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.
CipherScript Unity
Free browser extension that turns DeepSeek, Gemini, Kimi, GLM, Qwen, Arena or Meta AI into a Unity Editor AI agent — create GameObjects, write C# scripts and control the Editor fr…
Fridayy
Turn existing APIs and apps (OpenAPI, REST, Node.js, Laravel) into secure, reviewable MCP tool servers
Baa Ton
An orchestration baton for herding coding agents.
Tinvest MCP
Неофициальный MCP-сервер Т-Инвестиций (T-Invest MCP, Тинькофф Инвестиции) — open-source альтернатива: подключите ИИ-агента к брокерскому счёту. Песочница, риск-лимиты, токен остаё…
Jev Model Router
Pick the best AI model and reasoning effort for any task in ~1s. Plugin for Claude Code, Claude Desktop and Codex, powered by TypeSafe's Jev decision model and live OpenRouter pri…
Vdl MCP
MCP server for vdl — lets Claude and other AI assistants resolve, download and transcribe (Whisper) videos via your self-hosted vdl instance
AI Workflow Advisor
面向国内办公场景的 AI 工具顾问：只读扫描工作区，推荐该装哪些 CLI、MCP 和 Agent，附官方入口、权限说明与卸载方式。
Personal Context Hub
Local-first personal context for any agent. Encrypted vault on-device, MCP pairing, loopback only.
Sight MCP
让只会读文字的 Agent 拥有视觉能力
Seed
Universal AI agent kernel — LLM loop, sessions, memory, tool runtime, cron & webhooks. Build your own agent with Markdown persona.
Agent2llm
Universal Brain x Harness collaboration framework — CLI-first, adapter-first, local-first. 让最强的模型思考，让你顺手的 Agent 干活。
Awesome LLM Agent Protocols
A curated, layer-by-layer guide to protocols and standards for integrating LLM agents, with practical trade-off comparisons.
Wordlive
Drive a running Microsoft Word instance from Python — xlwings, but for Word, and built for LLM agents (CLI + MCP server included).
Zileo Chat
Multi-agent AI chat desktop app built with Svelte 5, Rust/Tauri 2 and SurrealDB. Agent orchestration, Kanban automation, MCP tools, vision and voice dictation. Works with Mistral,…
Cingulater Old
Cingulater is an autonomous AI agent execution engine that self-heals LLM inference streams in real-time to ensure task completion. It features full OpenAI API compatibility and s…
Faradium
A unified memory layer for coding agents - one cross-session knowledge store, shared across Claude Code, Codex & Gemini over MCP. Local-first and self-hostable.
Sakenowa MCP
🍶 The first MCP server for Japanese sake — a flavor-space engine over the Sakenowa open dataset: search, six-axis flavor profile, and flavor-similarity recommendation.
Azure Toolkit
An MCP server exposing Azure Blob, Key Vault, Service Bus, and resources as read-mostly AI tools.
Buildd
Task coordination for AI coding agents. Create or schedule tasks; agents claim them, branch, code, and open PRs. Missions, roles, shared memory, and MCP-native.
Minimalist Agent
An AI Agent for everyday SWE with minimalist style
Aim CLI
One context layer for every AI coding assistant — unified memory, tasks, docs & rules for Claude Code, Cursor, Windsurf, Copilot, Gemini & MCP, from a single source of truth. Zero…
LLM Offload
Claude の軽量な LLM 作業（要約・分類・抽出・簡単な質問）を、ローカルモデルや任意の OpenAI 互換プロバイダ（LM Studio・Ollama・OpenRouter・Grok・OpenAI・Groq・Together…）へオフロードする MCP サーバー | MCP server that offloads light LLM work (…
Openchatci
The localhost AI Agent Runtime -- Chat UI, Tools, RAG, and MCP in one pip install
Recallr
Local-first AI memory for your inbox. Index email + Slack into a single SQLite + vector store; ask questions from your CLI, a web UI, or Cursor / Claude via MCP. 100% on-device, B…
Lumi Installer
Lumi — desktop AI coworker. Optimised for Claude, with built-in Lumi Engine for local + cloud LLMs (Ollama, Gemini, OpenAI, Anthropic), bundled ComfyUI for image/video, and team-m…
Zest Lang
Token-efficient programming language for LLM tool calls; transpiles to Python; ships with MCP server
AI Engine
Self-hostable AI agent platform with visual Studio. Pydantic AI, native RAG (Pinecone), MCP, multi-step workflows.
