Awesome Agent SkillsSAFE
MCP server providing 100+ AI agent skills from Anthropic, Vercel, Trail of Bits, Hugging Face & more. Works with Claude, GitHub Copilot, and any MCP client.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/shadowrootdev/awesome-agent-skills-mcp/actions/workflows/ci.yml) [](https://github.com/shadowrootdev/awesome-agent-skills-mcp/actions/workflows/security-audit.yml) [](https://github.com/shadowrootdev/awesome-agent-skills-mcp/actions/workflows/codeql.yml) [](https://www.npmjs.com/package/awesome-agent-skills-mcp) [](https://www.npmjs.com/package/awesome-agent-skills-mcp) [](https://opensource.org/licenses/MIT) [](https://nodejs.org) [](https://modelcontextprotocol.io) [](https://github.com/shadowrootdev/awesome-agent-skills-mcp/releases) [](https://github.com/shadowrootdev/awesome-agent-skills-mcp/stargazers)
A Model Context Protocol (MCP) server that provides access to 100+ curated AI agent skills from the [VoltAgent Awesome Agent Skills](https://github.com/VoltAgent/awesome-agent-skills) collection.
Transform your AI assistants into specialized experts with skills from Anthropic, Vercel, Trail of Bits, Hugging Face, Stripe, Expo, and many more leading organizations.
🚀 Quick Start
npx awesome-agent-skills-mcp
That's
362d20669c32OBSERVED · 2026-10-09Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add awesome-agent-skills-mcp -- npx -y [email protected]
Exposed tools (4)
3 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_skill | read | Get detailed information and documentation for a specific skill |
invoke_skill | write | Invoke a skill with parameters to get formatted instructions |
list_skills | read | List all available agent skills that can be invoked |
refresh_skills | read | Refresh skills cache from the repository |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (7)
.eslintrc.cjs
const serverPath = join(__dirname, '../../dist/index.js');
const serverPath = join(__dirname, '../../dist/index.js');
import { SkillRegistry } from '../../src/models/registry.js';import { Skill } from '../../src/models/skill.js';import { RepositorySource } from '../../src/models/repository.js';@modelcontextprotocol/sdk, simple-git, zod, @types/node, @typescript-eslint/eslint-plugin, @typescript-eslint/parser, @vitest/coverage-v8, eslint
Gates applied: no_behavioural_pass.
362d20669c32full audit observations/trust-audit/mcp-server/shadowrootdev__awesome-agent-skills.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | 362d20669c32 | SAFE | B | 89 | first audit |
Questions
What is the Awesome Agent Skills MCP server?
MCP server providing 100+ AI agent skills from Anthropic, Vercel, Trail of Bits, Hugging Face & more. Works with Claude, GitHub Copilot, and any MCP client.
What tools does Awesome Agent Skills expose?
4 in total: 3 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Awesome Agent Skills safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Awesome Agent Skills need?
No credential environment variables were found in its source, so it appears to need none.
How does Awesome Agent Skills run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as awesome-agent-skills-mcp at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (362d20669c32), read on 2026-10-09. The repository is watched and re-audited when it changes.