MCP Servers
Model Context Protocol servers, independently scored · 60 shown
medusa
MCPAGPL-3.0Pantheon-Security/medusa
Medusa is an AI-first security scanner featuring over 40,000 detection patterns to identify vulnerabilities in AI/ML applications, LLM agents, and codebases. It includes specialized capabilities for detecting repository poisoning, analyzing remote GitHub repositories, and scanning chat or shell histories for leaked API keys.
headroom
MCPApache-2.0headroomlabs-ai/headroom
Headroom is a local context compression layer that reduces LLM token consumption by 60% to 95% for JSON and 15% to 20% for coding agents without losing accuracy. It operates as a library, local proxy, MCP server, and direct agent wrapper to optimize both incoming prompts and outgoing model responses.
Humane-Proxy
MCPApache-2.0Vishisht16/Humane-Proxy
Humane-Proxy is a lightweight AI safety middleware designed to intercept and filter user messages for self-harm ideation or criminal intent before they reach an upstream LLM. It combines heuristic keyword matching, semantic embeddings, and reasoning models to provide real-time risk evaluation, empathetic user care, and operator alerts.
aso-skills
MCPMITEronred/aso-skills
A comprehensive collection of AI agent skills specialized in App Store Optimization (ASO) and mobile app growth, powered by real App Store data via the Appeeky API.
OpenInsider-MCP
MCPMITbtopn/OpenInsider-MCP
OpenInsider-MCP is a Model Context Protocol server that supplies LLMs with free-data investment-research signals including insider trades, SEC filings, short data, and live quotes. It acts as a pure data layer without editorialization or recommendation features.
ai
MCPMITstripe/ai
This skill acts as a guided advisor for configuring Stripe Connect integrations, analyzing user business models, and recommending appropriate payment flows, charge patterns, and account structures.
graphify
MCPApache-2.0Graphify-Labs/graphify
Graphify maps entire project codebases, documentation, and media into an interactive local knowledge graph, enabling AI assistants to query the graph instead of grepping raw files.
DebugMCP
MCPMITmicrosoft/DebugMCP
DebugMCP is a VS Code extension that integrates an MCP server, allowing AI coding agents to control the built-in debugger via the Debug Adapter Protocol.
agents-shipgate
MCPApache-2.0ThreeMoonsLab/agents-shipgate
Agents Shipgate is a deterministic merge gate for AI-generated agent capability changes, analyzing tool sources and configurations locally without agent execution or network calls.
Sibyl-Memory
MCPMITSibyl-Labs/Sibyl-Memory
Sibyl-Memory is a local-first, SQLite-backed agentic memory infrastructure that uses a five-tier hierarchical schema and FTS5 search without relying on vector databases or embedding models.
stock-api
MCPMITzhangxiangliang/stock-api
Fetches real-time quotes, historical K-line charts, and symbol lookups for Chinese A-shares, Hong Kong, and US markets with automatic provider fallback.
telemem
MCPApache-2.0TeleAI-UAGI/telemem
TeleMem is a high-performance, drop-in memory management layer for AI agents offering character-profiled memory and a complete multimodal video understanding pipeline. It serves as an optimized, local-first alternative to Mem0 with enhanced accuracy and lower token overhead.
MeiGen-AI-Design-MCP
MCPMITjau123/MeiGen-AI-Design-MCP
An open-source Model Context Protocol server that integrates multi-provider AI image and video generation into major AI assistants.
obsidian-hybrid-search
MCPMITflowing-abyss/obsidian-hybrid-search
Obsidian Hybrid Search provides local hybrid retrieval combining semantic vectors, BM25 full-text, and fuzzy matching for Obsidian vaults. It exposes this engine through a CLI, MCP server, and native Obsidian plugin.
pi-llm-wiki
MCPMITzosmaai/pi-llm-wiki
Implement Andrej Karpathy's LLM Wiki pattern as a self-maintaining, Obsidian-compatible knowledge base extension for AI coding agents. It compiles raw sources into a structured, multi-layered vault that compounds over time.
better-design
MCPMITmarvkr/better-design
Better Design is an MCP server and design system registry that equips AI coding agents with production-ready design tokens, component styles, and accessibility review rules.
iai-personal-memory-engine
MCPMITCodeAbra/iai-personal-memory-engine
iai-personal-memory-engine (iai-pme) is a local, ambient personal memory engine for AI coding assistants that captures interactions verbatim and serves context via the Model Context Protocol (MCP).
AIHelms
MCPGPL-3.0beizhu-1209/AIHelms
AIHelms is an enterprise-grade AI resource management platform designed to help organizations control costs, track usage metrics, and securely manage AI assets and API access.