Context Tax
What your coding agent's context costs you every turn, and which of it you never used.
TokLedger
The local inference ledger -> a zero-dependency OpenAI-compatible proxy that prices every request your home GPU serves: tokens, TTFT, tok/s, kWh, local $ and cloud-equivalent cost.
Sample Governed Agentic Companion
A governed, orchestrator-driven multi-agent builder companion on Amazon Bedrock AgentCore. Safe by construction — never deploys, never leaks a secret, never presents an ungrounded…
Kusiscribe Core
KusiScribe: Local MCP Notary & Memory Fabric for Autonomous Multi-Agent Swarms". (Taquígrafo notarial local y tejido de memoria MCP para enjambres multi-agente)
AI MCP Chat
Desktop-чат (Electron + React) для OpenAI/OpenRouter-совместимых моделей с инструментами по MCP: файлы, браузер, git и что угодно ещё. Source-available.
Belmont
Desktop app for running AI agents on your own files. Eight model providers, MCP servers, per-folder projects, and an approval gate in front of every dangerous action.
Reprise
Deterministic record/replay & time-travel debugging for AI agents. Local-first, MCP-native.
Myterminal
MyTerminal：连接 ChatGPT 聊天模式与本地开发环境的终端桥梁。支持 Actions/MCP 双通道、多会话协作、Skill 工作流、Subagent 委派，全程可审计。
Musegen Lyrics Generator MCP
MCP server for songwriting: multilingual lyrics with English section tags, ready for music generation.
Jh AI Agent
Desktop AI agent that runs entirely on your machine - works with Ollama and any OpenAI-compatible endpoint, sends no telemetry, edits xlsx/docx/pptx with formulas and formatting i…
Spring AI Agent Book
「스프링 AI 2.0으로 배우는 AI 에이전트 개발 완벽 가이드」(위키북스, 2026) 예제 코드. Spring AI 2.0.0 GA, Java 21, 올라마 로컬 모델로 실행.
LLM Agent Harness Survey
模型决定上限，Harness 决定下限：LLM Agent 与 Harness 适配性研究综述 | A Survey on Model–Harness Adaptation (Agent = Model + Harness)
Gauntlet
A CI linter for what your MCP server publishes: tool poisoning and prompt injection across every surface an agent sees, definition drift between runs, and schema rot.
Langchain Poc
LangChain is a measured modern RAG and tool agent built with LangGraph, FastAPI, pgvector, React and assistant-ui. Hybrid retrieval, reranking, calibrated abstention, ACLs, dynami…
Benni Operator Gateway
🤖 Open Source MCP Gateway for AI Operators — connect any LLM to your autonomous agent stack (JARVAS-2, Claude, OpenAI) with approval gates, control plane & hot-reload connector re…
Cct
Reproduction harness, released run (n=144, qwen3:32b), and transcripts for the CCT inference-time probe — curated δ_IT method context vs δ_ref answer-keys — from 'Curated Context,…
Taskforce Docs
Brain OS - the versioned documentation vault behind TaskForce, the AI execution layer for teams that ship. Architecture, ADRs, API contracts, runbooks, security and R&D.
Zokai Station Free
A self-hosted, privacy-first AI workstation. Unifies local/cloud LLMs with your documents, email, and calendar in a single Human-in-the-Loop workspace.
Agent Governance
[DEPRECATED] Moved to microsoft/agent-governance-toolkit
Iapeer
Local background agents on Claude Code and Codex CLI — they message each other, wake on demand, and share one memory.
Minimal Agent
AI agent from scratch in a single Python file: Claude tool-use loop, MCP, long-term memory, sub-agents, lifecycle hooks. Each commit adds one concept. No LangChain.
Deep Claude
Companheiro executável de Deep Claude · O Currículo Executivo do Ecossistema Anthropic
AI LLM Automation Systems
AI/LLM automation reference: RAG, tool calling, human review, evals, observability, safety gates, and local deterministic samples.