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.
-
modal-mcp-serverupdated this year
MCP server that lets AI agents run tests, training jobs, and Python GPU workloads on Modal.com
npm MIT -
A test bench your coding agent operates: live kernels and verified runs on Modal GPUs, Colab or your machine, inside a budget. Claude Code plugin + MCP server.
MIT -
CPU and GPU stress test for Linux (GTK 4 / libadwaita) – live sensors and 30-minute graphs, power supply readings, safety limits, Vifte-aware, status icon and Claude (MCP) integration
GPL-3.0 -
ATLASgithub.com/web3guru888/ATLASupdated this year
Active-inference Training with Learned Adaptive Stigmergy — Pure Rust AGI framework, 21 crates, 565 tests, 28 MCP tools, BF16 GPU inference (15.4 tok/s OLMo-3-7B on A100), OpenAI-compatible API, ZK proofs. Zero external dependencies.
Apache-2.0 ★ 3 -
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 -
Zero-dependency 3-tier MCP router for Claude Code & Google Antigravity that offloads file scouting and test log triage to a local GPU with automatic cloud failover.
Apache-2.0 -
Local-first Python vulnerability remediation with a 4B model on a 4 GB laptop GPU: fixes proven in a network-less Docker sandbox, a repair loop with test feedback, frontier fallback, and an MCP server.
Apache-2.0 -
Dragon Brain — persistent long-term memory for AI agents via MCP (Model Context Protocol). Knowledge graph (FalkorDB) + vector search (Qdrant) + CUDA GPU embeddings. Works with Claude, Gemini CLI, Cursor, Windsurf, VS Code Copilot. 30 tools, 1121 tests.
MIT ★ 51 -
Self-hosted dashboard for AnyPS5 contributors: your GitHub work, build machines and your own AI (MCP) in one place, with sandboxed multi-GPU verification of fix branches.
MIT -
Cross-platform hardware inspection, monitoring, stress testing and tuning, with a CLI, TUI and MCP server.
Apache-2.0 -
MCP server for RunPod local developer experience — scaffolding, testing, linting, cost estimation
-
ORRERYgithub.com/bochen2029-pixel/ORRERYupdated this year
A headless, contract-bounded, deterministic simulation instrument for a final theory of everything. Eight golden-gated CUDA/C++/Python tools, each independently cold-verified; LLM-callable via MCP. Tested, not asserted.
-
An open-source robotics workshop for agents: simulate complete robots on high-fidelity physics, build digital twins, make the parts on CNC, laser and 3D-printer twins, connect simulation to real robots, and let AI agents program, test and debug it all, just by talking to it.
Apache-2.0 ★ 197