gmail.com
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityAmaintenanceSearch and discover AI agents, skills, prompts, bundles and MCP connectors from a curated catalog of 4500+ assets. Provides tools for searching, browsing categories, and accessing detailed information about each asset.5155MIT
- AlicenseAqualityDmaintenanceConnects AI coding agents to the SkillFlow marketplace to search, discover, and retrieve detailed information about agent skills. It enables users to browse trending skills, categories, and publisher data directly through MCP-compatible environments.5531MIT
- AlicenseAqualityCmaintenanceEnables discovery and installation of agent skills from curated GitHub repositories, allowing users to search large collections and inspect skill contents directly. It supports downloading skills locally and provides grounded scaffolds for creating new skills based on existing patterns.52MIT
- AlicenseAqualityCmaintenanceEnables AI assistants to search, discover, and get recommendations from 20,000+ skills, tools, agents, rules, and MCP servers.5251MIT
Related MCP Connectors
Search your team's shared AI-skill library, get install commands, and save skills from your agent.
A registry of 5,900+ peer-authored skills any MCP agent can search and load on demand.
Search 41,000+ agent skills, MCP servers, plugins & loops — real install counts and stars.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/simonlin1212/agentskill-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server