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.
Chess Coach MCP
Hybrid AI chess coach as an MCP server — local Stockfish + Lichess/Chess.com, personal weakness diagnosis and drills from your own blunders, bilingual EN/KO.
Kowork
Open-source Claude Cowork alternative that gets things done on your desktop.
Typesafe Jev MCP
MCP server exposing TypeSafe's Jev model as a typed evaluate tool.
Office Reporting MCP Kit
Reusable MCP contract, Agent Skill, and Python adapter kit for safe backend-authorized Office report generation and delivery.
Model Studio MCP
CLI and MCP server for Alibaba Cloud Model Studio (DashScope) in stdlib-only Python. 15 tools, no SDK, no venv, and a spend guard that is on by default.
Melete
Superintelligence personal AI that does work you while you sleep. Open source, model agnostic alternative to Muse. Built on Hermes
Loop Engine
Baltor: a reviewed library of skills, AGENTS.md sections, subagents, commands, hooks and protocol server settings that coding agents search and fetch for each step. This repositor…
Treeloom
GraphRAG code search over MCP. Parses code with tree-sitter, weaves a Neo4j code graph, and serves hybrid semantic search to AI agents at lower cost than grep.
Open Bdsg Os
Hệ điều hành doanh nghiệp mã nguồn mở: mô hình ngôn ngữ chạy trên máy của chính công ty, nối vào nền tảng nghiệp vụ qua MCP. Nhân giữ danh tính — quyền — hạn mức — nhật ký. Tiếng…
Local Forge
A fast, local-first desktop workbench for chat, image generation, QLoRA fine-tuning, and MCP-powered workflows.
Kaut
KAUT — Knowledge Actualization Under Trust: self-maintaining, AI-first project knowledge for AI agents. Source-bound docs, git-computed freshness verdicts, a gated write path, zer…
MoodBored
Visual mood-board workspace where humans and LLMs brainstorm together. Any LLM, any IDE, one canvas.
Fintz Harness Kit
Project-agnostic AI agent harness kit with stage machine, loops, memory, and metrics dashboard.
AI Media Stack
Self-hosted multi-tenant AI media platform on one GPU: floor plan → 3D (glTF) → photoreal SDXL shots & 360° panoramas, room-photo declutter & redesign, voice-to-voice translation,…
OpenJarvis
Open-source AI assistant with voice control, vision, and automation (like JARVIS)
DevCouncil
Code intelligence and deterministic verification for AI coding agents: symbol-level code graph, blast radius, dead-code analysis, and MCP servers for Claude Code, Cursor, and Code…
LibreControl
LibreControl — one universal /remote-control for every coding agent you run (Claude Code, Codex, Gemini, Cursor, Copilot, any MCP tool), across all your machines, centralized into…
Open Persona
macOS Desktop AI Chatbot with Character Personas - Gemini/OpenAI Multi-Model
Ah CLI
Daemon-first local runtime for AI agents. Run Claude/Codex agents on your own machine, keep transcripts local, orchestrate multi-agent fan-out, and expose over the A2A Protocol to…
Loopplane
Spec-first, embeddable agent harness runtime - a control plane for loop-engineered AI agents. Governed tool calls through one gateway, one normalized event stream, durable session…
SpaceCode
AI 驱动的智能编程桌面助手 — 编码 / 办公 / 设计三合一（Electron + Vue 3）
SOMA Public
Local memory, context, and trust-boundary layer for cloud LLM coding agents
AI Agent Luodi Shizhan
AI Agent/RAG落地：框架选型、RAG与Eval、MCP、十坑自查与报价锚点；姊妹篇SaaS/MVP外包避坑。
Axl Core
AXL Protocol v3: Universal semantic language for AI agent communication. Deterministic English-to-AXL compression (no LLM, or optional). 7 cognitive operations, 6 subject tags, 75…
Pudding
Local-first desktop AI workspace for macOS—multi-session chat, browser and terminal tools, shared canvas, MCP apps, skills, voice, and bring-your-own models.
