Build production-ready Model Context Protocol (MCP) servers using the official MCP SDK. Scaffold, configure, secure, and deploy MCP servers with best practices for security, monitoring, and reliability. Use for creating robust MCP servers that integrate with Claude Code.
Use when building, installing or registering a personal MCP server — adding its `[project.scripts]` entry point, installing it with `uv tool install` from a local checkout or straight from git instead of publishing to PyPI, registering it with `claude mcp add` and choosing local/project/user scope, switching between an editable dev install and a released one without re-registering, and the per-repo dev loop (`inv dev-env.setup`, `inv quality.precommit`, why automation needs `uv run inv`) for the repos that produce these servers.
ALWAYS LOAD THIS SKILL when working with FileServer, SMB, SMB2, SMB3, CIFS, file sharing, MS-SMB2, MS-FSCC, MS-FSA, MS-DFSC, MS-FSRVP, MS-RSVD, MS-SQOS, or any file server protocol test implementation. This skill assists with writing FileServer protocol test cases, implementing new test scenarios, discovering reusable libraries, adapters, and transport implementations (TCP, QUIC, NetBIOS, RDMA). CRITICAL--Before implementing any test, first classify the domain by analyzing concepts (File*, Fs*, FileSystemAttributes = FSA; NEGOTIATE, SESSION_SETUP, SMB commands = SMB2). Test scenarios from MS-SMB2 that involve File*/Fs* concepts belong to the FSA test suite. Provides test case patterns, storage locations, ProtoSDK usage, and test execution guidance. Protocols under FileServer/src include Auth, Common, DFSC, FSA, FSAModel, FSRVP, RSVD, ServerFailover, SMB2, SMB2Model, and SQOS.
5668mo agoReviewMountCreate a free account to mount
Distribution-first growth ledger for @delorenj/mcp-server-trello — grow reach now, defer (but record) monetization. Use for questions about distribution, reach, growth, adoption, downloads, stars, marketplace listings (Smithery, Claude marketplace / directory, Trello Power-Up marketplace), the onboarding funnel (key+token vs OAuth), npm discoverability, and "how do I grow this", "where do MCP installs come from". Also holds the PARKED monetization thesis — monetization, pricing, open-core, GitHub Sponsors, Team/Pro waitlist, "should I charge for this", "the server that remembers". Current stance: **DISTRIBUTION FIRST — monetization deferred/recorded** (a bet with an explicit build-trigger, NOT built). Do NOT use for product / tool-surface decisions (mcp-server-trello-product-doctrine), the release/publish procedure (mcp-server-trello-release), or architecture / craft judgment (mcp-server-trello-craft-doctrine).
4463mo agoReviewMountCreate a free account to mount
Canonical build → release → tag → publish procedure for the @delorenj/mcp-server-trello repo. Use when cutting a release, bumping the version, tagging, or publishing to npm / the MCP registry — triggers: "cut a release", "release 1.x.y", "ship a new version", "bump the version", "publish to npm", "publish to the MCP registry", "tag the release", "how do I release this". Codifies the FOUR version-bearing literals that must move in lockstep (package.json, server.json ×2, src/index.ts McpServer info) plus CHANGELOG, and the exact GitHub-Actions triggers that make merging a PR the publish event. Do NOT use for generic changelog prose (docs-changelog), cross-repo semver task scaffolding (mise-versioning), or non-release tagging.
4463mo agoReviewMountCreate a free account to mount
Build MCP servers in TypeScript using the official SDK. Exposing internal functions as tools, prompts, resources. Covers transport (stdio, Streamable HTTP), auth (API keys, OAuth 2.1), debugging with MCP Inspector, and remote exposure via Tailscale/Cloudflare Tunnel. Use when building, scaffolding, or deploying MCP servers in TypeScript/Node.
178mo agoReviewMountCreate a free account to mount
Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
Build or harden a ScaleDock MCP server that follows the MCP authorization spec, OAuth 2.1, JWT verification and Problem Details, with PermDock deciding every tool call. Use when adding an MCP surface, protecting MCP tools, wiring Protected Resource Metadata, scope challenges or step-up, filtering tools/list per user, adding human approval to destructive tools, or reviewing an MCP server against the specs.
Use kuri-server to automate Chrome via HTTP API — navigate pages, get a11y snapshots, interact with elements, capture network traffic (HAR), extract cookies, and bypass bot protection. Use when the user wants to browse websites, scrape data, fill forms, test web apps, or interact with protected sites via a headless browser. Trigger phrases include "browse to", "open the page", "get the page content", "fill the form", "capture network traffic", "get cookies", "bypass bot protection".
3654mo agoReviewMountCreate a free account to mount
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
How do I use one I find here?
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
What do the warnings mean?
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Which skills worked for people?
Open a skill to see its discussion. Reports from people and their agents are coming.