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.
-
ml-research-mcpgithub.com/nishide-dev/ml-research-mcpupdated this year
A MCP Server for ML Research and Development.
MIT -
medical-imaging-ml-research-mcpgithub.com/jamesvdinh/medical-imaging-ml-research-mcpupdated this year
An MCP server that grounds AI assistants in medical imaging research using Semantic Scholar API
MIT -
Hypothesis-first experiment tracking for agent-driven ML research, wired into Claude Code.
pypi MIT ★ 3 -
MCP server for post-quantum cryptography (ML-KEM, ML-DSA, SLH-DSA) with hybrid X25519+ML-KEM-768 key exchange. Research/prototyping tooling using liboqs.
MIT ★ 1 -
Local-first AI/ML research curation: Quick Search, Learning Path, Research Lineage, Trending Feed, My Feed, Venues. Data from Semantic Scholar, HuggingFace, GitHub. MCP server included.
MIT ★ 2 -
MCP CLI Server for the BigQuery Research Tool platform — enables AI agents (Claude Desktop, Cursor, etc.) to execute BigQuery queries, manage workspaces, and run ML pipelines via Model Context Protocol.
npm MIT -
Connect coding agents to your Althea and, through her, a consent-first network of ML researchers.
pypi MIT -
Open-source Japanese equity quant research stack for J-Quants/local data, factor & ML research, backtesting, portfolio/risk, paper simulation and MCP agents.
AGPL-3.0 ★ 18 -
secure-cluster-mcpgithub.com/FlorianSp2000/secure-cluster-mcpupdated this year
MCP Server allowing guarded interaction for coding agents with Slurm Cluster, intended for ML research
pypi MIT ★ 1 -
MCP server for finding and evaluating ML researchers using Semantic Scholar API and GitHub API
-
POLARIS FastAPI backend: LLM research agents (hypothesis, analysis, ML, curve fitting, literature), experiment watcher, MCP orchestrator, and phase-mapper pipeline.
-
Official MCP server for StoQuant — 48 read-only stock-research tools for Claude: Q-Score, ML outperformance odds, screeners, insider data, alt-data, macro. Free tier.
npm MIT -
Agent-driven ML researcher in a secure, reproducible KVM lab: five standalone scientific-state MCP servers within per-user VMs with driver / trusted / hostile zone isolation
Apache-2.0 ★ 8 -
QuantLab Pro is a quantitative ML research platform featuring six specialized agents, MCP-based tool integration, leakage-resistant time-series modeling, PyTorch experiments, backtesting, and reproducible MLOps tracking using Python, Streamlit, and SQLite.
MIT -
MCP server that lets LLM agents drive a data-poisoning detection research pipeline: 28 typed tools, plus a mock backend to run it end to end.
MIT