Claude skills and agent skills

rrezartprebrezaSkill

mcp-server

rrezartprebreza/spring-boot-skills/skills/spring-boot-3/mcp-server/SKILL.md

Use when exposing Spring Boot 3 application capabilities through Model Context Protocol tools, resources, or prompts. Covers Spring AI 1.x tool callback registration, transports, schemas, errors, security, and standalone MCP Java SDK compatibility.

rrezartprebrezaSkill

mcp-server

rrezartprebreza/spring-boot-skills/skills/spring-boot-4/mcp-server/SKILL.md

Use when exposing Spring Boot 4 application capabilities through Model Context Protocol tools, resources, or prompts. Covers Spring AI 2.0 MCP annotations, transport selection, schemas, errors, security, and the standalone MCP Java SDK 2.x.

Happy-Technologies-LLCSkill

mcp-server

Happy-Technologies-LLC/happy-platform-skills/skills/development/mcp-server/SKILL.md

Set up ServiceNow as an MCP (Model Context Protocol) server defining tool capabilities, authentication, resource endpoints, and integration patterns for AI agents

nimadorostkarSkill

mcp-server

nimadorostkar/Claude-Skills-collection/skills/ai/mcp-server/SKILL.md

Use when building a Model Context Protocol server. Covers tool, resource, and prompt design, transport choice, authentication, error handling, and testing an MCP server against a real client. Trigger on "build an mcp server", "expose our api to claude", "the model keeps calling my mcp tool wrong". Do not use for packaging the server into a distributable plugin — see the plugin-development skill; for the agent loop that calls tools, see the agent-design skill.

saschb2bSkill

mcp-server

saschb2b/skills/skills/engineering/mcp-server/SKILL.md

Build, extend, and maintain a Model Context Protocol (MCP) server across its whole lifecycle against the current spec and official SDKs. Covers the architecture, choosing a transport (stdio vs Streamable HTTP), writing tool definitions agents actually use, adding tools without breaking existing agents, versioning and deprecation, the security threat model (tool poisoning, token passthrough, prompt injection, OAuth), testing with the MCP Inspector, and publishing to the registry. Use when building an MCP server, exposing a CLI, API, or app to AI agents (Claude Code, Cursor, Cline, Windsurf), adding or reviewing MCP tools, fixing an agent that calls the wrong tool or loads too many, securing or authorizing an MCP server, migrating transports, or shipping and versioning one. Also for any new agent-tool integration where the target has a scripting API, CLI, or HTTP surface.

leewang246731-beepSkill

mcp-server

leewang246731-beep/aijiqun/skills/mcp-server/SKILL.md

AgentChat MCP Server — expose 8 AI providers as MCP tools for any MCP-compatible client (Claude Desktop, Cursor, Continue.dev). Configuration/reference skill, not executable

prizmadReads credentialsSkill

mcp-server

prizmad/agent-skills/mcp-server/SKILL.md

MCP server for AI agents to create video ads via Streamable HTTP. Primary auth is OAuth 2.1 + Dynamic Client Registration (the modern Claude Desktop / Claude.ai / ChatGPT / Cursor "Connect" flow); long-lived API keys remain supported for headless clients.

revealui-studioReads credentialsSkill

mcp-server

revealui-studio/revskills/skills/mcp-server/SKILL.md

Model Context Protocol server development patterns. Use when building custom MCP servers, exposing tools and resources, handling JSON-RPC, implementing credential isolation, or integrating with Claude Desktop, Cursor, or AI agents. Covers @modelcontextprotocol/sdk, StdioServerTransport, tool schemas, and multi-tenant credential patterns.

timsonnerPipes a download into a shellSkill

mcp-server

timsonner/agent-skills/mcp-server/SKILL.md

Specification for building Model Context Protocol servers using Python

michaelsvanbeekReads credentialsSkill

mcp-server

michaelsvanbeek/personal-agent-skills/skills/mcp-server/SKILL.md

MCP server design, development, and audit using the Python SDK (FastMCP). Use when: creating a new MCP server, wrapping an API as MCP tools, auditing an existing MCP server for patterns and gaps, adding auth/secrets/retry/observability to an MCP server, choosing between tools vs resources vs prompts, designing MCP resources or resource templates, creating MCP prompts for workflow bootstrapping, choosing between low-level Server and FastMCP, designing tool contracts, configuring pydantic-settings, adding structured logging, writing MCP server tests, or improving an existing MCP server codebase.

mukcoSkill

mcp-server

mukco/claude-skills/skills/mcp-server/SKILL.md

Ruby MCP server development — tools, prompts, resources, transport, the mcp gem, LLM tool integrations.

