Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
Quota-aware, read-only Figma tooling for MCP clients, terminals, and code-generation workflows.
MCP server for . Index your codebase once, then search using natural language.
Qwen3-30B-A3B-Thinking via OpenRouter plus multi-source web synthesis with citations.
icloud-mcp covers seven Apple services with two interchangeable backends, and as far as we know it is the only MCP server that does.
MCP tools for Roaming RAG
MCP server for Canadian government data — 266 bilingual tools across 9 federal, 7 provincial & 2 municipal open-data APIs (Bank of Canada, StatCan, weather, recalls, drugs, immigration,...
One of the strange design decisions Anthropic made was depriving Claude of timestamps for messages sent by the user in claude.ai or current time in general. Poor Claude can't tell what time it is!
newsmcp.io • integrations • REST API
A MCP server that connects to Stakpak API.
between your team and your AI coding agents. Define your rules once. Enforced everywhere. Every session.
MCP server + Chrome extension that gives AI agents control of your real browser with existing sessions and logins
Give an AI agent hands-on control of Blender: build geometry, apply materials, render, and check that a mesh is printable — 98 tools over the Model Context Protocol.
Agent Skills
micro-agent orchestrator for local agents
你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.
Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
Curated guidance for AI assistants building MapLibre applications — covering ecosystem and open-source best practices.
Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot,...
Public repository for Agent Skills
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills...
Generate draw.io diagrams from natural language — 11 presets (UML, SysML/MBSE, BPMN, network, C4…), 39 tools: codebase/CI/infra-to-diagram, image→editable diagram, Databricks product icons, mind...
The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞
adds freshness decay (time-weighted memory), claim verification (verify_file_path MCP tool), 12 MCP tools (was 8), and 30+ bug fixes.
Qiushi-Skill: Build agents that investigate first, focus on the main contradiction, validate in practice, and keep pushing until the work is actually done.
首先感谢 Andrej Karpathy 的《LLM Wiki》原文。这个项目直接受那篇 idea file 启发而来。