- 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.
LLM Os
A private, local-first agentic kernel. The LLM routes intent; sandboxed tools execute. Zero egress — turn your Wi-Fi off and it still works.
Light Weight Ensemble Agent
Budget-native multi-model coding agent with live steering, local Ollama, and trusted MCP tools.
AI Gantry
Long-horizon AI harness you actually own: one static Go binary, one persona, any OpenAI-compat LLM (Ollama, Gemini, Claude, ChatGPT), MCP tools, chat via Telegram/Discord/Slack. O…
Adaptive MCP Fabric
Containerized MCP demo stack with a Node.js backend, static web UI, local MCP tool servers, SearxNG search, and Ollama integration for interactive multi-tool AI workflows.
Claw Deck
Local-first desktop GUI for OpenClaw & Claude Code on your own Ollama - chat, multi-agent council, code map, and a malware-scanned upgrade gate.
Llmesh
Security-first local LLM swarm over MCP with signed peer discovery, fail-closed validation, audit trails, and Docker-based PoC nodes.
Bionic MCP
MCP server exposing local LM Studio (Bionic) models as typed tools
Agentic Studio
Privacy-first AI coding agent for Next.js — runs entirely on your own machine via Ollama, with codebase search/edit, terminal, database, and document tools all gated behind explic…
Evidence Normalizer
men (MCP Evidence Normalizer) — deterministic normalization of MCP tool results into clean, bounded evidence.
Chiezo
AI のための知識ベース。Wikipedia・OpenStreetMap・GeoNames の公式ダンプを SQLite (FTS5) に索引し、MCP と REST で AI に引かせる。AI が書き足せる notes と、Chiezo を道具として引くローカル LLM(agent モード・web 検索)も同梱。
Bigmac MCP
Turn a shared Ollama box into a team resource for Claude Code (or any MCP client): typed local-LLM tools + delegated, read-only repo exploration. Keep your frontier agent on its s…
Omlx Connector
Delegate text work to a local model on oMLX from Claude Code, Codex, and other MCP clients — the content never leaves your machine
Voltage Input MCP
Two-layer local input engine for MCP: an orchestrating model writes a state machine, two small local models chain the inputs at desktop speed.
Windows System Sounds MCP
An MCP server for Windows that plays system sounds and WAV files. Perfect for getting audio notifications from local LLMs in LM Studio.
Localagents
MCP server that delegates Claude Code agent work to local models (llama.cpp / vLLM) on your own hardware
Auto Model Switcher
Parallel model rotation across any CLI. Auto-discovers models, health-checks in <2s, scores by capability+cost, picks the best for every task.
Opencode Ollama Steroids
OpenCode + Ollama multi-agent workflow with builder/reviewer agents, headless runs, skills, validation gates, local session evidence, and redaction tools.
Seashell
MCP server bridging Claude Desktop and Wave Terminal
AgentInterdict
AgentInterdict — runtime enforcement for autonomous AI agents. Trust context. Verify authority. Interdict unsafe action.
Sentinal SRE
A production-grade, multi-agent DevOps orchestration system that detects incidents from live logs, performs Root Cause Analysis, self-corrects its own patches through a cyclic ver…
LLM Agnostic Icm Framework
Model-agnostic ICM framework: a folder structure as agent architecture for Copilot, Claude, Codex, or any CLI
Offload Harness
Delegate summarize/classify/extract/triage to a FREE local Gemma-4 cascade via llama.cpp. Go CLI + MCP server; never calls a cloud model. Includes a turnkey setup skill for Claude…
Llama Launcher
Profile-based launcher for local LLM servers - start, stop and switch models on llama.cpp, Ollama and LM Studio from one CLI/TUI. Zero resident overhead, optional MCP control plan…
AIIA
⌬ AIIA — the memory layer your AI tools should have. Persistent decisions, story-driven workflow, local-first LLM stack. Apache 2.0. Built at Aplora AI.