AnthropicSkill

build-mcp-server

anthropics/claude-plugins-official/plugins/mcp-server-dev/skills/build-mcp-server/SKILL.md

This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol. It is the entry point for MCP server development — it interrogates the user about their use case, determines the right deployment model (remote HTTP, MCPB, local stdio), picks a tool-design pattern, and hands off to specialized skills.

serverlessReads credentialsSkill

serverless-mcp

serverless/serverless/skills/serverless-mcp/SKILL.md

Hosts Model Context Protocol (MCP) servers on AWS Lambda with the Serverless Framework's built-in MCP support: an official-SDK server module, with the streaming endpoint, access control, OAuth discovery and packaging handled for you. Use whenever the user wants to deploy, host, secure or debug an MCP server on AWS or Lambda, writes or edits an `mcp:` block in serverless.yml, exposes tools, resources or prompts to Claude or another AI client over HTTP, or hits an `MCP_*` configuration error (MCP_UNSUPPORTED_NODE_RUNTIME, MCP_FUNCTION_NAME_COLLISION, MCP_INVALID_STATE_ARN, and the rest). Trigger even when neither "Serverless Framework" nor "MCP" is named but the user describes putting their own tools in front of an AI client over an HTTPS endpoint.

andrea-magniSkill

mars-mcp-server

andrea-magni/MARS/Skills/mars-mcp-server/SKILL.md

Build MCP (Model Context Protocol) servers in Delphi with MARS-Curiosity, so AI agents (Claude, ChatGPT, Open WebUI/Ollama, MCP Inspector) can discover and call Delphi code as tools, read MCP resources, use MCP prompts and show interactive views (MCP Apps). Use this skill whenever the user wants to expose Delphi/MARS functionality to an AI agent or LLM, mentions MCP, MCP server, MCP tools, resources, prompts, tool calling, function calling, AI agents, connectors, or wants Claude/ChatGPT/a local model to query their Delphi application or database; also when working with MARS.MCP.* units, TMCPResource, [MCPTool], [MCPResource], [MCPPrompt], [MCPToolUI], [MCPAppResource], TMCPOAuthServer, MCP Apps / interactive UIs rendered by Claude next to a tool result, or debugging an MCP client that cannot connect or authenticate to a MARS server.

benborlaSkill

mcp-server-mysql

benborla/mcp-server-mysql/skills/mcp-server-mysql/SKILL.md

Query MySQL databases from Codex via MCP

dust-ttSkill

dust-mcp-server

dust-tt/dust/.claude/skills/dust-mcp-server/SKILL.md

Step-by-step guide for creating new internal MCP server integrations in Dust that connect to remote platforms (Jira, HubSpot, Salesforce, etc.). Use when adding a new MCP server, implementing a platform integration, or connecting Dust to a new external service.

No other project uses it yet

awarexoneReads credentialsSkill

mcp-server-audit

awarexone/Agentic-Bug-Hunter/skills/mcp-server-audit/SKILL.md

Security audit of Model Context Protocol (MCP) servers — tool poisoning, prompt injection via tool descriptions and results, unscoped/over-privileged tools, path traversal in file tools, command injection in shell/exec tools, SSRF in fetch tools, secret leakage through tool output, missing approval gates on state-changing actions, confused-deputy and rug-pull tool redefinition, token passthrough, and unsafe stdio/HTTP transport config. Covers auditing both first-party and third-party MCP servers (Python FastMCP, Node MCP SDK) and their client configs (Claude Desktop, Cursor, Cline, Windsurf, Zed). Use when reviewing, hardening, or hunting bugs in an MCP server, an agent's tool integrations, or a mcpServers config block. 中文触发词：MCP审计、工具投毒、提示注入、智能体安全、MCP服务器漏洞

nesquikmReads credentialsSkill

setup-mcp-server

nesquikm/mcp-rubber-duck/.claude/skills/setup-mcp-server/SKILL.md

Add mcp-rubber-duck MCP server to an AI coding tool (Claude Desktop, Cursor, VS Code, Windsurf, etc.)

blazickjpSkill

arxiv-mcp-server

blazickjp/arxiv-mcp-server/skills/arxiv-mcp-server/SKILL.md

Use when finding, comparing, reading, or monitoring arXiv papers, including requests for abstracts, citation graphs, original LaTeX, section-level technical details, or literature reviews.

No other project uses it yet

samugit83Skill

mcp-server-tools

samugit83/redamon/skills/mcp-server-tools/SKILL.md

Adding, removing or changing a tool on RedAmon's INBOUND MCP server, where external agents connect in with a personal access token. The wiki API reference is generated from the server's live tools/list and goes stale silently, and each tool's annotations and declared scopes are published to connected clients. Trigger: editing a registerTool call in webapp/src/lib/mcp/server.ts; editing tools.ts, writeTools.ts, scopeCopy.ts or apiReference.ts in webapp/src/lib/mcp/; changing the scope list, default scopes, expiry presets or token prefix in webapp/src/lib/mcpAuth.ts.

No other project uses it yet