- Conduid
- Marketplace
- #llama-cpp
MCP servers tagged llama-cpp
109 live MCP servers tagged "llama-cpp", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with llama-cpp.
Tabletalk
Ask a SQLite database questions in plain language. Local LLM agent with tools, evals and an MCP server.
Prax
Self-hosted personal knowledge base: bring in what you read, collect and write — papers, manuals, web pages, chats — then search it, ask it, see how it connects, and let your too…
AIDesktopStudio
Agent-drivable generative creation studio on the desktop: 310 MCP actions across 26 families cover everything the interface can do. Local models on the machine — GGUF LLMs, offlin…
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.
Local LLM Orchestrator
Private OpenAI-compatible orchestrator for llama.cpp multi-model routing, prompt improvement, MCP tools, and Skill-Agents workflows.
TextWren
Translate, fix grammar and dictate in any macOS app. ⌘C twice for a popup, fn⌃ to talk; cloud models or fully on-device.
Airlocked Agents
Deterministic IaC for a private, self-hosted AI automation stack — untrusted content stays in the airlock.
Celula Madre
Autonomous AI Stem Cell: A self-evolving agent framework with on-demand terminal differentiation, invariant testing, and Docker sandboxing
Docent
Docent: your private AI assistant. Chat with your PDFs and Office files, search the web and connect MCP servers, running on your own machine.
Local LLM MCP
本地模型管家 MCP：管理 GGUF 模型与 llama-server —— 模型台账 / 显存估算 / 服务生命周期 / chat 代理（FastMCP）
Diffusion LLM MCP
FastMCP fleet MCP server for diffusion LMs (dLLM). DiffusionGemma on Goliath RTX 4090 — batch inference, HLE-shaped reasoning, ~200–400 tok/s. Doc phase; llama-diffusion-cli sidec…
Morgan
Self-hosted, self-learning, provider-agnostic personal agent kernel. Local-first memory in one SQLite database, project-scoped, reachable from any tool over MCP or a CLI.
Llauncher
llama-server model endpoint manager with JiT swapping with human UI, MCP and pi extension support.
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.
Web Search Addon For Offline LLM
RAG + offline MCP Server for llama.cpp and LM Studio | web search during Iran internet disruptions
Bayes Execution Engine
A deterministic Plan-and-Execute multi-agent orchestration engine using LangGraph and MCP, integrating Bayesian probabilistic modeling (pgmpy) to eliminate hallucination loops and…
Sphaera Context Engine
Evidence-first local context engine for AI agents - durable project memory for code, documents, and model-adaptive ContextPacks.
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…
Llama Server Memory Local
MCP memory service for llama-server
Llama Swap
MCP server for hot-swapping llama.cpp models in Claude Code - launchctl (macOS) + systemd (Linux)
Owllm
Local-first AI workstation. Run open-weight models, fine-tune, orchestrate multi-agent teams. No cloud required.
Swift Mlx Forge
Native Apple Silicon AI workbench for local MLX/GGUF models, adjustable reasoning, visual agent graphs, MCP, and an OpenAI-compatible API.
Local Swarm MCP
MCP server that delegates mechanical tasks to local OpenAI-compatible inference backends (llama.cpp, Ollama, etc.) and provides context-management tools (compaction, scratch store…
Llmesh
Security-first local LLM swarm over MCP with signed peer discovery, fail-closed validation, audit trails, and Docker-based PoC nodes.
Mata Kadalz
A local Vision MCP server for any MCP client, using Qwen3-VL through an external llama-server. One secure image-inspection tool over stdio or Streamable HTTP.
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.
Cancerbero
Local, offline-first GGUF and llama.cpp pre-load inspector
Localagents
MCP server that delegates Claude Code agent work to local models (llama.cpp / vLLM) on your own hardware
ThreadShelf
Archive, search, and continue AI conversations from multiple platforms in one private, local-first workspace.
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…
Nanos
Lightweight, process-isolated WebAssembly micro-runtime for sandboxed AI agents with native GPU (Metal & CUDA) offload
Tema Q Agent
A high-performance AI coding agent.
Verbative Dist
Release binaries for Verbative — voice control and a fully-local memory engine for the Claude Code CLI in VS Code. Hosts the on-device artifacts the extension and the verbative-me…
LLM Proxy
Local-first LLM orchestrator & agent platform with an OpenAI proxy, guardrails, and Vue 3 UI.
HeyBuddy
Local-first Windows AI assistant built with .NET and WPF, with voice, vision, app control, memory, MCP connectors, and approval-gated agents.
Kuroshin
Kuroshin OS - fully-local $0-cloud autonomous AI assistant (30B model on 8GB VRAM, MCP-orchestrated)
Voidtalon
[Mirror of https://git.mzte.de/LordMZTE/voidtalon] LLM Chat TUI that sucks less while still being feature-rich
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.
Hecker Lab
Llama.cpp based agentic playground for everyday work
Opencode Homelab
Local-first AI coding agent stack: OpenCode + llama.cpp + Qwen3.6 with smart context routing
FormicOS
AI kernal/api/ui multi-agent orchestration
Quantize Gguf MCP
MCP server for quantizing Hugging Face models to GGUF via llama.cpp — powered by QuantizeLab
Local Model Gateway
Lightweight local AI workstation management for local agents and LLM apps.
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.
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.
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…
Rdna4 LLM Stack
Running capable LLMs locally on an AMD RX 9070 XT (RDNA4) with Vulkan, local-Qwen3.6 + Claude workflow.
HEngram
High-Performance Knowledge Graph MCP Server (Haskell + C++ Supervisor)
Qmd Openclaw Kit
Reusable OpenClaw integration kit for upstream QMD with bilingual docs, backend wrappers, MCP templates, and collection bootstrap scripts.
LocalKnowledgeTerminal
Local-first, privacy-preserving multilingual knowledge cards grounded in cited books on your own hardware.