OmniRoute
MCPMITdiegosouzapw/OmniRoute
OmniRoute is a unified AI proxy and router supporting hundreds of LLM providers with automatic fallback, advanced routing strategies, and built-in resilience mechanics.
hound-mcp
MCPMITtiluckdave/hound-mcp
Hound MCP is a free, zero-configuration security guard dog designed specifically for AI coding agents to scan dependencies and prevent vulnerabilities. It integrates smoothly across seven major programming ecosystems using public unauthenticated APIs.
QwenPaw
MCPApache-2.0agentscope-ai/QwenPaw
An offline documentation indexing and command assistance skill for the Alibaba Cloud CLI in Chinese, utilizing structured section routing to prevent hallucinated parameters.
LocalAI
MCPMITmudler/LocalAI
Development guide and instructions for AI coding assistants contributing to LocalAI, an open-source self-hosted AI engine.
agentor
MCPApache-2.0CelestoAI/agentor
Agentor is an open-source Python framework designed for building long-running AI agents equipped with durability, observability, and robust security integrations. It supports both the Model Context Protocol (MCP) and Agent-to-Agent (A2A) communication standards.
task-orchestrator
MCPMITjpicklyk/task-orchestrator
Task Orchestrator is an MCP server that provides server-enforced workflow discipline, persistent work item graphs, and quality gates for AI agents.
contextplus
MCPMITforloopcodes/contextplus
Context+ is an advanced Model Context Protocol (MCP) server that provides semantic intelligence, RAG-based code search, AST structural analysis, and Obsidian-style feature linking for large-scale codebases.
browser-search
MCPMITJohell1NS/browser-search
Multi-engine web search and content scraping skill utilizing SearXNG, Camofox, and CloakBrowser for deep AI research.
stock-sdk
MCPISCchengzuopeng/stock-sdk
Stock SDK is a zero-runtime-dependency TypeScript library designed for both browser and Node.js environments to fetch and process real-time and historical financial market data. It includes built-in CLI support and a Model Context Protocol (MCP) server for seamless AI assistant integration.
LiveAgent
MCPMITStack-Cairn/LiveAgent
LiveAgent is a local-first AI agent desktop client and code review skill that uses parallel independent reviewers and evidence-based validation to catch high-confidence defects in pull requests and local changes.
agentic-awesome-skills
MCPMITsickn33/agentic-awesome-skills
Agentic Awesome Skills (AAS) is a comprehensive catalog and core toolset providing local, agent-owned skill stacks for coding assistants.
ECC
MCPMITaffaan-m/ECC
Everything Claude Code (ECC) is a comprehensive production-ready agent harness and plugin system providing dozens of specialized sub-agents, domain skills, commands, and security guidelines.
refero_skill
MCPMITreferodesign/refero_skill
An AI design assistant framework that enforces a research-first methodology using real-world UI, style, and flow references to eliminate generic AI design patterns.
awesome-claude-code-plugins
MCPApache-2.0ccplugins/awesome-claude-code-plugins
Facilitates structured multi-agent discussions and reviews by orchestrating various AI CLI tools to analyze proposals, challenge assumptions, and generate comprehensive decision reports.
agents
MCPMITwshobson/agents
A comprehensive multi-harness agentic plugin marketplace providing production-ready building blocks, agents, skills, and commands from a single Markdown source of truth.
TrendRadar
MCPGPL-3.0sansan0/TrendRadar
TrendRadar is a rapid-deployment trend and news aggregation assistant that filters, translates, and analyzes hot topics from multiple platforms using AI. It pushes summarized insights directly to various notification channels.
ai-engineering-from-scratch-zh
MCPMITfancyboi999/ai-engineering-from-scratch-zh
An interactive assessment tool designed to test students' comprehension of lessons within the 'AI Engineering from Scratch' curriculum using targeted quizzes.
touchdesigner-mcp
MCPMIT8beeeaaat/touchdesigner-mcp
An MCP server that bridges AI models and TouchDesigner, enabling agents to programmatically build, query, and manipulate visual generative projects.
lucid-agents
MCPMITdaydreamsai/lucid-agents
An AI coding guide and architecture overview for the lucid-agents TypeScript monorepo, which provides a protocol-agnostic runtime for building, monetizing, and verifying AI agents.
flyto-core
MCPApache-2.0flytohub/flyto-core
Flyto2 Core is an open-source AI agent framework and workflow automation engine featuring 468 registry-backed modules, browser automation via Playwright, and step-level recipe replayability.
figma-mcp-bridge
MCPMITgethopp/figma-mcp-bridge
Figma MCP Bridge is a plugin and MCP server combination that streams live Figma document data directly to AI tools, bypassing standard Figma API rate limits.
hister
MCPAGPL-3.0asciimoo/hister
Hister is a private, self-hosted search engine that indexes local files and visited web pages for retrieval through a web UI, terminal, or AI assistant.
kordoc
MCPMITchrisryugj/kordoc
This skill generates standardized South Korean administrative documents in HWPX format based on Ministry of the Interior and Safety guidelines. It automatically handles structural rules, indentation levels, administrative markup, and proper text formatting.
relay
MCPApache-2.0dbisina/relay
Relay is a vendor-neutral AI coding agent orchestrator and daemon that rotates coding tasks across multiple AI providers using signed continuation contracts.
