- Conduid
- Marketplace
- #local-llm
MCP servers tagged local-llm
463 live MCP servers tagged "local-llm", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with local-llm.
Storytime
A local-first, AI-powered dynamic storytelling platform built in C# / WinForms. Storytime uses a graph database to model narratives as a hierarchy of nodes, driven by a chain of s…
Inferbench
Benchmark local LLM inference speed (tokens/sec) on your own hardware — llama.cpp native + cloud APIs, 124-model catalog, optimal-quant picker, and an MCP serve mode.
NeurOS
Ubuntu 24.04 remix with a local LLM wired into the shell, system tray, editor and an MCP server. No cloud API, no telemetry.
Sous
Stretch your Claude Code Pro/Max plan: an MCP server that offloads small, mechanical coding tasks to a sandboxed local MLX model (Qwen) on your Apple silicon Mac. Hybrid local + c…
Gitee MCP
Gitee (Chinese GitHub) bridge for AI assistants: humming radar & momentum, repo intel, cross-lingual search, zh->en translation via local LLM, watchlist, ecosystem graph, GitHub m…
Modeldock
The home port for your local AI. Zero-install Mac app + MCP server: talk to Claude to discover, download and verify Hugging Face models straight to your own drive. By CAIO Group.
Pi Delegate
Delegate coding work from Claude Code to a local pi agent — MCP tools with mid-run steer/abort, plus per-project discipline hooks.
Open Nuechat
Open-Nuechat: The Lightweight, Agentic Alternative to Open WebUI
AE Agent
Automate After Effects with an AI agent platform that runs any model or endpoint under your control
Scrub MCP
A 22-tool MCP server and CI-ready CLI that cuts cloud LLM token usage on code quality tasks. Deterministic tools handle what they can. A local LLM (via DSPy) handles the rest. Clo…
Local LLM Delegation MCP
Intelligent task delegation for AI agents: Offload the "easy" work to your local machine and save premium tokens for the hard stuff.
Ollama MCP Go
MCP server for Ollama — chat, generate, embed, list models. Pure Go, zero dependencies.
Nft Log Analyzer
AI-powered log analysis MCP server — 100% local via Ollama, auto-files GitHub Issues
Dualrole Pipeline
Autonomous Dual-Role MCP Server: Enterprise Code Auditor & System Architect powered by Local LLMs (LM Studio) with AST Guard & Discord Observability.
MCPedia
Turn any local codebase or documentation folder into a searchable knowledge base that AI tools can use through the Model Context Protocol.
M1K3
Your AI. Your Mac. Nothing leaves. On-device AI companion for macOS — MLX inference, live voice, knowledge graph + RAG, and an MCP server.
HomeFleet
Your coding agent, but your other PCs do the heavy lifting. A per-machine LAN daemon that lets any MCP-capable agent delegate tasks to local models on your other home machines. No…
Podman AI
Podman AI Assistant is a command-line tool that helps you manage Podman containers using plain English. Just type what you want to do—like "list all containers"—and it turns that…
Ollama Local
🧠 MCP + Ollama Local · FastAPI web con chat, tools MCP (sandbox) e historial SQLite. LLMs locales con tool calling sin enviar datos a la nube. 🔒
Ragdoll
Retrieval-Augmented Generation Driven by Offline Local LLMs
Postgres MCP Assistant
An AI-powered PostgreSQL assistant built using the Model Context Protocol (MCP). Supports database metadata exploration, secure read-only SQL execution, and natural language query…
Apfel Harness
Local web GUI harness for Apple Intelligence via the apfel CLI (on-device FoundationModels). Streaming chat with an exact 4k context gauge, JSON-schema constrained decoding, batch…
Chrome Needle
Run a private, offline AI browser agent in Chrome with 18 built-in tools and zero cloud dependencies.
Multi Agent Memory MCP
Local-first multi-agent memory MCP with bounded multi-hop Graph RAG for Claude Code, Codex, OpenCode, Llama, Ollama, and local LLM agents.