Tools Ja
Hub repo for Claude Code related tools (Japanese distributions)
Tema Q Agent
A high-performance AI coding agent.
Evidence Gated Scientific Agent
Self-hosted evidence-gated scientific AI with isolated Python/R, independent review, deterministic validation, and complete provenance.
HydraOps
Self-hosted multi-agent AI system with a chat interface. Agents with editable personalities run tasks across API and local LLMs, behind a credential firewall.
Magenticbrain Vllm Aspire
Run microsoft/MagenticBrain (14B) locally on GPU via vLLM (Docker), orchestrated with Aspire + the aichatweb RAG template.
Builder 2
Generic governed local platform for agent-assisted software development. Goose + deepagents + MCP, governed by explicit authority boundaries, HITL gates, and durable artifacts. Ze…
Obsearch
Obsidian semantic search MCP
Localai Code Editor
Free, open-source, self-hosted AI code editor powered by local LLMs (Ollama, LM Studio). Features agentic AI assistant, MCP protocol support, agent skills marketplace, Docker sand…
Gate.cat
Block irreversible AI-agent actions before they run — deterministic, fail-closed action veto for Claude Code, Codex, Cursor, and other tool-using agents.
Dual Mode Conversational AI Assistant
Open-source dual-mode AI assistant for chat and voice, featuring conversational intelligence, multimodal interaction, and productivity-focused automation.
Agent Assembly Line
The simple way to build and embed AI agents into any software stack. Code-native, modular, and LLM-agnostic.
Agentic File Explorer
Local-first AI agent for filesystem tasks: ReAct loop, hierarchical sub-agents, context compaction, git-backed rollback.
LLM Proxy
Local-first LLM orchestrator & agent platform with an OpenAI proxy, guardrails, and Vue 3 UI.
QuirkLLM
Local, GPU-free CLI coding copilot with RAM-aware optimization, RAG, and MCP integration.
BildsyPS
Turn your PowerShell terminal into an AI-powered assistant. Chat with Claude, GPT, or local LLMs. Execute commands, manage files, search the web, and connect to MCP servers.
Organism Memory
Local memory layer for AI agents — persistent, searchable memory across sessions without external APIs
Codedistill
CodeDistill Community Edition — open-core (AGPL-3.0). The full scratchpad→classify→verify→provenance loop; commercial editions add MCP write tools, code anchors, and more.
LLM Ladder
Cascading confidence-gated router across tiered local LLMs — escalates to a bigger model only when self-consistency voting drops below threshold, logging a cost-savings ledger.
Origin Of Memory
Persistent memory for coding agents on Windows — automatic session capture, a nightly knowledge compiler, and FTS5 BM25 retrieval injected into every prompt. Built for Claude Code…
Kibborg AI Assistant
KIBBORG AI Assistant — a modular layered AI agent for coding, algorithmic trading, automation, vision, voice, and local LLM workflows.
K8SHomelab
GitOps Kubernetes homelab with Flux CD, local LLM inference, MCP agent infrastructure, monitoring stack, and self-hosted tooling on bare-metal + Oracle Cloud
Ollama MCP Agent
Universal local AI agent for querying any MCP-enabled data source using Ollama - vaults, databases, emissions data, and more. 100% offline, 100% sovereign.
Kuroshin
Kuroshin OS - fully-local $0-cloud autonomous AI assistant (30B model on 8GB VRAM, MCP-orchestrated)
MASE Agent Memory
Governed white-box memory for LLM agents: every fact carries a mechanically-verified evidence span, every rejected hypothesis is documented. Local-first (SQLite+FTS5), 1000+ tests…
EliteDangerousKB
Autonomous, self-verifying Elite Dangerous knowledge engine + local RAG copilot (COVAS). Grounded-only answers, 100% local inference, built by an AI council.
Haiggoh Codex
Codex-native skills and a publishable bundle for measured changes, MCP verification, and safe local-model offload.