LibreChat
MCPMITdanny-avila/LibreChat
LibreChat is a self-hosted, open-source AI chat interface that unifies multiple LLM providers, offering advanced agent capabilities, file analysis, and enterprise security controls.
ai-agent-book
MCPApache-2.0bojieli/ai-agent-book
An open-source technical reference book and companion repository titled 'Understanding AI Agents: Design Principles and Engineering Practice', featuring 10 chapters and 95 hands-on experiments.
agent-bom
MCPApache-2.0msaad00/agent-bom
This repository provides engineering and operating guidelines for developing agent-bom, an open security scanner and self-hosted control plane for AI-era infrastructure.
linkly-ai-skills
MCPApache-2.0LinklyAI/linkly-ai-skills
This skill enables AI agents to search, browse, read, and take notes across local and cloud documents indexed by Linkly AI using either a CLI or MCP tools.
web-researcher-mcp
MCPMITzoharbabin/web-researcher-mcp
An MCP server and research assistant designed to provide verified web search results, full article scraping, and trustworthy citations without hallucinated links.
grepai
MCPMITyoanbernabeu/grepai
Grepai is a privacy-first semantic code search CLI and AI skill that replaces traditional grep with vector embeddings for natural language code exploration.
Adobe_Premiere_Pro_MCP
MCPMIThetpatel-11/Adobe_Premiere_Pro_MCP
Operate local Adobe Premiere Pro projects directly through an MCP server bridge with hundreds of tools for video editing, timeline management, and media ingest.
pattern8
MCPMITAquifer-sea/pattern8
Pattern 8 (P8) is a zero-trust governance framework designed to control AI coding agents by enforcing strict operational pipelines, security guardrails, and deterministic outputs via the Model Context Protocol (MCP).
gini-agent
MCPMITOpen-Curiosity/gini-agent
Development guidelines and operational rules for working with the Gini agent personal agent runtime repository.
figwright
MCPMITawdr74100/figwright
Figwright is an open-source, bidirectional Figma agent for MCP clients that connects an MCP server to a Figma plugin via a local WebSocket relay. It enables AI agents to both read high-fidelity design context and write directly back to the canvas without requiring a paid Figma tier.
skybridge
MCPMITalpic-ai/skybridge
Skybridge is a full-stack TypeScript framework designed to help developers and AI agents build interactive Model Context Protocol (MCP) apps and ChatGPT applications. It abstracts runtime differences so that a single backend server and React frontend can render rich UI views across multiple AI clients.
Wireshark-MCP
MCPMITbx33661/Wireshark-MCP
This skill provides a structured methodology for analyzing network packet captures (pcap/pcapng) using the Wireshark Model Context Protocol (MCP) server. It guides AI assistants through disciplined investigation workflows including triage, security hunting, incident response, and protocol troubleshooting.
bpmn-generator
MCPMITStieges/bpmn-generator
This skill provides autonomous agents and developers with tools to generate, validate, and manipulate BPMN 2.0 XML files and SVG previews from natural language or structured JSON.
mcp-notion-server
MCPMITsuekou/mcp-notion-server
An AI-friendly Model Context Protocol server that bridges AI assistants with Notion workspaces, allowing them to search, read, query, and modify Notion content efficiently.
research-hub
MCPMITWenyuChiou/research-hub
Connects Zotero, Obsidian, and NotebookLM into an AI-operable research workspace with a CLI, MCP server, REST API, and dashboard.
skills
MCPMITlongbridge/skills
Integrates Longbridge financial platform content, real-time news, regulatory filings, community topics, and SEC EDGAR analysis directly into AI coding assistants.
joompulse-skills
MCPMITjoomcode/joompulse-skills
Monitors the aggregate health and performance metrics of a Mercado Livre category using JoomPulse data, offering snapshot generation and period-over-period comparisons.
arifOS
MCPAGPL-3.0ariffazil/arifOS
arifOS is a constitutional governance kernel and operating system substrate for autonomous intelligence that evaluates actions against 13 physical and epistemic floors.