Trending MCP servers for Claude Code

Rank 1. supabase

by supabase

#1

Gives your app a hosted Postgres database with built-in auth, auto-generated APIs and file storage, and the explorer skill helps you build Studio surfaces like SQL snippets, notebooks and query cells.

Rank 2. open-ontologies

by fabio-rovai

#2

Builds, validates and manages RDF/OWL ontologies and knowledge graphs through an MCP server, including SPARQL queries and SHACL validation. Useful for anyone working with ontology or RDF data in Claude Code.

Rank 3. awesome-llm-apps

by shubhamsaboo

#3

Gives you working starting points for AI agents, agent skills and retrieval-augmented generation apps that you can clone, run and adapt to your own project. The examples work with several model providers, so you can switch models without rewriting the app.

Rank 4. appllama

by appllama

#4

Skills for building native-feeling mobile app screens in Expo and React Native, based on patterns from real app screens and flows. Includes a skill for researching those screens through the Appllama MCP before building.

Rank 5. deepagents

by langchain-ai

#5

Gives you a ready-made agent for long, multi-step coding work that can delegate subtasks to sub-agents, manage its own context, keep memory across sessions, and ask you to approve tool calls before they run.

Rank 6. payload

by payloadcms

#6

Gives Claude Code a Payload skill for working with Payload CMS projects, covering collections, fields, hooks, access control and the Payload API, plus commands for dependency audits, CI flake triage, test conversion, UI review, issue triage and translation generation.

Rank 7. editor

by pascalorg

#7

An open-source, local-first 3D building editor built with React Three Fiber and WebGPU. Run it in the browser or from the CLI, and connect AI agents through MCP.

Rank 8. open-computer-use

by ifuryst

#8

Lets an AI agent or MCP client control a computer's desktop apps on macOS, Linux, and Windows through the accessibility layer, without taking over the screen. Use it to automate clicks and typing in apps that have no API.

Rank 9. skill-up

by alibaba

#9

Evaluates Agent Skills, agents and workspaces by running declarative test cases and grading the responses and file changes, with reports produced locally or in CI. It can also inspect failures and improve a skill's test suite from conversation.

Rank 10. ccusage

by ccusage

#10

A command line tool that analyzes Claude Code usage, reading local usage data so you can see how you have been using Claude and what it costs.

Rank 11. gpt-researcher

by assafelovic

#11

Autonomous deep research agent for web and local sources, producing detailed, factual research reports with citations. Available to Codex through an MCP server and a skill.

Rank 12. openreality

by reality-opened

#12

Open Reality: phone video to AI-queryable 3D scenes. MCP tools for Claude/Codex/Cursor (npm openreality-mcp), the self-hostable broker, and the VGGT-SLAM library, in one repo. BSD-2-Clause.

Rank 13. linkedin-mcp-server

by stickerdaniel

#13

Gives Claude Code access to LinkedIn through your own browser session, so it can read profiles, research companies, search jobs, and manage messages and connection requests. An independent open-source project.

Rank 14. typeui

by bergside

#14

Gives your AI assistant design skills, UI prompts and brand kits so the interfaces it builds for websites and apps look more deliberate. It also brings in universal guidance on visual hierarchy, typography and accessibility for design decisions.

Rank 15. oh-my-posh

by jandedobbeleer

#15

A skill for installing, configuring, and troubleshooting Oh My Posh, a cross-platform prompt renderer. It covers shell setup, themes, segments, and Nerd Font icons for PowerShell, zsh, bash, and fish.

Rank 16. supabase-agent-skills

by supabase

#16

Agent Skills to help developers using AI agents with Supabase. Agent Skills are folders of instructions, scripts, and resources that agents can discover and use to do things more accurately and efficiently.

Rank 17. drawio-mcp

by jgraph

#17

An MCP server that lets Claude create and open diagrams, flowcharts, and mockups in the draw.io editor.