ThinkLess
The decision plane for AI agents. Rules and small calibrated models make the routine decisions, the LLM is reserved for the steps that need thought, and every step is traced.
Rag Best Practices
Educational RAG playbook + stdlib Python toolkit: chunking, hybrid search, eval, claim-check anti-hallucination, canaries, citations
BaseDrift
Pre-authorization layer for outbound payments. Holds beneficiary changes whose authorization can't be established, using deterministic rules plus an LLM semantic layer.
Session Browser
Local, private browser for AI coding CLI sessions (Claude Code + Copilot + Codex) — unified search, usage/cost dashboard, resume-from-anywhere, cross-CLI bridge, reasoning trails,…
Compdes Workshop
COMPDES 2026 workshop: securing MCP/RAG AI agents for small businesses. Build, break (Garak, PyRIT, Promptfoo), harden. / Taller de seguridad de agentes de IA.
Chat Sidebar For Opencode
VS Code sidebar chat GUI for a locally installed opencode — multi-session streaming chat, permission approvals, slash commands, @-mentions, todos & native diffs. English/繁體中文 bili…
Helix SDK
Client SDKs for the Agent Execution Protocol (AEP), the wire protocol behind Helix
Nessy
Nessy — an AI agent harness framework for Java
Kiri Gate
A gate in front of your AI agent's tools: acts on what can be undone, asks about what can't.
Rahul Chaube Skills
The most comprehensive open-source AI skills library for LLMs, AI agents, prompt engineering, deep research, and production AI systems.
Comfyui Runpod Agentic Nodes
ComfyUI Runpod Agentic workflow nodes for visually designing, planning, launching, monitoring, and cleaning up typed agent workspaces on Runpod.
Common Sense Skill
One file. 9 questions. Stops AI agents from doing the obviously-wrong thing. MIT. Works with Claude Code, Codex, Cursor, OpenClaw.
The Bureau
Virtual AI agent office — your digital team does your real work
Hitl Support Agent
Production-grade Human-in-the-Loop customer support agent — LangGraph + real Gmail + real Slack + 3 capability-isolated MCP servers + v3↔v4 multi-agent head-to-head eval. Honest a…
Flutter MCP Suite
Production-ready Model Context Protocol (MCP) suite for Flutter & Dart. Headless agent orchestration, shared UI widgets, classic AI agent chat, and dynamic Generative UI (GenUI).
Autonomous Gtm Engine
Enterprise-grade autonomous GTM platform built with LangGraph, FastAPI, Redis Streams, event sourcing, distributed workers, OpenTelemetry, MCP Tool Registry and production resilie…
Everett
One layer above all your AI coding agents: see every session, route work, agents message agents, shared memory, MCP.
Unvara
Private AI that runs on your own computer: a local LLM chat and coding agent for Windows with hardware-aware model picks, one-click downloads and MCP connectors.
Flow Weaver
Durable workflows compiled into TypeScript you own. MCP server for AI-written workflows.
Evo Fall MCP
MCP server (47 tools) turning LLM agents into hardware developers: build/flash/OTA, telemetry self-validation, tool factory, self-evolving plugins | 自进化 AI 硬件能力中枢
Fox Agent
A light coding harness with agent-controlled context. Full machine control, zero permission prompts. 200+ LLM providers, ACP/A2A, plugins, SQLite sessions, TUI + headless.
Awesome Agent Collaborate Tools
A curated list of tools for AI agent-to-agent communication, coordination, and collaboration
Projmap
Python CLI and MCP server for compact codebase maps, symbol lookup, and persistent context for AI coding assistants.
Openviveksha
AI-programmable agent runtime — open spec, typed Canvas & minimal kernel with local MCP
FlashAgent
The coding agent built for local models. One native binary for your terminal that finds the model your local server has loaded, and tells you whether that model can actually drive…