MCP servers tagged llm
10K live MCP servers tagged "llm", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with llm.
NarrativeForge
NarrativeForge (NF) — 内容契约层：让 AI 稳定产出长内容的协议 + 质量门 + 资产标准｜content contract layer, model-agnostic, spec-driven, MCP-ready
Cosmos
The minimal operating layer for a team building with AI: memory, charter, atlas, lanes, horizon, flares, gate, and slash commands for every agent. pip install cosmos-dev · zero de…
Illusion Forge
AI-driven CAD workbench and coding agent for Windows, evolved from illusion-agent: shared canvas for design discussion, headless 3D preview, SolidWorks-connected real-machine mode…
Adaption Cursor Plugin
Adaption plugin for Cursor — datasets, training, and AutoScientist workflows
Embodied AI Note
ROS2 与具身智能图文笔记
Clawds
Clawds — open-source local AI swarm and multi-agent workspace. An open alternative to OpenAI Dots and xAI Grok Bot, powered by Claude Code and your own models.
Skillstate
O(1) prompt footprint for long-horizon agents. The SKILL.state paper (arXiv:2608.26263) reimplemented — eq. 8 reproduces exactly, 82.5x at 60 files. 100% coverage.
Brainyard
One API for agentic coding CLIs — Claude Code, Codex and Antigravity: status checks, one-shot asks, streamed agent runs with steering, sessions, models and MCP.
Kctx
Turn any Kaggle competition into Claude-ready context — workspace folder, Claude skill, or local MCP server. One curl, one TUI.
OpenNotch
Open-source AI assistant that lives in your MacBook notch, with Ledge, a 3D desktop companion. Native Swift agent, private by design.
Plainsolid
Parametric CAD as a Python file: a browser GUI, a CLI and an MCP server over one engine. Press / to ask a model for the next edit.
Ha Dev Tools
Give your AI coding assistant hands-on access to your Home Assistant instance - the same way it already helps you with code, but for automations, entities, dashboards, and helpers.
Torana Edge
Hook into every step of your AI coding agent: Claude Code, Codex, Gemini or any other. A programmable local proxy: rewrite requests, swap models, transform streams and tool output…
Gittok
开源版抖音信息流 — 用中文刷 GitHub 好项目
WebChatMCP.js
MCP server with a built-in browser: send prompts through the private/temporary chat of ChatGPT, Claude, Grok & Gemini — no chat history, guest use supported. Plugins for OMP, Pi,…
Synthetick Oss
Turn an investment thesis into audited, evidence-backed picks. MIT.
Aispice
AI agent for LTspice circuits: edits schematics, simulates on ngspice, LTspice, Xyce or Spectre, and sizes parts to meet your specs. Desktop app, CLI and MCP server.
Anki For Claude
Anki MCP Server, allows Claude Desktop to create, read and handle Anki Cards
Hce
Middleware memory engine for LLMs — replaces linear chat history with three parallel structures (Entity Graph, Semantic Tree, Focus Buffer) to retrieve only the most relevant cont…
Joyjoy
Self-hosted, multi-tenant AI agents platform built on deepagents, LangGraph & assistant-ui. Bring your own models (Anthropic, OpenAI, AWS Bedrock, Gemini), connect MCP tools, and…
VFagent
V-Fletch：模型无关本地办公 Agent 框架。Node 后端 + Vite/React 前端，SSE 流式工具回合，接入 MCP 工具生态；内置知识库、三级权限与审计留痕；SQLite 本地优先、零云端依赖，一键启动。
Index One Landing Page
Free, local-first meeting notes for macOS. IndexOne records your calls, transcribes them on-device with Whisper, writes structured Markdown notes into your Obsidian vault and answ…
Chronofact
⚡ ChronoFact: 4-Pillar Epistemic AI Backbone. Real-time temporal cutoff calibration, active NLI claim verifier, zero-pollution memory, and mcplex TF-IDF cost optimizer.
Agent Brain Hub
Shared, brain-inspired memory for AI agents: 13 brain regions with awake/sleep loops, a live visualizer, agents connected via REST/SDK/MCP, governance & audit, and business-value…
Freegem
Local bridge exposing the Gemini web session as an OpenAI-compatible API, a Google-native API, and MCP tools, with a guarded web scraper and cited research.