Rank 18. amazon-sorftime-research-mcp-skill

by liangdabiao

#18

Gives Amazon sellers skills for analyzing competitor listings, researching product categories and keywords, and mining reviews for pain points and return reasons. Reports are saved as Markdown, so you get a ready-made research write-up instead of collecting the data by hand.

Rank 19. mirage

by strukto-ai

#19

Gives Claude Code a bash-style interface to files and directories mounted from cloud storage, databases, and APIs in one virtual filesystem. Includes skills for working with mounted data and for building custom adapters for new data sources.

Rank 20. agent-governance-toolkit

by microsoft

#20

Provides policy enforcement, zero-trust identity, execution sandboxing, audit trails, and reliability engineering for autonomous AI agents, with commands and MCP servers for Claude Code users.

Rank 21. adobe-premiere-pro-mcp

by hetpatel-11

#21

Lets an AI agent operate a local Adobe Premiere Pro project through MCP, to inspect, edit, verify, and export timelines. Works with Claude Code, Codex, and Claude Desktop.

Rank 22. powercontext

by oceanbase

#22

Gives Claude Code persistent project memory: search, save and inventory project context, hand off work between sessions, agents and people, and review saved candidates.

Rank 23. premiere-pro-mcp

by leancoderkavy

#23

An MCP server that lets AI assistants inspect, edit, verify, save, and export an open Adobe Premiere Pro project, covering rough cuts, timeline assembly, and clip and track changes. Also includes a skill for developing the repository itself.

Rank 24. banana-claude

by agricidaniel

#24

A Claude Code plugin that generates, edits, and compares images with current Google Gemini image models. It covers product and character visuals, reference-based consistency, and text in images, with prompt guidance from a creative director skill.

Rank 25. claude-real-video

by huangchihhungleo

#25

Lets Claude watch videos by extracting scene-aware keyframes and a timestamped transcript from a video URL or local file. Useful for summarizing or discussing video content, which Claude cannot ingest directly.

Rank 26. cocoindex-code

by cocoindex-io

#26

A lightweight code search engine that uses AST-based semantic search with local embeddings and incremental indexing. It helps Claude Code users find code faster and more efficiently.

Rank 27. oh-my-cassette

by cassette-editor

#27

Oh My Cassette is an open-source AI video editing plugin and local MCP server for Claude Code, Codex, Hermes Agent, and OpenCode.

Rank 28. mobilebuildmcp

by getsentry

#28

An MCP server and CLI that gives AI agents tools to build, test, run, debug, and automate UI on iOS, macOS, watchOS, tvOS, and visionOS projects. Includes skills for both the MCP server and the CLI.

Rank 29. mcp-server-mysql

by benborla

#29

An MCP server that gives Claude read-only access to MySQL databases, letting it inspect schemas and run read-only queries. It also supports SSH tunnels, PII redaction and multiple databases.

Rank 30. heygen

by heygen-com

#30

Skills and MCP tools that let an AI coding agent create avatar videos, giving it a digital face and voice so it can send video messages. Works with Claude Code and other AI coding agents.

Rank 31. tunnel-client

by openai

#31

Lets you create, connect, list and inspect secure tunnels that expose a private or localhost MCP server through a local tunnel client. Useful for reaching MCP servers that are not publicly reachable.

Rank 32. seo-audit-skill

by seo-skills

#32

Audits any website for SEO, technical, Core Web Vitals, structured data, security, and AI search readiness using the SEOmator CLI. Returns prioritized reports with health scores across its rule set.

Rank 33. arxiv-mcp-server

by blazickjp

#33

A local MCP server that lets an agent search arXiv, read individual paper sections from the original LaTeX, generate BibTeX entries, and set up topic watches. Papers are stored on disk.

Rank 34. horosa

by horace-maxwell

#34

Lets an AI assistant run real astrology and metaphysics calculations, such as natal charts, predictive techniques and horary readings, on your own machine with no internet needed. Every result comes with a traceable record of how the chart was derived.

