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.
-
@vbotholemu/mcp-llm-inferenceupdated this year
MCP tool for LLM inference — chat completions, text generation, and model listing via L402 API
npm MIT -
MCP server to fine-tune LoRA, export GGUF, and deploy local LLMs on Onde Inference.
npm -
inference-predictor-mcpgithub.com/traction-layer-ai/kpg_predictorupdated this year
MCP server for LLM inference performance prediction — Traction Layer AI
pypi Proprietary -
inference-labs-mcpgithub.com/bosslesss/inference-labs-mcpupdated this year
Model Context Protocol (MCP) server for Inference Labs - adds vendor-neutral LLM routing, model comparison, and live LLM pricing to Claude Desktop, Cursor, Windsurf, and any MCP client.
NOASSERTION -
Temporal inference cost arbitrage for AI agents — defer non-urgent LLM work to cheap-energy hours, track savings, and learn user flexibility. MCP-native. Built for AGI House Hackathon.
MIT -
CPU-only LLM inference engine in pure Rust — 4-bit quantized models, hand-written AVX2 kernels, speculative decoding, and a local HTTP/MCP server. No GPU, no Python runtime.
cargo Apache-2.0 ★ 16 -
diffusion-llm-mcpgithub.com/sandraschi/diffusion-llm-mcpupdated this year
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 sidecar next. Complements local-llm-mcp.
MIT ★ 2 -
Agentic toolkit for building and optimizing high-performance inference engines tailored to your GPU and desired LLM.
pypi Apache-2.0 ★ 48 -
mcpgithub.com/cheapestinference/mcpupdated this year
Remote MCP server for CheapestInference — discover unlimited LLM inference pools, subscribe with USDC on Base, get connected from any MCP client
-
Pure Rust AI coordination — MCP server, multi-provider inference routing, local-first LLM orchestration. Sovereign AI for distributed computing. AGPL-3.0
NOASSERTION -
Tenchi-MCPgithub.com/DovahkiinYuzuko/Tenchi-MCPupdated this year
[ENG] A hybrid cloud/local LLM inference orchestrator via Model Context Protocol (MCP) and Ollama / [JPN] Model Context Protocol (MCP) と Ollama を活用したクラウド・ローカル LLM ハイブリッド推論オーケストレーター
MIT -
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 -
self-evolving CLI for DSPy program management — featuring hot-swap inference, MCP agent interoperability, a Generative Feedback Loop (GFL) pipeline, skills system, llms.txt generation, and full MLflow experiment tracking.
★ 1 -
Loopback-only, OpenAI-compatible inference server in Go that lets coding agents run against a local LLM without source code, prompts, or credentials leaving the machine.
Apache-2.0 -
SharpInfergithub.com/JPaulDuncan/SharpInferupdated this year
A pure C# LLM inference engine built from scratch — no Python, no llama.cpp bindings, no ONNX Runtime. SharpInfer loads GGUF and Safetensors models directly, dequantizes weights in managed code, and runs the full transformer forward pass natively on .NET 8.
MIT ★ 6 -
MCP server for Gate402: pay-per-call agent APIs over x402. Open-model LLM inference, Base trading data, SEC filings and web scraping. 20 tools, free tier, no signup.
npm MIT ★ 1 -
A production-grade Model Context Protocol (MCP) server that augments local LLM inference (via vLLM or Ollama) with real-time external data (e.g., weather, finance, news) to make responses dynamic, accurate, and context-aware. This system is designed for modularity, scalability, and performance in local or hybrid LLM deployments with support for co
-
token-scoutgithub.com/jackccrawford/token-scoutupdated this year
For OpenClaw, Hermes and more. Find free and low-cost inference (LLM models). Use them directly. Provides both a CLI and MCP server that knows which free-tier LLM APIs exist, which ones you have keys for, and which one fits your task. Returns endpoints so can you call models directly. No proxy, no middleware, no latency tax.
MIT ★ 9 -
Benchmark AI model inference speed — like speedtest.net but for LLMs. MCP server with zero telemetry.
MIT -
MCP server for local LLM inference on Ryzen AI Max+ 395 with queueing, deadlines and telemetry; benchmark findings
MIT -
llm-mcp-fastapigithub.com/ahmadalsharef2/llm-mcp-fastapiupdated this year
FastAPI + MCP server for LLM inference — chat API with tool-calling, streaming responses, and model-context-protocol support.
