MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
iflow-mcp_run-llama_llamacloud-mcpupdated this year
Expose LlamaCloud services as MCP tools
pypi MIT -
llama-mcp-servergithub.com/ahays248/llama-mcp-serverupdated this year
MCP server bridging Claude Code to local llama.cpp
npm MIT -
MCP memory service for llama-server
MIT -
—
go mit -
llamas-mcpupdated this year
LLamas AI OS — MCP server for shared memory, skills, and orchestration across AI agents
npm MIT -
llama-mcp-servergithub.com/oloruntoba-madamori/llamacloud-mcpupdated this year
MCP server for document parsing with LlamaCloud multimodal understanding
pypi MIT -
A MCP server connecting to a managed index on LlamaCloud
npm MIT -
llama-herdgithub.com/JakeAve/llama-herdupdated this year
MCP server for Ollama agents
-
A Model Context Protocol (MCP) implementation with weather tools server and Claude & LLaMA integration.
-
MCP server bridge for Claude and llama.cpp - Connect Claude Desktop to your local models
npm CC0-1.0 -
Workspace CLI, Web agent workbench and local MCP tools service
npm MIT -
llama-mcpgithub.com/DaWasteh/llama-mcpupdated this year
🔌 Zwei getrennte MCP-Server für llama.cpp: gehärteter Dateisystem-Zugriff und sichere Internet-Recherche (DuckDuckGo, Wikipedia, arXiv)
MIT -
llama.cpp's llama-server + Web UI, compiled natively for your exact CPU/GPU in Docker, with a hardware guard and private local web search (SearXNG + MCP).
MIT ★ 2 -
MCP stdio server for Windsurf that routes tool calls to a local llama.cpp llama-server (GGUF), optimized for low-VRAM GPUs.
★ 1 -
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 plane, importable as a Go library.
MIT ★ 2 -
mcp-llama-swapgithub.com/oussama-kh/mcp-llama-swapupdated this year
MCP server for hot-swapping llama.cpp models in Claude Code - launchctl (macOS) + systemd (Linux)
pypi Apache-2.0 ★ 5 -
Python cli tool using mcp protocol and llama-8b using groq api to calculate roots of a quadratic eqn.
-
llama-index-tools-ejentumgithub.com/ejentum/llama-index-tools-ejentumupdated this year
LlamaIndex tool spec for the Ejentum Reasoning Harness. Wraps the hosted Ejentum MCP server and exposes 8 tools (4 harnesses × dynamic + adaptive).
pypi MIT ★ 1 -
Open WebUI + Ollama + servidor MCP em Go (via MCPO) com tool calling de calculadora em Docker Compose.
MIT -
Zambo tools for LlamaIndex: tools behind one MCP endpoint (https://zambo.dev/mcp), a verifiable AER-1 receipt for every job, and HANDOVER continuity across AIs.
pypi mit -
Contract-driven coding workflow: the strong model plans and accepts, your local LLM does the coding. 25 MCP tools + 6 skills, 8 agent hosts (ZCode, Claude Code, Codex, VS Code, DSH, pi, omp, opencode). Local-first, no telemetry.
MIT -
llama-server model endpoint manager with JiT swapping with human UI, MCP and pi extension support.
★ 2 -
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.
MIT -
TranslateGemmaMCPgithub.com/woheller69/TranslateGemmaMCPupdated this year
MCP server and WebUI for TranslateGemma running via llama.cpp
MIT ★ 3 -
ocr-mcpgithub.com/aovestdipaperino/ocr-mcpupdated this year
MCP server that transcribes screenshots with a local GLM-OCR model via llama-server
cargo MIT -
llamacpp-mcpgithub.com/lukasmki/llamacpp-mcpupdated this year
An MCP (Model Context Protocol) wrapper for running local LLMs using llama-cpp-python
MIT ★ 4 -
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)
MIT -
maldroidgithub.com/yayaya142/maldroidupdated this year
Local MCP-enabled CLI for secure, static-only Android artifact investigation with llama.cpp
MIT -
Strata 125B MoE + JEV mode: llama.cpp fork with parallel-decision endpoints (yes/no in ~10ms), an MCP server, and a llama-swap router swarm for Claude Code & DeepSeek Harness.
MIT ★ 1 -
locogithub.com/ilovepixelart/locoupdated this year
MCP server for local LLMs — Ollama, LM Studio, llama.cpp
MIT -
Native Mac resources behind one MCP endpoint: Metal rendering, CoreML, VideoToolbox, llama.cpp.
Apache-2.0 -
MCP server that delegates Claude Code agent work to local models (llama.cpp / vLLM) on your own hardware
MIT ★ 19 -
llamaai-mcpgithub.com/rocnubie/llamaai-mcpupdated this year
Llama AI (llamaai.online) is a browser-based chat workspace built around Meta's Llama 4 family of models, with Llama 4 Maverick available by default.
