by agentfront
TypeScript-first framework for the Model Context Protocol (MCP). You write clean, typed code; FrontMCP handles the protocol, transport, DI, session/auth, and execution flow.
# Add to your Claude Code skills
git clone https://github.com/agentfront/frontmcpGuides for using mcp servers skills like frontmcp.
Last scanned: 5/30/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-30T16:12:00.585Z",
"npmAuditRan": false,
"pipAuditRan": true
}See how frontmcp compares with popular alternatives.
frontmcp is an open-source mcp servers skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by agentfront. TypeScript-first framework for the Model Context Protocol (MCP). You write clean, typed code; FrontMCP handles the protocol, transport, DI, session/auth, and execution flow. It has 146 GitHub stars.
Yes. frontmcp passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/agentfront/frontmcp" and add it to your Claude Code skills directory (see the Installation section above).
frontmcp is primarily written in TypeScript. It is open-source under agentfront on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other MCP Servers skills you can browse and compare side by side. Open the MCP Servers category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh frontmcp against similar tools.
No comments yet. Be the first to share your thoughts!
Top skills in this category by stars
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
frontmcp.dev · Learn · Reference · Examples · Playground · Blog
Classes in, protocol out. FrontMCP handles transport, DI, sessions, auth and execution flow, and the same server runs locally and in production unchanged.
import 'reflect-metadata';
import { App, FrontMcp, Tool, ToolContext, z } from '@frontmcp/sdk';
@Tool({
name: 'add',
description: 'Adds two numbers together',
inputSchema: { a: z.number(), b: z.number() },
})
class AddTool extends ToolContext {
async execute(input: { a: number; b: number }) {
return input.a + input.b;
}
}
@App({ id: 'calc', name: 'Calculator', tools: [AddTool] })
class CalcApp {}
@FrontMcp({
info: { name: 'Demo', version: '0.1.0' },
apps: [CalcApp],
http: { port: 3000 },
})
export default class Server {}
npx frontmcp create my-app # new project (Node 24+)
npx frontmcp init # or add FrontMCP to an existing one
Then follow Learn on frontmcp.dev, or browse Tools, Resources, Prompts, Agents, Auth, Plugins, Tool UI, Testing and Deployment. Try it live in the Playground.
Install frontmcp (CLI) and @frontmcp/sdk. The rest is pulled in for you, or opt-in. Keep every @frontmcp/* package on the same version; a mismatch fails fast at boot (why).
| Package | What it does |
|---|---|
frontmcp |
CLI: create, init, dev, build, inspect, doctor |
@frontmcp/sdk |
Core framework: decorators, DI, flows, transport, MCP protocol |
@frontmcp/auth |
OAuth, JWKS, DCR/CIMD, sessions, credential vault |
@frontmcp/testing |
E2E test framework with fixtures and matchers |
@frontmcp/adapters |
Generate tools from an OpenAPI spec |
@frontmcp/skills |
Curated SKILL.md catalog for scaffolding and skills install |
@frontmcp/guard |
Rate limits, concurrency and policy guards |
@frontmcp/observability |
Structured logging, metrics and tracing |
@frontmcp/react |
React hooks and client for a FrontMCP server |
@frontmcp/ui / uipack |
Widgets, SSR renderers, MCP Bridge, themes |
@frontmcp/edge |
Run a server on Cloudflare Workers / V8 isolates |
@frontmcp/storage-sqlite |
SQLite session, task and elicitation stores |
@frontmcp/nx |
Nx generators and executors |
Internal, published so the above resolve: protocol, di, utils, lazy-zod.
| Package | What it does |
|---|---|
@frontmcp/plugin-cache |
Cache tool results with a TTL |
@frontmcp/plugin-remember |
Per-session memory (this.remember) |
@frontmcp/plugin-approval |
Human approval gates before a tool runs |
@frontmcp/plugin-codecall |
Let the model compose tool calls as code |
@frontmcp/plugin-dashboard |
Built-in web dashboard |
@frontmcp/plugin-feature-flags |
Toggle tools and apps at runtime |
@frontmcp/plugin-skilled-openapi |
OpenAPI to skills and meta-tools for big APIs |
@frontmcp/plugin-webmcp |
Expose in-page tools to browser agents (WebMCP) |
PRs welcome: see CONTRIBUTING. Released under the Apache-2.0 license.
Docs also mirrored at docs.agentfront.dev/frontmcp.