★ 1 -
@gpuflow/mcpactive
GPU Flow MCP server — exposes European LLM inference as tools for agents.
npm MIT -
angruvadalgithub.com/anna-claudette/angruvadalupdated this year
RAM-Backed MCP Memory Architecture for Consumer LLM Inference — 900K token context on 16GB VRAM
★ 3 -
hive-mindgithub.com/tlee933/hive-mindupdated this year
🐝 Distributed AI Memory System with Redis Cluster + MCP + Local LLM Inference
MIT -
MCP server with tools estimating carbon emissions and energy costs associated with LLM inferences
-
io.github.luckyjupiter/occultronno update data
Crypto-paid uncensored LLM inference with signed execution receipts. No account.
oci -
Local-first AI memory system for an Obsidian vault: cited LLM wiki, MCP agent, MoE inference on a 16 GB GPU
MIT -
buyno update data
Pay per request for APIs, compute, browsers, RPC and LLM inference with stablecoins on Celo.
npm -
LuisCore Chorus Field MCP — inference-scale runtime substrate for multi-step agents at LLM labs
npm -
jsonlensupdated this year
MCP server that gives LLMs six tools for exploring arbitrarily large JSON files — schema inference, scoped query, sampling, search/filter, pagination, and statistics.
nuget MIT -
Benchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.
pypi -
@exostream/mcpgithub.com/exostream/exostreamupdated this year
MCP server for Exostream LLM pricing oracle - get real-time inference costs for Claude, GPT, Gemini, and more
npm MIT -
hardware-probegithub.com/yamaru-eu/hardware-probeupdated this year
Expert hardware probe for AI, Gaming, and HPC. Analyzes GPU, VRAM, and Memory Bandwidth to optimize local LLM inference (Ollama) and provide actionable hardware upgrade recommendations.
npm Apache-2.0 ★ 7 -
ace-enginegithub.com/hassekf/ace-engineupdated this year
Architectural Coverage Engine — zero-dependency incremental architectural analysis for Laravel projects. Measures consistency, infers patterns, evaluates security baselines, and exposes an MCP server for LLM integration.
npm MIT -
Icici MCP Server wrapper (No Trade Executions) to integrate with Perplexity or any other LLM for inference and Portfolio rebalancing
★ 1 -
LLM routing proxy for coding harnesses. Auto-routes to cloud or local inference via Bonsai LLM classification. Fallback, prompt rewriting, MCP code review, Signal/Discord Remote Communication
★ 7 -
A Discord bot that answers questions about Google Docs using llms via Groq. Built with a modular, MCP server using Google Docs retrieval from URL, dynamic prompt generation, and LLM inference.
-
Official Model Context Protocol (MCP) server for ModelGate: run LLM inference through the ModelGate gateway and inspect models, usage, cost and request traces from Claude, Cursor, VS Code and any MCP client.
npm MIT -
AI music platform with local LLM inference (Qwen via Ollama) and MCP integration for real-time Claude control.
-
Fully local AI stack in Docker Compose — Ollama LLM inference, SearXNG private metasearch, Firecrawl scraping + real browser automation, and Langfuse observability behind one authenticated gateway with an MCP tool interface. No cloud calls, your data stays on your hardware.
MIT -
@gaki-ai/skillgithub.com/gaki-ai/skillupdated this year
Gaki Marketplace — buy and sell LLM inference access on-chain (USDC). MCP tools + HTTP API skill.
npm MIT -
MCP server forcing evidence-gated, honestly-tiered (FACT/INFERENCE/SPECULATION) claim reporting. Deterministic, no-LLM, MIT.
pypi -
Scenario-driven framework for evaluating demographic bias in single- and multi-agent LLM workflows. Tracks bias across sequential stages, separates model non-determinism from systematic effects, and prevents agents inferring evaluation intent. REST API and MCP server.
MIT -
pch-mcp-servergithub.com/pathcourse-health/pch-mcp-serverupdated this year
MCP server for PathCourse Health (PCH) — drop-in cheaper LLM inference, USDC-based agent payments, and agent identity / reputation lookup. Works in Claude Desktop, Cursor, Cline, Continue.dev, and Zed.
npm MIT -
Self-hosted AI knowledge base with hybrid semantic search (pgvector + FTS + RRF), MCP server, multi-provider LLM inference (Ollama, OpenAI, OpenRouter, llama.cpp), multimodal ingestion (vision, audio transcription, speaker diarization), and knowledge graph. Rust + PostgreSQL.
