- 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.
GemmaM5 1 FullStack
Repeatable and auditable local Gemma 4 26B A4B QAT setup for MacBook Air M5 (24 GB) with vision, reasoning, documents, controlled tools, MCP and local APIs. No model weights inclu…
Little Monkey
Open-source local Agent OS for autonomous AI agents — run local or cloud models with real tools, persistent jobs, sandboxed execution, MCP, and inspectable permissions.
Ollama Client
Lightweight MCP client that uses a local Ollama LLM to query multiple MCP servers defined in config.json
Hirn
Monorepo for Hirn. Hirn is a composable, private, local-first AI agent ecosystem that, by default, runs 100% private natively on your own hardware
Zephyr
uZephyr is a local-first AI sidekick with a primary React control room backed by a FastAPI bridge over the shared Python runtime. The browser UI is the default interface now; the…
Ollama MCP Chat CLI
A terminal MCP chat agent on a free local model (Ollama) with Groq/GitHub fallbacks - implements an MCP Server (tools, resources, prompts) and an MCP client with an agentic tool-…
Raone Aura
The omnipotent, local-first vibe coding engine for your terminal. Powered by Ollama.
Pentool MCP Server
MCP (stdio JSON-RPC) server for Pentool AI — local LLM assistant for pentest: pick checks, bypass WAF, find endpoints. Made for DrXOps/pentool.
Vts Local Orchestrator
Claude delegates code search & file-reading to a free local LLM — so it spends tokens on thinking, not raw output. Local-only.
Minimal MCP Agent Loop
Secure MCP client and agent loop for local LLMs — bridges LM Studio to MCP tool servers with OWASP LLM mitigations
Yachiyo Claw
Open-source Android AI chat, on-device agent, local models, Live2D, Skills, MCP, and Vibe Coding
Glpi Plugin Aiticketanalysis
GLPI 11 plugin: AI ticket analysis via AnythingLLM (RAG, attachment OCR, optional read-only GLPI MCP), running on local models
Opencode Homelab
Local-first AI coding agent stack: OpenCode + llama.cpp + Qwen3.6 with smart context routing
My Agent
Open-source local-first terminal coding agent for DeepSeek, LM Studio, and Agora with MCP tools, resilient long-running workflows, and native memory.
Helix Agent
Extend Claude Code with local Ollama models — autonomous ReAct agent with auto-routing, local benchmarks, and file tools
Aiwatcher MCP
AI news ingestion, distillation, and alert system
Paceforge
Offline-first AI running coach: a local LLM agent that reasons over Garmin and Strava data through MCP.
PlayWright RAG CustomMCP
Take a Jira ticket to a passing Playwright web-UI test, fully local: checks existing coverage, then runs it (env-aware) or authors a framework-standard test and self-heals until g…
Local LLM Delegate
Claude Code plugin that delegates simple, well-scoped tasks to a locally running LLM (Ollama, LM Studio, llama.cpp, vLLM) via MCP
Thmes
Thai Hermes Agentic Shell — agentic terminal UI for local MLX/Ollama models: privacy relay, agentic tools, self-heal, web terminal
F0 Pentest
Offensive-security tools, skills, and MCP servers for local AI agents — privacy-first, small-model-driven. Authorized pentest/red-team companion: 6 MCP servers (27 tools), all irr…
PHP MCP Web Tools
A Model Context Protocol server for local LLMs — runs on shared hosting, zero dependencies.
Caix
caix — native Apple Core AI inference server for Apple silicon (beta): OpenAI/Anthropic API, dashboard, streaming chat with tools/skills/MCP, MTP speculative decoding.
Sfx Lead Intelligence
SFX Lead Intelligence Command Center: local-LLM hub plus lead dashboard, quality lifted 61 to 99 percent via a ground-truth eval harness. Showcase; source private.
WebNav
Local-first open-source browser agent with MCP server, visual workflows, and Manifest V2 support. Self-hostable automation platform connecting to local LLMs via CDP.
Local Model Gateway
Lightweight local AI workstation management for local agents and LLM apps.
