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.
-
MCP server to connect an MCP client (Cursor, Claude Desktop etc) with your ZenML MLOps and LLMOps pipelines
MIT ★ 49 -
Production-ready MCP (Model Context Protocol) AI agent for automating Australian telehealth patient intake, TGA/AHPRA compliance pre-screening, and doctor pre-consult briefs.
MIT -
evalbenchgithub.com/cognis-digital/evalbenchupdated this year
Offline LLM / agent eval harness with regression gates
NOASSERTION -
ragkitgithub.com/cognis-digital/ragkitupdated this year
Batteries-included local RAG pipeline — ingest, index, serve
NOASSERTION -
toolguardgithub.com/cognis-digital/toolguardupdated this year
Runtime allowlist and policy for agent tool-calls
NOASSERTION -
skillhubgithub.com/cognis-digital/skillhubupdated this year
Local skill registry and installer for AI agents
NOASSERTION -
promptpackgithub.com/cognis-digital/promptpackupdated this year
Versioned prompt / template registry with A/B and rollbacks
NOASSERTION -
A MCP server allowing LLM agents to easily connect and retrieve data from any database
NOASSERTION ★ 98 -
sysinfo-mcp-servergithub.com/intruderfr/sysinfo-mcp-serverupdated this year
MCP server exposing live system metrics to Claude -CPU, memory, disk, processes, and network info
MIT -
memorybankgithub.com/cognis-digital/memorybankupdated this year
Portable long-term memory store for agents, exposed over MCP
NOASSERTION -
Model Context Protocol (MCP) server for LLM spend & latency intelligence. Ask Claude why our LLM bill jumped.
★ 3 -
google-cloud-mcpgithub.com/krzko/google-cloud-mcpupdated this year
🤖 A Model Context Protocol (MCP) server for Google Cloud (GCP)
Apache-2.0 ★ 80 -
modelroutegithub.com/cognis-digital/modelrouteupdated this year
Local model router / proxy across Ollama, vLLM, and cloud with fallback
NOASSERTION -
skeinrankgithub.com/SkeinRank/skeinrankupdated this year
SkeinRank — Domain Language Control Plane for enterprise search, RAG, and AI-agent workflows.
Apache-2.0 ★ 2 -
protocolboxgithub.com/ianuragbhatt/protocolboxupdated this year
The Standard Library for the Agentic Web. A collection of verified, high-performance MCP tools designed to give AI Agents reliable superpowers.
MIT ★ 1 -
Portkey Admin API control-plane MCP server with Prisma AIRS interoperability guidance
npm MIT ★ 6 -
praxosgithub.com/JustVugg/praxosupdated this year
MCP-powered memory, policy, and experience layer for safer AI agents.
MIT ★ 12 -
Allow any MCP-capable LLM agent to communicate with or delegate tasks to any other LLM available through the OpenRouter.ai API.
MIT -
Governed MCP server and agent runtime: signed action approvals, typed tool effects and audit logs for Claude Desktop, Cursor and custom agents.
AGPL-3.0 -
llmtest-mcpgithub.com/tjacquesson/llmtest-mcpupdated this year
MCP server for LLMTest — benchmark AI models on real prompts, find cheaper alternatives across 340+ models. Works with Claude Code, Cursor, Windsurf.
MIT -
Open-source, self-hosted control plane for OpenClaw and Hermes AI-agent fleets on Docker/Kubernetes — REST, CLI, and MCP.
npm Apache-2.0 ★ 60 -
MCP server for AI economics — 12 calculators for token cost, LLM energy, agent-hour, Proof-Adjusted Autonomy, revocation exposure. Free API, no key. By Michał Piszczek.
MIT ★ 1 -
New API 管理 MCP — MCP server giving AI agents full administrative control over a self-hosted New API gateway. Go, generated route table, upstream drift detection.
MIT ★ 1 -
ThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.
npm MIT -
Open source agent workforce platform. Next.js + Postgres + MCP server for AI agent teams with human-in-the-loop review, built in.
MPL-2.0 ★ 3 -
Give AI agents cited, versioned context from your docs and spreadsheets. Build, diff and roll back what Claude Code, Codex and any MCP client read. Local-first, no API keys.
Apache-2.0 ★ 4 -
A self-hosted AI platform: inference, tool use, browser automation, image generation, speech synthesis, transcription, object storage, agentic code execution, and more, behind a single OpenAI-compatible endpoint. One docker-compose up.
WTFPL ★ 18 -
LLM observability and evals in a single binary: traces, prompts, datasets, scores and review queues for LLM and agent apps. Self-hosted, SQLite inside, OpenTelemetry-native, MCP and CLI for coding agents.
Apache-2.0 ★ 1 -
Switch AI models without breaking your product: find every model your code calls and when it retires, turn real usage logs into tests, compare and pick replacement models. CLI, GitHub Action and MCP server.
MIT -
Self-hosted hub for AI agent configuration: versioned personas, playbooks and knowledge with a mandatory review step, served to agents over MCP. Agent configuration you review — not behavior you hope for.
NOASSERTION -
See every hop of a request through your local LLM system: a tracing server, a live flow map, a waterfall per request, and an MCP server for Claude Code and Cursor. One static Go binary.
Apache-2.0 ★ 1 -
Drop-in OpenAI / Anthropic / Gemini BaseURL Proxy & Edge MCP Server (~0.04ms). Cut LLM input tokens by 60–99% via AST code skeletons, JSON pruning & stream healing with 1 line of config.
MIT ★ 1 -
Regression testing for LLM applications in CI. Sample your reference and a score drop is read against how much that score moves on its own. A flip from pass to fail is always a regression. Python CLI, pytest plugin, MCP server.
pypi Apache-2.0 ★ 10 -
Governed AI agents that actually do the work - in the cloud or on your own machine - across business systems, real browser tabs and real Android apps. Visual builder, MCP server, and official SDKs in 9 languages.
NOASSERTION ★ 8 -
personal-ai-employeegithub.com/Murad-Hasil/personal-ai-employeeupdated this year
An autonomous Digital FTE (Full-Time Equivalent) framework powered by Claude 4.5 & Obsidian. Features 24/7 multi-channel perception (WhatsApp/Gmail), Odoo financial integration, and distributed Cloud-to-Local orchestration. Local-first, privacy-centric, and Human-in-the-Loop.
-
vstackgithub.com/valani9/vstackupdated this year
AI agents fail like junior teammates, looping on bad ideas, ignoring feedback, and escalating commitment. vstack ports 34 of the most-cited organizational-behavior frameworks so you can diagnose your agents the same way you'd diagnose your team.
MIT ★ 1 -
Claude Code plugin for Synapse, a compiler for AI agent workflows: compiles a workflow to a typed graph, optimizes it, and blocks any rewrite that fails an equivalence check. Side-effecting steps are never reordered, repeated or cached. MCP server + 4 slash commands.
MIT -
A flight recorder for AI agents: records every step, ranks the step most likely at fault, then proves it by replaying the run with only that step repaired, at zero model calls. Top-1 0.60 on unseen failures against 0.25 baselines. MCP server, CI regression firewall, on PyPI.
MIT -
Provider-neutral prompt calibration engine with sensitivity-ranked meta-axes, hard-gate x soft-score fitness, walk-forward ship gates, guarded/expedition profiles, and explicit capability/risk reporting across Anthropic, OpenAI, Gemini, and local OpenAI-compatible backends. Optional sub-tools (mini-omega-lock, mini-antemortem-cli) distribute separately and plug in via the omegaprompt.preflight interface.
pypi Apache Software License