Local Vision
Give text-only LLMs (GLM, DeepSeek, ...) eyes. MCP server that reads images and PDFs with a vision model on your own GPU — no API keys, nothing leaves the machine.
Svdb MCP
Local semantic search over your Markdown files, exposed to an LLM as an MCP server. Embeddings run on Ollama.
Agmind MCP
MCP server for measured local-LLM benchmarks from the AGmind claim registry — AMD Strix Halo (Ryzen AI Max+ 395) llama.cpp numbers today, NVIDIA DGX Spark on the bench. search_cla…
VKLP
A research prototype for a model-independent, verifiable shared knowledge layer for local or remote LLMs
Ollama Code MCP
MCP server for delegating coding tasks from Claude Code to a local/LAN Ollama instance (Qwen3)
Averos
Deterministic execution & evolution layer between AI intent and production software — turning structured intent into reviewable, reproducible code. 🔥
Llama Swap
MCP server for hot-swapping llama.cpp models in Claude Code - launchctl (macOS) + systemd (Linux)
Timps
The AI memory layer with 17 intelligence tools — catches contradictions, predicts burnout, tracks relationships. Model-agnostic, self-hosted
AI Calendar Assistant
🗓️ AI Calendar Assistant powered by local LLM (Ollama) + Google Calendar API + MCP
Skill Agents
Personal AI-agent skills, workflows, prompts, and setup guides for local LLMs and MCP-powered assistants.
Marq
Universal cyber assistant: ~80 audited Kali tools + an expert skills library, driven by any model over MCP or direct run
With Qwen And Ollama
Local Model Context Protocol (MCP) execution setup integrating local Qwen models hosted on Ollama with dynamic MCP tools.
Pmem Project Memory Tool For Claude Code
Local-first RAG memory for Claude Code. Semantic search over your project's docs, decisions, and history. No external APIs. Setup in 2 minutes.
Owl Memory MCP
Memory that thinks. Local AI memory with hallucination firewall, 95% token savings, Cloudflare bypass, and P2P LAN bug sharing. 55+ tools. Zero cloud.
Pageindex Local MCP
Local-first MCP server for indexing and querying PDF/Markdown files using PageIndex — no cloud APIs required
Vassal Assistant
Vassal is an AI-powered remote-control assistant for your computer — command it from anywhere by voice or text, and it carries out real actions through thousands of MCP tools.
Owllm
Local-first AI workstation. Run open-weight models, fine-tune, orchestrate multi-agent teams. No cloud required.
Lmstudio Agent
Offline-first coding agent for local LLMs (LM Studio + MCP). Project-aware context, memory, and filesystem tooling for real coding workflows directly in your codebase.
Llmflow Search
LangGraph web research agent for macOS with Ollama
My Tiny Local AI Agent
Local-first chat agent that runs comfortably with small-context local LLMs (from 2B) without losing the original goal of a long conversation. Multi-window context with rollovers,…
Ari VoiceCommand
Open-source Windows AI voice assistant and autonomous desktop agent built with Python/PySide6. Supports wake words, speech-to-text, text-to-speech, local LLMs with Ollama, MCP too…
MyWellWallet
Flutter app: on-device MedGemma, FHIR via MCP, Apple Health + SQLite for private health Q&A and research.
Agents MCP System
Production-grade multi-agent collaboration framework powered by MCP orchestration, Ollama (local LLM), and Streamlit UI
Evidencegene Court
Adversarial autonomous DFIR: Prosecutor/Defender/Arbiter AI court over a typed read-only MCP server. Findings without real evidence refs are structurally rejected. SANS FIND EVIL!…
Swift Mlx Forge
Native Apple Silicon AI workbench for local MLX/GGUF models, adjustable reasoning, visual agent graphs, MCP, and an OpenAI-compatible API.
Molla
Local inference server in pure Mojo. Speaks OpenAI, Anthropic, and MCP. Models are OCI artifacts. Same source runs on CPU, NVIDIA, AMD, and Apple GPUs. Apache-2.0 all the way down.