Local AI Web
Local web search and rendered web reading MCP server for LM Studio using SearXNG and Playwright.
Knowledge Curator MCP
Local, zero-cost MCP server that fact-checks Markdown/Obsidian notes using a local LLM (Ollama) + free sources (Wikipedia, DuckDuckGo)
Local Fusion
Local OpenRouter-Fusion-style multi-model council: panel + judge + synthesizer over local OpenAI-compatible servers (Ollama/LM Studio/llama.cpp) and/or Pi subscription models. Inc…
Lymerorium Local LLM Debate
Self-hosted heterogeneous LLM debate engine - Gemma on Jetson edge + Qwen + Llama argue in parallel, confidence-weighted voting. +40pp MMLU vs single-model baseline.
Tool MCP LMStudio
MCP server for diagnosing, testing, verifying, and safely controlling LM Studio and local LLMs.
Anjian Agent
Local-first, authorization-gated web security assessment agent with MCP, Claude Code, local LLM support, evidence correlation, and Markdown reports.
Kotys
A private AI agent that runs on your own computer — chat, tools, memory, and tasks, on Ollama (local or cloud) and any OpenAI-compatible server like oMLX.
Apple Fm Bridge
Access Apple's on-device Foundation Models via a CLI, an MCP server, and Apple Shortcuts
Stabbur
stabbur — the Norwegian storehouse for your models: build a local LLM library, then run, chat and serve it with MCP tools. Source-available, proprietary.
Liteagent
A native, single-user, local-model-first AI agent. Works with any OpenAI-compatible endpoint (Ollama, vLLM, LM Studio) — full tool-calling loop, MCP client, memory, scheduler, and…
Localbrowser
Self-hosted web search + page reading for local LLMs. SearXNG + fastCRW over MCP. No API keys, no per-query cost.
CodeBrowser
CodeBrowser with Ollama Integrations
Localgraph
LocalGraph is a zero-dependency CLI tool written in Go that parses repositories into SQLite relationships (Imports, Definitions, Calls). It computes semantic embeddings locally us…
Gitnexus Fleet
GitNexus Fleet is a local runner script designed to aggressively clone down your entire GitHub repository fleet, automatically index all repositories with `gitnexus`, and start up…
Elyxndra Local
Private, local AI chat for macOS & Windows. Run open LLMs (Llama, Qwen, Mistral - any GGUF via llama.cpp, MTPLX on Apple Silicon) 100% offline on your own hardware: no account, no…
Unsloth Local Agent MCP
Unofficial Windows stdio MCP bridge for delegating Codex tasks to local Unsloth Qwen models with aliases, safe progress, cancellation cleanup, bounded continuation, and single-fli…
Jmp Docs MCP
Local-first MCP server and chat app for the JMP 19.1 documentation. Ask in your own words, get the menu path and the steps. Runs fully offline via Ollama.
Rdna4 LLM Stack
Running capable LLMs locally on an AMD RX 9070 XT (RDNA4) with Vulkan, local-Qwen3.6 + Claude workflow.
Hoheit
Vendor-neutral AI orchestration endpoint - OpenAI-compatible, with explainable routing across cloud and local models, YAML agents and MCP tools. Self-hosted.
Ollamancer
Fully-local terminal AI agent for Ollama. 34 tools, MCP, local RAG, deterministic hallucination checks. No cloud, no API keys, nothing leaves your machine.
Neeagent
An advanced, omnichannel autonomous AI agent suite with persistent SQLite graph memory and self-improving ReAct loops.
Signalforge
Offline-first engineering work OS — turn daily work into promotion-ready impact evidence with a local LLM. Native macOS app + MCP server for Claude Code & Windsurf.
SystemOneEngine
High-performance, calibrated non-autoregressive decision engine (<4ms CPU) powering dual-process agent reflexes, Antigravity IDE lifecycle hooks, MCP server, and OS automation.
AI Flight Agent
Conversational flight agent: a local qwen2.5:7b picks a tool, MCP carries the call over stdio to query_flights / buy_ticket / check_in, and those drive a .NET airline API behind a…