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. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. 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.
-
github.com/inference-gateway/inference-gateway/examples/docker-compose/mcp/time-servergithub.com/inference-gateway/inference-gatewayupdated this year
—
go Apache-2.0 -
A Python-based MCP server implementing causal inference analysis on synthetic customer spending data. Uses DoWhy for causal effect estimation and FastMCP for exposing causal tools. Enables interactive causal analysis with treatment and outcome variables from program signup data.
-
inference-predictor-mcpgithub.com/traction-layer-ai/kpg_predictorupdated this year
MCP server for LLM inference performance prediction — Traction Layer AI
pypi Proprietary -
@inference-casino/mcpactive
MCP server for Inference Casino (inference.casino): AI agents play PvP coinflip, jackpot and poker for real CREDIT on Robinhood Chain.
npm MIT -
@inference-relay/mcpactive
MCP server for inference-relay: 19 IDE tools for financial intelligence, health monitoring, security, and fleet management
npm SEE LICENSE IN LICENSE -
MCP server to fine-tune LoRA, export GGUF, and deploy local LLMs on Onde Inference.
npm -
Docker MCP server for vendor-neutral manufacturing AI inference infrastructure, BOM, sourcing, compliance, and deployment planning
MIT -
MCP server that lets AI assistants (Claude Desktop, Cursor, MCP Inspector) call an image-classification inference API: classify, explain with a heatmap, model info.
MIT -
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 -
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.
Apache-2.0 ★ 16 -
⚡ Ultra-fast O(1) Active Inference & Bayesian Cognitive Governor for AI Agents (Antigravity, Claude, Cursor) & Embedded Systems. Zero-alloc C11 core (<36KB) + FastMCP server.
MIT ★ 5 -
myai-mcpgithub.com/myaitoken/myai-mcpupdated this year
MCP server for the MyAi decentralized AI inference network
pypi MIT -
mollagithub.com/tamnd/mollaactive
Local inference server in pure Mojo. Speaks OpenAI, Anthropic, and MCP. Models are OCI artifacts. Same source runs on CPU, NVIDIA, AMD, and Apple GPUs. Apache-2.0 all the way down.
Apache-2.0 -
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 -
NVIDIA Triton Inference Server control plane — model repository manipulation, VRAM monitoring, and inference over gRPC via FastMCP 3.2
MIT ★ 1 -
skillinfer-mcpupdated this year
MCP server for skillinfer — Bayesian skill inference for AI agents and humans
pypi MIT -
@ebowwa/mcp-modalupdated this year
Modal GPU Cloud MCP server - manage GPU workloads, training, and robot inference
npm MIT -
aigroup-econ-mcpgithub.com/jackdark425/aigroup-econ-mcpupdated this year
Econometrics MCP server for regression, causal inference, time series, panel data, and statistical analysis workflows.
pypi MIT ★ 10 -
MCP Server for HuggingFace inference endpoints with custom LoRA and story generation
npm MIT -
omni-nligithub.com/CogitatorTech/omni-nliupdated this year
A multi-interface (REST and MCP) server for natural language inference
pypi MIT ★ 3 -
MCP server for Agentware: browse and buy agent software, and pay per call for inference, on Robinhood Chain.
npm MIT -
Animica MCP server — chain, AI inference, quantum beacon and mining tools for MCP clients (wraps animica[mcp])
pypi Apache-2.0 -
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
-
parallelix-mcpgithub.com/parallelixnetwork/parallelix-mcpupdated this year
MCP server for the ParalleliX Compute API. Offload parallel inference sub-tasks to a distributed GPU network, paid in $PRLX credits.
npm MIT -
TypeScript type inference and symbol navigation MCP server for Claude Code
npm MIT -
@neuracomputes/mcpupdated this year
MCP server for NEURA Compute — OpenAI-compatible inference that agents can pay for on-chain by burning $NEURA (Base mainnet).
npm MIT -
MCP server for AntSeedStats: the AntSeed AI-inference marketplace on Base (sellers, models, prices, epochs, $ANTS) for AI clients
npm MIT -
typescript-sdkgithub.com/gc4ai/typescript-sdkupdated this year
Type-safe TypeScript SDK + MCP server for gc4.ai — OpenAI-compatible AI inference, paid for with gift cards.
Apache-2.0 -
Profile llama.cpp-family GPU inference, run controlled experiments, and compare results with evidence labels. CLI, MCP server and Agent Skill.
MIT ★ 1 -
Pure Rust AI coordination — MCP server, multi-provider inference routing, local-first LLM orchestration. Sovereign AI for distributed computing. AGPL-3.0
NOASSERTION -
@gns-foundation/hai-mcpupdated this year
GEIANT Hive MCP Server — geospatially-aware AI inference tools for Claude, Cursor, and any MCP client. Every dispatch carries a signed GNS identity.
npm Apache-2.0 -
onlymemes-mcpactive
MCP server for OnlyMemes Stacknet: rent machines (inference, VMs) and pay as you go in SOL or USDC, from any MCP client. Nothing else to install.
npm UNLICENSED -
Agent Skills and an MCP server for GPU performance profiling, benchmarking, optimization, and reporting, with an inference focus.
