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.
-
agnostic-multicloud-delivery-frameworkgithub.com/segoja7/agnostic-multicloud-delivery-frameworkupdated this year
Transform any Kubernetes CRD into type-safe KCL schemas and developer-friendly blueprints with CLI and AI integration
Apache-2.0 ★ 2 -
frontendmaxxinggithub.com/sirdath/frontendmaxxingupdated this year
481 standalone CSS+JS snippets for frontend design. Vanilla. Zero build step. Zero dependencies. Framework-agnostic.
MIT ★ 1 -
Taichi is a language-agnostic, plugin-driven test orchestration framework — run API, gRPC, UI, static, and regression tests with one CLI, extend via third-party skill plugins in any language, integrate AI agents for auto-fix loops, and ship JUnit/JSON/HTML reports.
Apache-2.0 ★ 1 -
phaseopsgithub.com/agentxworks/phaseopsupdated this year
Modular, ecosystem-agnostic agentic SDLC framework.
pypi MIT -
Persistent, semantic memory for AI agents - mcp-native, local-first, framework-agnostic, production-ready
pypi mit -
A mixin-first SCSS design system. Write your own selectors and call cia mixins: 24 themes, 32 framework-agnostic recipes, a 33-tool MCP server so AI agents read the real API, WCAG-graded themes, and zero runtime JavaScript in the package.
npm MIT ★ 1 -
MCP-compatible message bus for multi-agent systems — framework-agnostic inter-agent communication
MIT -
CONTINUUM: Verifiable semantic recovery for long-running AI agents. Semantic checkpoints (not conversation dumps), an idempotent action ledger that refuses duplicate side effects, and a hash-chained tamper-evident event log, all exposed as a deny-by-default MCP server. Framework-agnostic, Python 3.11+
Apache-2.0 ★ 27 -
Persistent identity and memory across AI tools - mcp-native, local-first, framework-agnostic, production-ready.
MIT ★ 3 -
Framework-agnostic live WebRTC inspection and fault injection: peer connections, tracks, data channels, WebSockets, fake mic/camera, and real transport/signaling fault injection for reconnect testing.
npm MIT -
Framework-agnostic Java observability sidecar agent: chat with a live JVM via MCP/web UI (metrics, slow calls, errors, logs, thread dumps, method traces). Self-hosted, attachable (Arthas-style). Apache-2.0.
Apache-2.0 ★ 3 -
Manage knowledge as apps | CLI | MCP | AI Knowledge Framework for AI Agents & Humans
NOASSERTION ★ 11 -
Independent security verification for code written by humans and AI agents. Scan, repair, then prove it — Dvalin runs your project's own checks and issues a Verified Fix Record anyone can re-derive offline. Local-first, policy-bound, MIT.
npm MIT ★ 121 -
My personal Jarvis in one MCP: shared tools, memory, and personality across Claude, Gemini, ChatGPT, or voice. Swap the LLM provider/framework, keep the same Alistair.
-
npm launcher for the open-compute MCP server: model-agnostic computer-use (screenshot, safety-gated actions, Windows UIA) over MCP; spawns the Python open-compute server from GitHub.
MIT ★ 1