Rank 35. kinocut

by kyanitelabs

#35

Guardrailed video editing MCP server for AI agents. FFmpeg, Hyperframes, repurposing tools, Python client, and CLI. Local, fast, free.

Rank 36. cursor-talk-to-figma-mcp

by grab

#36

This project implements a Model Context Protocol (MCP) integration between AI agent (Cursor, Claude Code) and Figma, allowing AI agent to communicate with Figma for reading designs and modifying them programmatically.

Rank 37. unbrowse

by unbrowse-ai

#37

Lets Claude Code search and call websites through Unbrowse's hosted API or MCP, reusing indexed site tools to read pages and run structured web tasks without driving a full browser.

Rank 38. hevy-mcp

by chrisdoc

#38

Lets Claude read, summarize, and log your Hevy workouts, routines, exercises, and body measurements from the terminal or through an MCP connection. Useful for reviewing training history or planning sessions.

Rank 39. ralph-loop

by pageai-pro

#39

A long-running agent loop that works through a software development task list step by step until the list is complete. It includes MCP servers for documentation retrieval and browser automation.

Rank 40. klavis

by klavis-ai

#40

Gives AI agents a way to connect to outside tools and services through MCP servers, so they can act on your accounts and data without you wiring each integration by hand. Also includes a documentation lookup skill that answers questions about libraries and frameworks with code examples.

Rank 41. codspeed

by codspeedhq

#41

Benchmarks and optimizes code for performance using CodSpeed, with CPU-simulated measurements, differential flamegraphs to find regressions commit by commit, and PR status checks. Includes skills to set up benchmark harnesses and to optimize code iteratively.

Rank 42. mcp-email-server

by wh1isper

#42

An MCP server that lets Claude read, search, organize, and send email over IMAP and SMTP. It runs on Windows, macOS, and Linux, and includes a skill for safe email operations and account setup.

Rank 43. microsoft-docs

by microsoftdocs

#43

Gives Claude Code access to official Microsoft documentation, with skills for finding SDK code samples, checking API signatures, and fixing SDK errors. Also includes a skill for building agent skills for Microsoft technologies.

Rank 44. open-bsp-api

by matiasbattocchia

#44

Connects Claude Code to WhatsApp and Instagram Business messaging through the OpenBSP platform, with tools for managing allowed contacts, webhooks and account setup.

Rank 45. railway-skills

by railwayapp

#45

Agent skills that let a Claude Code user operate Railway infrastructure: sign in or sign up, create projects, provision services, databases and buckets, and deploy code.

Rank 46. drawio-skills

by bahayonghang

#46

Creates, edits, and exports draw.io diagrams offline from YAML, covering architecture, network, flowchart, and UML diagrams. Includes an academic overlay for publication-ready figures.

Rank 47. sentrux

by sentrux

#47

Scans a project and grades its structure from A to F across several dimensions such as coupling, cycles, cohesion, dead code, and test coverage. Useful when you want to check code quality and architectural health.

Rank 48. subframe

by subframeapp

#48

Subframe is a UI design tool featuring a drag-and-drop visual editor, React + Tailwind code export, and AI-powered design and prototyping features.

Rank 49. radare2-mcp

by radareorg

#49

An MCP server to use radare2 with AI agents such as OpenCode, Mai, VSCode, Claude, CLION.

Rank 50. refero

by referodesign

#50

Gives Claude Code a design skill that requires reference research before UI, landing page, dashboard, or styling work, plus a read-only MCP connection to Refero's design reference library.

Rank 51. bankmcp

by noskillish

#51

Your AI now reads your bank. Ask it anything about your accounts. Read-only, self-hosted, one user. Standard MCP; tested with Claude and Ollama. BankMCP is not a bank. It is a small open-source server you host yourself (npm package bankmcp).

Rank 52. nteract

by nteract

#52

nteract is a local-first notebook environment where humans, kernels, and AI agents can work with the same live document. It ships as a native desktop app with realtime sync across windows and programmatic clients, and managed local environments.