Awesome AI Agent Stack
Curated map of 3,000+ open-source AI agent tools: coding agents, agent frameworks, MCP servers, RAG, memory and local LLMs, sorted by layer and ranked by GitHub stars.
Agentic Finance System
An AI finance assistant that forecasts crypto and stock moves with honest confidence ranges, lets an LLM fact-check every call against the news and tracks its own record in public…
OctopusStudio
Local-first AI workspace for research, documents, data, media, scheduled automation, MCP tools, model choice, and software development.
Mcd Meal Optimizer
麦麦算盘 —— 基于麦当劳 MCP 的营养×预算双目标餐搭求解器 | 麦当劳程序员创意开发大赛参赛作品
Mindfork Rs
A terminal AI chat written in Rust: local models via llama.cpp or OpenAI, Anthropic, Gemini, Grok and OpenRouter in the cloud, with persistent memory, notes, RAG and tools
Accessibility Devkit LLM
Archived experimental accessibility language-model prototype; maintained work moved to Accessibility Devkit
Deepseek Practices
Адаптация Claude Code Practices для opencode/DeepSeek. 13 рецептов, 9 практик, 5 агентов, плагин handoff-injector (~95% доставки). Интерактивный чеклист. Russian.
1context
1Context passively captures what you work on, builds a living wiki for every project you touch, updates as you work, and opens in any browser with a shareable link. Claude Code an…
Qilinclaw
QilinClaw — A self-hosted AI agent platform with a fully visual WebUI. Create agents, connect 15+ chat platforms (Telegram, Discord, WeChat, Feishu...), build RAG knowledge bases…
Orbit App
AI context engine for your codebase. Generate CLAUDE.md, .cursorrules, copilot-instructions.md from project structure — not code dumps.
Model Audit
LLM distillation detection & model fingerprinting via statistical forensics — behavioral probing, stylistic signatures & representation similarity. CLI + MCP ready.
3 Surgeons
Multi-model consensus system — 3 LLMs cross-examine each other to catch blind spots on critical decisions
Tack Guard
Runtime risk scoring for AI agent tool calls. Catch privilege escalation, baseline deviations & exfiltration inline, under 1ms, zero deps, no LLM.
LaunchIQ
LaunchIQ: AI-powered product launch intelligence with a multi-agent pipeline (market intel, personas, strategy, content).
Kortex Memory
Production-grade, multi-tenant memory layer for LLMs and AI coding agents (Claude Code, Codex, OpenCode). Plug it in via MCP and your agents get a shared, durable, scoped, access-…
Jak Swarm
Public-beta AI workflow operator for founder-led teams: plan tasks, route specialist agents, request approvals, and record audit evidence.
AI Agent Pulse
Daily automated tracking of 19 AI agent frameworks. Pulse Score ranks momentum via star velocity, release freshness, commit activity, and community health.
Cubex
A desktop coding agent for any model. Cloud providers and local runtimes, with every change reviewed before it lands.
AI Video Studio
Turn one line of text into a finished, narrated, motion-graphics video. Local-first AI video engine with an MCP agent kit.
AI Engineering Book
AI Engineering: From Software Engineer to Production AI Engineer — a complete textbook with runnable code, six projects and a capstone.
Snapdec
Snap decisions for coding agents — one command, any machine, any agent. Local System One decision layer (MCP + Agent Skill).
OpenGloss
英语四六级词汇的自然辅助阅读，在AI加持下的实时记忆算法，读英文网页时自动标注生词，词汇在真实阅读里自然积累——四六级词汇顺带覆盖，不背单词卡、不打卡、不测验。本地优先：数据全在你机器上的一个 SQLite 文件，零遥测。｜ Passive vocabulary acquisition while reading the web: inline annot…
SpatialOmicsLab
SpatialOmicsLab: an integrated research environment for AI co-scientists in spatial transcriptomics
AI Agent Library
AI Agentを理解から設計・実装・評価・運用まで学ぶ日本語ライブラリ。199記事・16章、APIキー不要のモック対応Pythonサンプル、検索・依存マップ・音声学習を収録。
Yangqiong Agent Harness
泱穹 Agent Harness 是一套用纯 Java 构建的企业级 AI Agent 运行时开发框架，ReAct 循环、六大范式、子代理编排、持久化执行、安全护栏、全链路可观测。