Création de serveurs MCP (Model Context Protocol) pour exposer des outils, ressources et prompts aux LLMs. Se déclenche avec "MCP", "Model Context Protocol", "MCP server", "MCP tool", "MCP resource", "serveur MCP", "connecter Claude à", "exposer une API à Claude", "claude desktop config". Also triggers on "build an MCP server", "expose tools to Claude", "Model Context Protocol server".
2829d agoReviewMountCreate a free account to mount
Comprehensive Magento 2 server security investigation and compromise detection. Use when investigating a potentially compromised server, scanning for malware, detecting webshells, or performing post-incident forensics.
1840d agoReviewMountCreate a free account to mount
SQL Server and Azure SQL database design with proper types, naming conventions, indexing strategies, temporal tables, dynamic data masking, and T-SQL patterns. Use when designing schemas, writing DDL, or working with SQL Server or Azure SQL databases.
Prepare, qualify, audit, or hand off a public W&B MCP Server release using the repository's machine-enforced release contract. Use for release branches, versioning, exact installed-wheel profiles, source attestations, release notes, immutable artifact evidence, readiness reviews, or rollback preparation.
7247d agoReviewMountCreate a free account to mount
Framework server plugins and the `/_agent-native/` route namespace. Use when adding a custom server plugin, deciding whether to create an `/api/` route vs an action, or debugging auto-mounted framework routes.
Steady48 mentions in 2 weeks
No other project uses it yet
7.7k5mo agoReviewMountCreate a free account to mount
Guides creation of high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). Covers tool design, authentication, Docker deployment, and evaluation creation. NOT when consuming existing MCP servers (use the server directly).
2711mo agoReviewMountCreate a free account to mount
Guides building a NEW rich-domain MCP server or tool, and auditing an EXISTING one up to a measured reference, using Introspective Context Engineering: discover the domain from live data, name fields so they cannot be misread, deliver guidance where every target client receives it (description head, input schema, response — not the output schema, not past the host's cut), compute determinate verdicts, record provenance per rule, and measure the result. Invoke when asked to add, build, scaffold or wire an MCP server or tool; review, audit, enrich or fix tool metadata (descriptions, inputSchema, outputSchema, field names, alerts, interpretation, summaries); run a data-discovery session against an API (what does this field mean, which fields are null, probe the API); decide where discovered knowledge should be written down; prepare a domain-expert validation session; or measure a metadata change with an eval. Also triggers on "the agent picks the wrong tool", "the agent misreads this field", "the agent ignores the description", user-feedback triage, and tool-call-log pattern analysis.
Guides building a NEW rich-domain MCP server or tool, and auditing an EXISTING one up to a measured reference, using Introspective Context Engineering: discover the domain from live data, name fields so they cannot be misread, deliver guidance where every target client receives it (description head, input schema, response — not the output schema, not past the host's cut), compute determinate verdicts, record provenance per rule, and measure the result. Invoke when asked to add, build, scaffold or wire an MCP server or tool; review, audit, enrich or fix tool metadata (descriptions, inputSchema, outputSchema, field names, alerts, interpretation, summaries); run a data-discovery session against an API (what does this field mean, which fields are null, probe the API); decide where discovered knowledge should be written down; prepare a domain-expert validation session; or measure a metadata change with an eval. Also triggers on "the agent picks the wrong tool", "the agent misreads this field", "the agent ignores the description", user-feedback triage, and tool-call-log pattern analysis.
Generate a complete MCP server project in TypeScript using the MCP TypeScript SDK v2 (@modelcontextprotocol/server) with tools, resources, and proper configuration
4 projects use a version of this
41k22d agoReviewMountCreate a free account to mount
Stateless MCP database server enabling AI agents to query and manage MySQL, PostgreSQL, SQLite, SQL Server, Oracle, and H2 databases without storing credentials
Add and configure custom MCP servers in Docker MCP Gateway. Use when users want to: (1) Integrate their own MCP server into the gateway, (2) Add new servers to catalogs or profiles, (3) Set up server authentication, networking, and configuration, (4) Understand MCP server integration requirements.
179mo agoReviewMountCreate a free account to mount
Use Proxies.sx residential and mobile proxies from any MCP-compatible AI agent (Claude Desktop, Claude Code, Cursor, Windsurf, Cline, Continue). Trigger this skill when the user wants to install, configure or use the Proxies.sx MCP server, get a proxy URL for the Pool Gateway (gw.proxies.sx), check proxy stock per country, hold a session or an IP, rent or renew a Private modem (a dedicated 4G/5G modem with unlimited traffic), top up the balance by card, manage dedicated mobile ports, read usage and pricing, open a support ticket, debug an MCP tool or gateway error, or let an agent pay for proxies with USDC (x402). Also when the user mentions "@proxies-sx/mcp-server", "Proxies.sx MCP", "proxy MCP", PROXIES_API_KEY, AGENT_WALLET_KEY, psx_ keys or pak_ keys.
Design and build a safe, useful MCP server that exposes your app's own data (analytics, funnel, revenue, crashes) to an AI assistant: read-only, least-privilege, AI-consumable. Use when someone asks "how do i build an MCP server for my app", "expose my analytics/funnel to my AI", "make my app's data reachable by Claude/Cursor", "wire an MCP over my backend", or "MCP security best practices". Enforces a security layer (read-only, field allowlist, no secrets in tool output, aggregate-not-row-level) and usability rules (Markdown output, few well-named tools) so the server helps without leaking.
TAK Server API reference covering Missions, Data Sync, WebCOP, Federation, Certificates, CoT (Cursor on Target), and server administration. Load this skill whenever the user mentions TAK, ATAK, TAK Server, CoT events, missions, data sync, WebCOP, or is building any integration that talks to a TAK Server -- even if they just say 'connect to the server' or 'send position data' in a TAK project context. Also load when you see TAK-related paths like /Marti/api/ or references to callsigns, UIDs, or mission packages.
1032d agoReviewMountCreate a free account to mount
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.