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.
MCP (Model Context Protocol) sunucusu yazma: kavramlar (tools, resources, prompts), TypeScript SDK ile sunucu (Zod girdi şemaları, yapılandırılmış çıktı), stdio ve Streamable HTTP taşıma, uzak sunucuda OAuth ile kimlik doğrulama, araç tasarımı (az ve net araç, iyi açıklama, düzeltici hata mesajları), sayfalama ve büyük çıktılar, güvenlik (en az yetki, onay gerektiren işlemler, prompt injection), MCP Inspector ile test ve Claude Code / Claude Desktop'a ekleme. "MCP sunucusu yaz", "uygulamamı Claude'a bağla" dendiğinde kullan.
Model Context Protocol server exposing 53 tools, 3 resource types, and 3 prompts for AI agent consumption — quoting, building transactions, fee management, analytics, AMM operations, social fees, wallet operations over stdio transport.
1508mo agoReviewMountCreate a free account to mount
Builds, secures and tests Model Context Protocol (MCP) servers - choosing MCP vs a CLI or API, tools, resources and prompts, stdio vs Streamable HTTP transport, task-shaped tool design, logging rules, OAuth for remote servers, input validation, testing with the MCP Inspector, and versioning. Use when creating or reviewing an MCP server, exposing an API or database to AI agents through MCP, or debugging an MCP server that fails to connect, hangs or confuses the model. Not for designing the agent loop itself (use building-agents).
Use with Codex, Claude Code, or another MCP client when lsp-mcp-server is connected and semantic code navigation, analysis, refactoring, or diagnostics are needed. Covers all 29 lsp_* tools for TypeScript, Python, Rust, Go, C/C++, Ruby, PHP, Elixir, Kotlin, Java, and user-configured languages. Prefer these tools to text search for definitions, references, types, diagnostics, rename, code actions, hierarchy, symbols, ranges, and indexing.
2440d agoReviewMountCreate a free account to mount
How to use the b1-mcp-server MCP tools against SAP Business One (HANA / MS SQL database and Service Layer OData). TRIGGER when: a `b1-mcp-server` tool (`connect_database`, `execute_sql`, `execute_service_layer`, `execute_service_layer_write`, `get_schema_info`, `check_connection`) is about to run or has just failed; a query is rejected ("Only SELECT is permitted", "Unterminated quote or bracket", a table hint "is not permitted"); a result shows `TRUNCATED`; a HANA query fails with `Socket recv timeout`; a Service Layer write is refused or waits for approval; a profile connects the database but not the Service Layer. SKIP for writing the SQL or OData request itself — this skill covers the server's behaviour, not SAP B1 data modelling.
Add or change a tool, a tool's input schema or description, or the step, Maily email-body, skip-condition or payload-property schemas in apps/mcp-server (the hosted Novu MCP server, also shipped in process to the enterprise Copilot as @novu/mcp-server/tools). Keeps tools/list small (per-tool budgets, no $ref), advertises loose.pipe(strict) inputs that stay fully validated, keeps errors actionable without the schema, and preserves backward compatibility. Use before editing apps/mcp-server/src/tools or apps/mcp-server/src/utils.
40k3d agoReviewMountCreate a free account to mount
Read-only inspection of a third-party MCP server BEFORE it is added or trusted: scans tool descriptions and scopes for poisoning, returns an add, decline or sandbox verdict for a human. Never installs. Do not use to vet a skill or plugin (use skill-vet), to review first-party code (use review-hard or security-review), or to fetch a remote server definition (record its origin via capture-references, then get a local copy out of band).
1037d agoReviewMountCreate a free account to mount
Use to build, wire up, or debug an MCP (Model Context Protocol) server that gives Claude access to an internal API, database, or SaaS tool. Trigger when the user wants Claude to connect to their own system, asks for an MCP server, needs custom tools for Claude Code or the Claude app, or an existing server's tools are not showing up.
37856d agoReviewMountCreate a free account to mount
Use when the user asks to build an MCP server, create an MCP integration, wrap an API for AI agents, or expose tools via the Model Context Protocol. Guides through deployment model selection (remote HTTP, MCPB, local stdio), tool-design patterns, and framework choice before scaffolding code.
Add a new MCP server to pi (local stdio scripts or remote HTTP servers with OAuth/API keys like Slack, Linear, Grafana, Redash, Snowflake). Covers mcp.json, the pi mcp CLI, OAuth sign-in, exposure settings, cookie-gate auth-hook prefixes, and verification. Use when the user asks to add/configure/register a new MCP server in pi.
Guide for using Apollo MCP Server to connect AI agents with GraphQL APIs. Use this skill when: (1) setting up or configuring Apollo MCP Server, (2) defining MCP tools from GraphQL operations, (3) using introspection tools (introspect, search, validate, execute, explorer), (4) configuring authentication, CORS, health checks, or telemetry, (5) writing Rhai scripts for request lifecycle hooks, (6) defining MCP prompts, (7) troubleshooting MCP server connectivity or tool execution issues, (8) building MCP Apps for interactive UI experiences, (9) deploying Apollo MCP Server to production.
12310mo agoReviewMountCreate a free account to mount
Migrates an MCP server with interactive widgets from the OpenAI Apps SDK (window.openai, text/html+skybridge) to the MCP Apps standard (@modelcontextprotocol/ext-apps), covering server-side and client-side changes.
809mo agoReviewMountCreate a free account to mount
Generate a complete Go MCP server project with proper structure, dependencies, and implementation using the official github.com/modelcontextprotocol/go-sdk.
No other project uses it yet
41k21d agoReviewMountCreate a free account to mount
Pentest an MCP server for authentication bypass, confused-deputy SSRF, and tool-argument injection - black-box from its URL, deeper with repo or host access. Use to assess an MCP server's exposure.
15447d agoReviewMountCreate a free account to mount
Configures Google Cloud API Gateway to act as a remote Model Context Protocol (MCP) server (Public Preview) that exposes REST APIs as agent tools over HTTP (POST /mcp). Use when migrating OpenAPI 2.0 specs to OpenAPI 3.x for MCP, annotating specs with x-google-api-management.mcp and x-google-mcp-tool, securing tools/list with JWTs or API keys, connecting Google ADK (McpToolset) or Apigee API hub and Agent Registry, or troubleshooting MCP JSON-RPC errors (-32601, -32602, -32000). Do not use for Apigee X proxy bundles, outbound LLM model routing, or GKE Gateway API.
Steady+28 stars this week
No other project uses it yet
24k48d agoReviewMountCreate a free account to mount
Audit an MCP server's own declaration — primitive choice (tool/resource/prompt), tool naming, input/output schemas, behavior annotations, error channels, transport fit, server instructions, and tool-count/token budget — the design-rule slice of the MCP spec plus agent-friendliness rules. Invoke when authoring, reviewing, or publishing an MCP server, or vetting a third-party server before wiring it in. Skip when auditing individual tool definitions' ergonomics or verifying annotations against their implementation — even for tools an MCP server exposes (use audit-tool-definition) or the whole agent harness's exfiltration/security architecture (use audit-lethal-trifecta).
Design, scaffold, audit, and upgrade Model Context Protocol servers. Use when the user asks to build or migrate an MCP server, adopt MCP 2026-07-28, add dual-era support, create an MCP integration, expose an API or data source through MCP tools/resources/prompts, add OAuth or API-key auth to an MCP endpoint, run an authorization server for it, support browser-hosted MCP clients, or choose an MCP transport/auth/deployment shape.
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.