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.
-
Exposes the PyMDP active-inference library to AI agents and applications over the Model Context Protocol and a plain REST API: build generative models, infer states and policies, and simulate agents in environments
MIT ★ 3 -
genie-lockergithub.com/nhantour/genie-lockerupdated this year
Read-only MCP connector and public API for quality-gated, ephemeral private AI inference.
MIT -
bridgenode-mcpgithub.com/applefanaimail-blip/bridgenode-mcpupdated this year
BridgeNode — AI inference without API keys. Pay per request with Solana USDC via x402 (alias for the bridgenode toolkit).
pypi MIT-0 -
Claude Code and Codex plugin for deeplit: manage GPU inference instances, volumes, models and billing from your coding agent, authorized by a scoped API key.
Apache-2.0 ★ 2 -
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 -
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 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 -
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 -
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 -
openrouter-admin-mcpgithub.com/oviron/openrouter-admin-mcpupdated this year
MCP server for the OpenRouter management API — credits, inference-key CRUD with daily/weekly/monthly reset & expiration, activity drill-down (by_model/day/provider/key), one-shot dashboard.
npm MIT -
k402-mcpgithub.com/kali123411/k402-mcpupdated this year
MCP server for the k402 agent-payable API catalog on Kaspa — text tools, chain data, GPU inference, covenants, and zk attestation, paid per call in KAS with no account or API key
pypi MIT -
MCP server for RVC WebUI — voice training, inference, model management, vocal separation via Gradio API (12 tools)
MIT ★ 1 -
Local-first MCP server: 17 AI tools + 5 system endpoints for Claude & Cursor, powered by Ollama — all inference on-device, no API key, no data egress.
MIT -
MCP server for LightningProx: pay for AI inference with Bitcoin Lightning. No API keys. Pay per request in sats. 24 models across 5 providers.
npm MIT -
k402-mcpgithub.com/Kali123411/k402-mcpupdated this year
MCP server for k402 agent-payable APIs on Kaspa — text tools, chain data, GPU inference, covenants-as-a-service, and RISC Zero zk attestation, paid per call in KAS/BTC/LTC/DOGE/BCH/DASH/ETH/USDC — no account or API key
MIT ★ 1 -
Command-line interface and Python SDK for VoltageGPU: confidential GPUs on demand (Intel TDX, tenant-side NVIDIA attestation) and an OpenAI-compatible inference API, billed per second.
MIT ★ 1 -
MCP server for Gate402: pay-per-call agent APIs over x402. Open-model LLM inference, crypto/finance data, SEC filings and web tools. Free tier, no signup.
npm MIT -
spraay-x402-mcpgithub.com/plagtech/spraay-x402-mcpupdated this year
MCP server for the Spraay x402 Gateway — 148 pay-per-call tools for AI inference, batch payments, DeFi, research & compute on Base, with Solana, Ethereum, XRP & Stellar rails. USDC via x402, no API keys.
MIT ★ 4 -
animica-mcpgithub.com/animicaorg/animica-mcpupdated this year
MCP server for the Animica post-quantum blockchain — 22 read/compute tools (chain reads, free AI inference + embeddings, quantum RNG, pool stats, notarisation, x402 catalog). No API key, no private keys. pip install animica-mcp / uvx animica-mcp; remote: https://mcp.animica.org/mcp
Apache-2.0 -
AgisHub MCP — 34 pay-per-call tools for AI agents (x402, USDC on Base). Web scraping, crawling, AI inference, timezones, memory, media and developer utilities. Most tools also run free over MCP; from $0.01 per call over HTTP. No API key, no signup.
npm MIT -
OpenAI-compatible inference for open-weight models, set up by your coding agent. Prepaid, pay per token, no subscription. US live; Canada coming soon.
npm MIT -
omni-nligithub.com/CogitatorTech/omni-nliupdated this year
A multi-interface (REST and MCP) server for natural language inference
MIT ★ 3 -
Run AI models like Llama, Qwen, and Gemma on every computer you own, and manage them for everyone on your network. Local first, with OpenAI- and Anthropic-compatible APIs, people and roles, and MCP.
AGPL-3.0 ★ 5 -
Core server for exposing India’s open government data (data.gov.in) APIs via the Model Context Protocol, powering agentic AI data exploration.
MIT ★ 2 -
Keys, money and subagents for AI agents: Phantom AI keys and child keys, budgets and plans, model routing, an agent wallet, and signed receipts. CLI, MCP server, and a skill for pi, Claude Code, Codex and Cursor.
npm MIT -
AI/ML and HPC at planetary scale. One API. Every Accelerator. Any Region. MIT-0 licensed.
MIT-0 ★ 55 -
Make the call. Run local Laya, Von, CLM or hosted Jev for typed classification and scoring through one HTTP and MCP API, with resource-aware batches.
WTFPL ★ 3 -
mindbridge-mcpgithub.com/pinkpixel-dev/mindbridge-mcpupdated this year
MindBridge is an AI orchestration MCP server that lets any app talk to any LLM — OpenAI, Anthropic, DeepSeek, Ollama, and more — through a single unified API. Route queries, compare models, get second opinions, and build smarter multi-LLM workflows.
MIT ★ 41 -
Local AI desktop app: a Chromium browser with a GPU-aware llama.cpp runtime, OpenAI-compatible API, AI chat and agents, Stable Diffusion image/video, TTS and music, plus an MCP server so Claude Code, Codex and Cline can drive your browser. Windows, macOS, Linux.
NOASSERTION ★ 144