MIT ★ 4 -
TRINITYIDAIOSgithub.com/Joshua42atkinson/TRINITYIDAIOSupdated this year
Trinity ID AI OS — 12-crate local-first AI agent platform with multi-backend inference routing, MCP server, 24-tool registry, RAG pipeline, and SSE streaming
Apache-2.0 -
TypeScript inferred types, completions and type errors for AI coding agents and type tests: an MCP server, a CLI, and snapshot-test helpers
npm MIT -
GSTD Network MCP server — decentralized inference for Claude Code. Run Llama 3, Mistral, CodeLlama, Qwen, DeepSeek and 50+ open-source models for free, no API key.
npm Apache-2.0 -
MCP server and private mode for coding agents on OffRouter private inference. Every model runs in a GPU TEE, and your prompts are encrypted to the enclave before they leave your machine.
npm MIT -
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 -
🌍 MCP server giving Claude live environmental data: air quality, wildfires, and weather, plus statistical anomaly detection and causal inference (DoWhy) to explain why pollution spikes happen.
MIT -
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 -
hermes-botcoingithub.com/botcoinmoney/hermes-botcoinupdated this year
Native BOTCOIN proof-of-inference mining for Hermes Agent. Plugin + CLI + MCP server + autonomous cron miner. Multi-provider solver (Venice default), EIP-1559 on Base, ERC-8004 reputation.
pypi MIT -
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 -
ppb-mcpgithub.com/paulplee/ppb-mcpupdated this year
Poor Paul's Benchmark as an MCP server. Queryable GPU inference data — quantization, throughput, VRAM, concurrent users — for Claude Desktop, Cursor, Windsurf, Cline, and any MCP client. Self-host or use the free hosted endpoint.
MIT -
Production-grade distributed ML inference platform — FastAPI gateway, Redis-backed worker pool with dynamic batching, WebSocket result streaming, and a live ops dashboard. Serves YOLO, Whisper, RAG and text models, with an MCP agent server and streaming chat.
MIT -
StatsPAI is an Agent-native Python library for causal inference and applied econometrics — unified API, broad cross-method coverage, structured result objects, machine-readable schemas, Skills, an MCP server, and R/Stata parity validation.
pypi MIT ★ 375 -
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
-
synap-mcpactive
MCP server for Synap by Linkrra: OpenAI-compatible inference on self-hosted open models. Chat, live model list, and task tools (summarize a URL, review a diff, extract JSON, describe an image). Pay with an API key, or per call in USDC over x402 (Base or S
npm MIT -
Make your model serve faster on your GPU, and prove it. Skills for Claude Code, Codex and OpenCode, plus a CLI and MCP server: your agent picks and tunes inference engines, can write GPU kernels, and backs every number with client-timed benchmarks, anti-cheat gates and quality checks.
pypi Apache-2.0 -
The all-in-one, airgapped Local AI. Ypipe bundles a high-performance inference engine, specialized models, and pre-configured MCP servers into a single, self-contained Java executable. Zero-dependency orchestration for autonomous agent workflows with 100% data sovereignty. No cloud, no Python hell - just industrial-grade local intelligence.
★ 14 -
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 -
MCP server for automatic Python type inference and checking using Pyrefly
MIT ★ 1 -
MCP server with tools estimating carbon emissions and energy costs associated with LLM inferences
-
peakinfer-mcpgithub.com/Kalmantic/peakinfer-mcpupdated this year
MCP Server for peak AI inference performance. Use with Claude Desktop and Claude Code.
npm -
@ai-gentik/lm-studio-mcpgithub.com/ai-gentik/mcp-serversupdated this year
MCP server for LM Studio local model inference
npm MIT -
Model Context Protocol (MCP) server integrated with an external inference service (e.g., Ollama/Gemma3) via middleware.
MIT -
Security MCP server for coding agents: triage semgrep findings with GMI Inference, with cost shown before every run.
pypi MIT -
io.github.farmmer938-lgtm/af-databridgegithub.com/farmmer938-lgtm/af-m938-1-portfoliono update data
Zero-dependency MCP server: CSV to JSON conversion with type inference, and weighted KPI scoring.
mcpb -
coral-tpu-mcpgithub.com/marc-shade/coral-tpu-mcpupdated this year
Coral TPU MCP Server - Fast local ML inference for agentic systems
★ 1 -
json-mcpgithub.com/hayderhassan/json-mcpupdated this year
Lightweight MCP server for JSON validation, formatting, querying, and schema inference
MIT -
@gpuflow/mcpactive
GPU Flow MCP server — exposes European LLM inference as tools for agents.
npm MIT