MIT -
CLI + MCP server for the Llama Ventures investment workbench (command.llamaventures.vc).
npm MIT -
Локальный OCR на GPU: llama.cpp + GLM-OCR. Горячая клавиша, трей, фоновая модель, MCP-сервер. Windows
-
MCP server for Llama project management - connect Claude to your agile workflow
npm MIT -
searxng-mcp-bridgegithub.com/designcomputer/searxng-mcp-bridgeupdated this year
Minimal SearXNG->MCP streamable-HTTP bridge for the llama.cpp WebUI
MIT ★ 7 -
Profile llama.cpp-family GPU inference, run controlled experiments, and compare results with evidence labels. CLI, MCP server and Agent Skill.
MIT ★ 1 -
codeindex.mcpgithub.com/mishkidreams/modelcontextprotocolupdated this year
MCP server for semantic code indexing with Qdrant and llama.cpp. Provides tools for indexing Git repositories and semantic code search.
nuget MIT -
moltbook-sentiment-mcpgithub.com/julybrian-art/moltbook-sentiment-mcpupdated this year
MCP server for real-time crypto sentiment from 2M+ AI agent discussions. Powered by Llama 3.1 8B.
-
Domain-pluggable LLM agent runtime with tool permissions, human approval, MCP server, and a repeatable eval harness. Local models (llama.cpp) and hosted APIs.
MIT -
A compiler for the code AI agents write: a flat SSA language with JSON diagnostics, compiled in under a millisecond to sandboxed native code, as MCP tools. Its Llama 3.2 1B prefills 1.7-2.4x faster than llama.cpp.
Apache-2.0 ★ 1 -
web-search-addon-for-offline-llmgithub.com/Fateh-Studio/web-search-addon-for-offline-llmupdated this year
RAG + offline MCP Server for llama.cpp and LM Studio | web search during Iran internet disruptions
NOASSERTION ★ 1 -
MCP server for fetching real-time documentation from Langchain, Llama-Index, OpenAI, UV, and Qubrid using web search
npm MIT -
Universal context governor for local-LLM agent CLIs: an OpenAI-compatible proxy + MCP server that keeps context bounded in front of llama-server.
MIT ★ 7 -
Universal AI skill compiler + MCP bridge. Write once, run across ChatGPT/Codex, Claude, Gemini, DeepSeek, Meta/Llama and browsers.
mcpb MIT ★ 1 -
ai-security-gatewaygithub.com/etho0/ai-security-gatewayupdated this year
Hybrid AI Security Gateway — rule-based + LLM-assisted (Nemotron + Llama) prompt injection detection + MCP security (rules+policy+AI Assisted)
MIT ★ 2 -
Serve, size and benchmark open LLMs on one 16 GB GPU: vLLM vs llama.cpp vs Ollama, KV cache and offload planning, MCP server
MIT -
Ts RAG system. ingest documents, creates embeddings, stores in pgvector and query through cli or mcp server. fully local with node-llama-cpp
★ 1 -
MCP server for AWS Bedrock - text, image, video, and embeddings across Claude, Llama, Mistral, Nova, Qwen, DeepSeek, GPT-OSS and more
npm MIT ★ 3 -
llm-stackgithub.com/KI7MT/llm-stackupdated this year
Local LLM + 42 ham radio MCP tools in a browser — Docker Compose reference stack (Open WebUI + llama.cpp + qso-graph MCP servers)
-
@antarose/mcp-visionstale
🔍 MCP server for image analysis using Cloudflare Workers AI (Llama 3.2 Vision) - Analyze images with structured JSON output
npm MIT -
@pinghuachiu/mcp-visionstale
🔍 MCP server for image analysis using Cloudflare Workers AI (Llama 3.2 Vision) - Analyze images with structured JSON output
npm MIT -
Local MCP server exposing the Cloudflare Clef-Flash decision model to AI agents — structured decisions with probability outputs, fully offline via llama.cpp.
npm Apache-2.0 ★ 8 -
Question answering over your documents with cited sources: FastAPI + SSE, retrieval over MCP (cMCP + cRAG), local LLM via llama.cpp, evaluation gated in CI
MIT ★ 1 -
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.
MIT ★ 2 -
KINDXgithub.com/ambicuity/KINDXupdated this year
Local-first hybrid cli search engine (BM25 + Vector) for personal knowledge bases and agentic workflows. Runs entirely on-device via node-llama-cpp.
npm MIT -
recon-intelgithub.com/Usamaaa824/recon-intelupdated this year
AI competitive intelligence agent — LangGraph multi-agent system with 4 MCP servers, Groq Llama 3.3 70B, FastAPI SSE streaming, and Next.js dashboard
-
Agente LLM local e Servidor MCP em Python (Anthropic MCP SDK + llama.cpp nativo Windows) com sandbox de segurança, rotinas YAML e bateria de avaliação contra prompt injection
-
MCP server that delegates mechanical tasks to local OpenAI-compatible inference backends (llama.cpp, Ollama, etc.) and provides context-management tools (compaction, scratch store, token estimation).
MIT ★ 1