NOASSERTION ★ 30 -
tuningengines-cligithub.com/cerebrixos-org/tuning-engines-cliupdated this year
Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles p
npm MIT -
Badgr — GPU Compute, AI Model Deployment & Agent Executionno update data
**Run GPU workloads, deploy AI models, access inference APIs, and execute AI agents using Badgr's MCP server.** Badgr is an AI compute and workload execution platform for developers, coding agents, and AI assistants. Run workloads on cloud GPUs or compatible customer-owned GPUs (BYO GPU), with cost controls, execution logs, and verified results. **What can Badgr do?** - **GPU Compute / AI Workloads:** Run Python scripts, machine learning jobs, batch inference, and supported ComfyUI workflows. - **AI Model Deployment:** Deploy and serve LLMs using compatible runtimes such as vLLM and SGLang. Get a verified, OpenAI-compatible inference endpoint. - **AI API / LLM Inference:** Make AI API requests with response validation, supported fallback routing, and bounded execution. - **AI Agent Execution:** Launch coding and testing agents, run tasks, check acceptance criteria, and retrieve execution receipts. **Key features:** Cloud GPU execution, BYO GPU support, model serving, AI agent jobs, workload verification, execution logs, cost limits, and deployment management. Connect Badgr to your MCP-compatible AI assistant to execute real workloads instead of just generating instructions. Get started: https://aibadgr.com **Requires a Badgr API key. GPU workloads and other paid execution may incur usage charges.**
smithery -
MCP research assistant that scrapes provider pricing pages with Firecrawl, stores the extracted plans in SQLite, and answers cross-provider LLM inference price comparisons, with a key-free demo mode. · 基于 MCP 的研究助手:用 Firecrawl 抓取各家 LLM 推理定价页,把提取出的方案写入 SQLite,并回答跨 provider 的价格对比;提供无需 key 的 demo 模式。
MIT -
HIPAA-compliant medical AI agent built with MCP framework, featuring role-based access control and local LLM inference. Demonstrates PHI data masking for doctors vs. unrestricted admin access, with integrated X-ray analysis using TorchXRayVision.
★ 2 -
A research paper discovery and ingestion tool built on top of arXiv, ChromaDB, and FastMCP. Originally developed as a FastAPI backend with local LLM inference via Ollama, then migrated to an MCP server so that an LLM host (like Claude) handles all reasoning.
MIT -
A code graph an LLM can actually use. Tree-sitter across 6 languages, typed ontology with inferred architectural roles, impact analysis, 9 interactive views, MCP server. No embeddings, no vector DB.
MIT ★ 2 -
coreforge-media-mcpactive
MCP server for CoreForge media and local-model services: speech-to-text, document parsing (Granite-Docling), page-to-markdown, translation (MADLAD-400), embeddings and reranking (BGE), LLM inference (Qwen3-8B) and draft image generation (FLUX.1-schnell) —
npm MIT -
Mult-Hands-Eyes-MCPgithub.com/MicroHEROX/Mult-Hands-Eyes-MCPupdated this year
MCP server that gives online LLMs local hands and eyes: OpenAI-compatible local inference (KoboldCpp / Unsloth / llama.cpp / LM Studio / Ollama) for cheap text work and vision work (OCR / image analysis / comparison).
npm MIT -
Zendriver-MCPgithub.com/ShubhamChoulkar/Zendriver-MCPupdated this year
Undetectable browser automation MCP server for LLM agents. Uses Chrome DevTools Protocol to bypass bot detection (Cloudflare, Akamai). Features token-optimized DOM walking (96% reduction vs raw HTML), smart label inference, region detection, CDP network logging, and 35+ tools for building AI agents that interact with the real web.
★ 6 -
This Project uses large language models to automate customer support. It classifies tickets, analyzes content, generate and send responses automatically to the given customer email address. Built with Streamlit and MCP Inspector Tool.
★ 1 -
Multi-backend GGUF vision-language inference engine (moondream3.1 · VideoChat3 · Qwen2.5-VL · MOSS-VL · VideoMAE/ViViT · SmolVLM) with a unified CLI, Web UI and an MCP server for agents.
NOASSERTION ★ 4 -
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 -
Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 30 MCP tools (preview)
pypi MIT -
AI-Inference-Managed-by-AI: Go binary for managing AI inference on edge devices
go Apache-2.0 ★ 19 -
A self-hosted token-completion server for local open models, with chat and completion APIs, SSE streaming, WebSockets, gRPC, MCP and verified setup.
Apache-2.0 ★ 3