Rank 53. drawio-mcp-server

by lgazo

#53

An MCP server that lets Claude Code create and edit draw.io (diagrams.net) diagrams through browser automation with Playwright or Chrome DevTools, for developers who want to build diagrams from prompts.

Rank 54. jupyter-mcp-server

by datalayer

#54

An MCP server that lets AI assistants connect to and manage Jupyter notebooks in real time, with kernel status and execution. It can run notebook code locally or on cloud sandboxes such as Datalayer, Kaggle, Google Colab and Modal.

Rank 55. claudexor

by razzant

#55

A local-first control plane that routes coding tasks across Claude Code, Codex, Cursor and OpenCode, choosing the harness and account for each task based on quota and availability.

Rank 57. opentrade

by opentradeoss

#57

The open-source trading harness for Claude Code / Codex agents.

Rank 58. media-pipeline

by guinacio

#58

Generates AI images with Google Gemini or OpenAI's gpt-image model, built into Claude Code for creating visual content for websites and presentations.

Rank 59. codemap

by jordancoin

#59

codemap, structural ground truth for coding agents. Resolves what your code actually imports, tells you what breaks if you change it, and is explicit about what it couldn't figure out.

Rank 60. notebooklm-skill

by claude-world

#60

Automates Google NotebookLM for research: create notebooks from URLs, text, or local files, ask source-grounded questions with citations, run web research, and draft articles. Usable by people in a terminal or by AI agents through MCP.

Rank 61. healthcare

by anthropics

#61

A healthcare plugin with skills for extracting structured data from clinical notes, drafting clinical trial protocols, answering questions across contract corpora, converting documents to text, and building FHIR API endpoints. It also connects hosted MCP servers.

Rank 62. awizemann-harness

by awizemann

#62

A native macOS developer tool that uses an AI agent to drive an iOS Simulator, a macOS app, or a web app, so you can run user-style tests on them.

Rank 63. agenticmail

by agenticmail

#63

Gives each AI agent its own real email address and phone number, so it can send and receive email and text messages and place outbound voice calls without manual setup. Each agent gets an isolated inbox, and outbound messages are scanned so keys or personal data do not leak.

Rank 64. mcp-taiwan-legal-db

by lawchat-oss

#64

An MCP server that lets compatible AI assistants search and retrieve public Taiwanese legal material, including statutes, court judgments and Constitutional Court rulings. Results are not legal advice.

Rank 65. piia-engram

by patdolitse

#65

Local-first AI memory you can see, edit, and override, portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.

Rank 66. data-table-filters

by openstatushq

#66

A React data table system for shadcn/ui with faceted filters, column sorting, infinite scroll and virtualization. Filtering, faceted counts and cursor pagination can run in SQL with Drizzle.

Rank 67. mcp-browser-use

by saik0s

#67

An MCP server that lets AI assistants control a web browser for automation and browsing tasks. Installs as a plugin with a browser-use skill.

Rank 68. memora

by agentic-box

#68

Gives AI agents persistent memory across sessions, with semantic search, a knowledge graph, and document storage backed by SQLite. Load stored context at session start, recall past work, and save important information for later.

Rank 69. codex-mcp-server

by tuannvm

#69

Bridge between Claude and OpenAI's Codex CLI, get AI-powered code analysis, generation, and review right in your editor.

Rank 71. weixin

by m1heng

#71

Bridges WeChat messages into Claude Code through the iLink bot API. Lets you log in by scanning a QR code, check channel status, and manage who can message Claude and how direct messages are handled.

Rank 72. graymatter

by angelnicolasc

#72

An MCP server that gives Claude Code and other AI agents persistent memory, with fact retrieval, checkpointing and memory consolidation to help cut token use.

Rank 73. cross-code-organizer

by mcpware

#73

A dashboard for viewing and managing memories, skills, MCP servers, hooks, and configs across Claude Code and Codex CLI. It also offers security scanning, context budget tracking, and backups.

