Best AI & LLM Tools MCP servers for Claude Desktop
3,317 ai & llm tools MCP servers with ready Claude Desktop config. Open a row to copy it.
- 1
Enables AI models to perform structured, step-by-step reasoning by writing, revising, and branching thoughts during problem-solving.
npm@modelcontextprotocol/server-sequential-thinkingLocal1 toolTypeScriptOtherConfig for Claude Desktop
claude_desktop_config.json{ "mcpServers": { "sequential-thinking": { "command": "npx", "args": [ "-y", "@modelcontextprotocol/server-sequential-thinking" ] } } }92.1KUpdated Nov 19, 2026Checks score 100 of 100 - 2
Lets an AI client run browser tasks in a real Chrome browser, including fills forms, clicks, extracts data, and downloads files.
PyPIbrowser-useLocalRemote7 toolsPythonMITConfig for Claude Desktop
claude_desktop_config.json{ "mcpServers": { "browser-use": { "command": "uvx", "args": [ "browser-use" ] } } }121.5K7M downloads / 30dUpdated Nov 19, 2026Checks score 80 of 100 - 3PraisonAImervinpraison/praisonai
An open-source AI agent framework that enables running multi-agent teams and workflows locally or via cloud providers.
PyPIpraisonaiLocal1 toolPythonMITConfig for Claude Desktop
claude_desktop_config.json{ "mcpServers": { "praisonai": { "command": "uvx", "args": [ "praisonai" ] } } }9.3K11.5K downloads / 30dUpdated Nov 20, 2026Checks score 89 of 100 - 4
Fetches up-to-date, version-specific library documentation and code examples into an AI coding agent's context.
npm@upstash/context7-mcpLocalRemote2 toolsTypeScriptMITConfig for Claude Desktop
claude_desktop_config.json{ "mcpServers": { "context7": { "command": "npx", "args": [ "-y", "@upstash/context7-mcp" ] } } }65.1K197K downloads / 30dUpdated Nov 18, 2026Checks score 100 of 100 - 5
Lets AI clients search n8n nodes, templates and docs, validate configurations, and build or deploy n8n workflows.
npmn8n-mcpLocal7 toolsTypeScriptMITConfig for Claude Desktop
claude_desktop_config.json{ "mcpServers": { "n8n-mcp": { "command": "npx", "args": [ "-y", "n8n-mcp" ] } } }23.3KUpdated Nov 19, 2026Checks score 100 of 100 - 6
Mocks AI infrastructure including LLM APIs, MCP tools, vector databases, and agent protocols for deterministic application testing.
npm@copilotkit/aimockLocalTypeScriptMITConfig for Claude Desktop
claude_desktop_config.json{ "mcpServers": { "aimock": { "command": "npx", "args": [ "-y", "@copilotkit/aimock" ] } } }1K1.9M downloads / 30dUpdated Nov 16, 2026Checks score 100 of 100 - 7
Provides AI assistants with real-time web search, reasoning, and deep research capabilities using the Perplexity API.
npm@cormac315/perplexity-mcpLocal3 toolsTypeScriptMITConfig for Claude Desktop
claude_desktop_config.json{ "mcpServers": { "modelcontextprotocol": { "command": "npx", "args": [ "-y", "@cormac315/perplexity-mcp" ] } } }2.6K162 downloads / 30dUpdated Nov 16, 2026Checks score 100 of 100 - 8
Turns web pages into clean markdown, JSON, or LLM-ready text and lets AI clients scrape, crawl, search, and extract structured data from websites.
npm@webclaw/mcpLocalRemote12 toolsRustAGPL-3.0Config for Claude Desktop
claude_desktop_config.json{ "mcpServers": { "webclaw": { "command": "npx", "args": [ "-y", "@webclaw/mcp" ] } } }2.4KUpdated Nov 15, 2026Checks score 100 of 100 - 9
Keeps bulky tool output out of a coding agent's context window by running work in a local sandbox and indexing results in SQLite for on-demand search.
npmcontext-modeLocal11 toolsJavaScriptOtherConfig for Claude Desktop
claude_desktop_config.json{ "mcpServers": { "context-mode": { "command": "npx", "args": [ "-y", "context-mode" ] } } }34.1KUpdated Nov 15, 2026Checks score 100 of 100 - 10
Lets an AI client orchestrate swarms of specialized agents, coordinate workflows, and retain self-learning memory across sessions.
npm@claude-flow/cli-coreLocalTypeScriptMITConfig for Claude Desktop
claude_desktop_config.json{ "mcpServers": { "ruflo": { "command": "npx", "args": [ "-y", "@claude-flow/cli-core" ] } } }81.8K991.1K downloads / 30dUpdated Nov 16, 2026Checks score 100 of 100 - 11
Enables AI agents to discover, recommend, and select optimal orchestration frameworks and agentic harnesses based on specific models and tasks.
PyPIagent-harnesses-mcpLocal17 toolsPythonCC-BY-SA-4.0Config for Claude Desktop
claude_desktop_config.json{ "mcpServers": { "best-of-agent-harnesses": { "command": "uvx", "args": [ "agent-harnesses-mcp" ] } } }1.5K644 downloads / 30dUpdated Nov 15, 2026Checks score 94 of 100 - 12
Lets an AI client search, inspect, lint, and install Agent Skills (SKILL.md) from the SkillMD registry.
npmget-skillLocalRemote5 toolsJavaScriptMITConfig for Claude Desktop
claude_desktop_config.json{ "mcpServers": { "skillmd": { "command": "npx", "args": [ "-y", "get-skill" ] } } }1441.1K downloads / 30dUpdated Nov 15, 2026Checks score 100 of 100 - 13
Lets an AI client mock, record, replay, verify and chaos-test HTTP, gRPC and LLM API dependencies.
Dockerdocker.io/mockserver/mockserver:9.4.0RemoteJavaApache-2.0Config for Claude Desktop
claude_desktop_config.json{ "mcpServers": { "mockserver-monorepo": { "command": "docker", "args": [ "run", "-i", "--rm", "docker.io/mockserver/mockserver:9.4.0" ] } } }5KUpdated Nov 20, 2026Checks score 100 of 100 - 14
Lets an AI client run Google searches and return structured JSON with organic results, AI Overview, People Also Ask, news, and shopping data.
npm@hasdata/google-search-mcpLocalRemote5 toolsJavaScriptMITConfig for Claude Desktop
claude_desktop_config.json{ "mcpServers": { "google-search-mcp": { "command": "npx", "args": [ "-y", "@hasdata/google-search-mcp" ] } } }14503 downloads / 30dUpdated Nov 15, 2026Checks score 100 of 100 - 15
Provides a two-layer memory system for AI agents with an immune system to validate and consolidate episodic experiences into long-term identity.
PyPIanneal-memoryLocal5 toolsPythonMITConfig for Claude Desktop
claude_desktop_config.json{ "mcpServers": { "anneal-memory": { "command": "uvx", "args": [ "anneal-memory" ] } } }1231.1K downloads / 30dUpdated Nov 16, 2026Checks score 100 of 100