Rank 74. shodh-memory

by varun29ankus

#74

Gives Claude Code persistent memory across conversations, with local embeddings, semantic search and a knowledge graph. It runs offline as a single binary, with no cloud service or API keys needed.

Rank 75. langserver

by nim-lang

#75

A language server for the Nim programming language that gives Claude Code symbol navigation, references, type resolution, and file and project diagnostics through MCP tools. It also runs as an LSP server for editors.

Rank 76. mcp-for-stata

by sepinetam

#76

MCP-for-Stata is an safety first open-source MCP server and CLI tool with Skills lets any AI agent you use invoke local Stata on your device for regression analysis, econometrics, paper replication, and empirical research.

Rank 77. graph-of-skills

by davidliuk

#77

Gives an agent a small, ranked set of relevant skills for a task instead of loading an entire skill library into its context. It also pulls in each skill's prerequisites, so the agent gets the supporting steps it needs along with the main one.

Rank 78. claude-mermaid

by veelenga

#78

MCP server for rendering Mermaid diagrams in Claude Code with live reload functionality and a built-in skill for expert guidance. Automatically renders diagrams in your browser with real-time updates as you refine them.

Rank 79. dagster-io-skills

by dagster-io

#79

Claude Code skills for building data pipelines and workflows with Dagster, plus an MCP server for accessing a Dagster+ deployment. The dagster-expert skill is deprecated and now ships in the dagster plugin.

Rank 80. connectors

by zapier

#80

A growing catalog of agent-callable tools for the 9k+ apps Zapier integrates with. Each tool is simultaneously an agentskills.io-compliant skill artifact and an MCP Tool-shaped TypeScript module.

Rank 81. magic-compact

by aerovato

#81

Compresses the context of a Claude Code session through a compact skill, aiming to reduce token use without losing information. Built for Claude Code and OpenCode users.

Rank 82. fofamap

by asaotomo

#82

Lets Claude Code validate FOFA search syntax, query and profile internet assets, and export bounded results. Scan plans are generated first and run through Nuclei only after one-time human approval of targets, templates and severity.

Rank 83. rustunnel

by joaoh82

#83

Exposes local services through secure tunnels, giving public HTTPS, TCP, or UDP URLs for testing webhooks, demos, and deployments. Built in Rust and billed pay-as-you-go.

Rank 84. episodic-memory

by obra

#84

Semantic search over past Claude Code conversations, so a session can recall earlier discussions, decisions, and patterns. It adds a remembering-conversations skill that checks prior sessions before the assistant says it doesn't know.

Rank 85. entroly

by juyterman1000

#85

Reduces AI context cost for coding agents by compressing context in a way that can be reversed, with byte-exact recovery and an auditable receipt for each reduction. Runs locally and works through a proxy, MCP server, SDK, or agent wrapper.

Rank 86. chainlink

by dollspace-gay

#86

A simple, lean issue tracker CLI designed for AI-assisted development. Track tasks across sessions with context preservation.

Rank 87. qveris-agent-toolkit

by qverisai

#87

Bring professional data and tools to the AI you already use: open-source MCP, CLI, SDKs, skills, and docs to find services, call them, and audit usage.

Rank 89. excalidraw

by edwingao28

#89

Diagram with your agent. Stay in control. Use Claude Code or Codex to edit an existing Excalidraw diagram. Review what changed, keep drawing in the same workspace, and export a native file you can keep editing.

Rank 90. omem

by ourmem

#90

Gives Claude Code persistent shared memory it can store, search and recall across sessions, with Space-based sharing between agents and teams. Available cloud hosted or self-deployed.

Rank 91. automatelab-tech-n8n-mcp

by automatelab-tech

#91

An MCP server for n8n that gives Claude, Cursor, and other AI agents tools for generating workflows, linting, diagnosing failed executions, and driving live n8n instances.