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.
-
RBO moves heavy builds, tests, QEMU runs, and Docker jobs from an AI coding assistant to one or more worker machines
npm AGPL-3.0 -
An experimental DSL used for building embeddable artifacts and orchestrating pipelines.
cargo Apache-2.0 ★ 1 -
MCP server for building reusable LLM skills. Create, store, search, and invoke code patterns with persistent state and artifact management. Augmentation of the CORE framework (Comprehension, Orchestration, Reasoning, Evaluation) for structured agentic workflows. Inspired by Anthropic's "Building Effective Agents" & "Code Execution with MCP".
MIT ★ 2 -
MCP-based automation orchestrator for generating, validating, and deploying workflow pipelines. Hackathon build (Nov 2025).
MIT -
Local-first, multi-tier orchestrator with director, project manager, and coding agents. Runs Claude Code, Grok Build, and Codex solo or in Collab mode.
NOASSERTION -
@visualprd/mcp-serverupdated this year
Intelligent MCP Server for VisualPRD - Autonomous build orchestration between VisualPRD and AI coding agents
npm MIT -
zaatoolgithub.com/afrizagilleon/zaatoolupdated this year
Notebook-first workflow orchestration for humans and AI agents—build, run, and manage durable workflows through a web UI and MCP.
MIT -
Codex Massa — a /massa slash command for Claude Code plus a local MCP orchestrator that delegates coding to OpenAI Codex and loops build → verify → review until the goal passes.
MIT -
Multi-agent code review mesh — orchestrates AI agents from multiple providers to review code in parallel, cross-review each other's findings, and build accuracy profiles over time. Agents that catch real bugs get picked more often. Agents that hallucinate get deprioritized. MCP server for Claude Code, Cursor, and other IDEs.
npm MIT ★ 40 -
Local Sapiom developer MCP server (sapiom-dev) — the unmetered surface for building and operating on Sapiom; today it scaffolds, tests, deploys, and inspects orchestrations. Not the remote Sapiom capability MCP.
npm MIT -
Slim launcher/orchestrator for Unreal Engine projects: supervises UE + agent, with a built-in MCP server (editor control, build, runtimes, permissions). Dependency-free, cross-compilable Linux -> Windows.
★ 2 -
🧩 Build AI-powered MCP Tools with Azure Functions, Durable Agents & Cosmos vector search. Features orchestrated multi-agent workflows using OpenAI.
MIT ★ 114 -
Orchestrate complex AI interactions with Context Compose. A powerful CLI and server for building, validating, and managing context for large language models using the Model Context Protocol (MCP)
MIT ★ 1 -
Orchestrate complex AI interactions with Context Compose. A powerful CLI and server for building, validating, and managing context for large language models using the Model Context Protocol (MCP).
npm MIT -
Build an MCP server for Google Stitch with 18 tools for design systems, accessibility, responsive UI, and React, Vue, Svelte orchestration
-
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 -
A multi-agent research MCP server + mini client adapter - orchestrates a net of async agents or streaming swarm to conduct ensemble consensus-backed research. Each task builds its own indexed pglite database on the fly in web assembly. Includes semantic + hybrid search, SQL execution, semaphores, prompts/resources and more
MIT ★ 56 -
Portable MCP server for AI agents: persistent session checkpoints, resume and Total Recall, with package-aware build tools. Linux, macOS, Windows and SSH.
NOASSERTION -
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 -
Run Claude Code, Codex, Antigravity, Grok Build and OpenCode behind one runtime, and a run only counts as done when checks it didn't write pass. Cross-engine fan-out, councils, session handoff, spend caps, MCP server, ACP agent.
npm MIT ★ 610 -
yapout CLI + MCP server — the PM tool that prioritizes building software: plans, directives, executions and the agents that ship them
npm UNLICENSED -
AI agent task board for Claude Code, Codex, Gemini CLI and Grok Build: plan, approve, build and review inside JetBrains or VS Code, with state in .moe/ in your repo
MIT ★ 33 -
Intelligence, composed — an extensible platform for building and operating AI agents.
-
Build for agents — from the AI Gateway to the entire application stack.
Apache-2.0 ★ 293 -
Graph-Engineering for Real Engineers: Graphs define workflows; workflows build graphs. Based on mattpocock/skills.
npm MIT -
sshi-mcp-systemgithub.com/runailabs-maker/sshi-mcp-systemupdated this year
Helps autonomous AI coding agents build projects more reliably — audited phases, real sandboxed tests, anti-mockup validators, MCP-native, tool-agnostic. AGPL-3.0 + commercial dual license.
AGPL-3.0 -
Open-source platform for building your agentic org chart: each agent gets its own sandboxed Docker workspace, tools, HTTP API, and MCP endpoint.
MIT ★ 7 -
macOS app that runs Claude Code, Codex and Grok Build as one team: a lead AI delegates to parallel workers, with every app feature exposed as MCP tools.
MIT ★ 2 -
Scale parallelism. Preserve alignment. A fleet of coding agents builds one task in parallel against a spec contract; a decision that contradicts one already in force is refused — deterministically, no model in the decision path.
npm MIT -
jenkins-ai-optimizergithub.com/karadhub/jenkins-ai-optimizerupdated this year
Meet the beast of Jenkins MCP with AI-powered diagnostics, and more with Industrial debugging on steroids, AI ripping through failure logs, vector search that thinks faster than you, and multi-instance chaos turned into orchestrated genius. CI/CD will never be the same.]
pypi NOASSERTION ★ 6 -
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
npm MIT ★ 81,864 -
Plan -> build -> review across models, as a zero-dependency MCP server for Claude Code, Cursor and Codex: spec gate before handoff, tool vetting, per-run and per-day cost/token hard stops, safe defaults, clear logs. Based on Codex on Crack by Ethan Rogers
npm MIT -
madoshogithub.com/hogu-dev/madoshoupdated this year
a headless retrieval backend. Serves traditional RAG via a tool server or OpenAI shim, drive it from agents over MCP, CLI, or skills, run autonomous research subagents, and rate and compare each pipeline build step in an optional frontend
Apache-2.0 ★ 1 -
Harness-neutral coding-agent delegation: one .NET NativeAOT binary (CLI + MCP server) lets an architect in any host hand builds, reviews and tests to agents on Claude Code, opencode, Copilot CLI, Cursor, ACP or a bare API, and get back one normalized receipt.
nuget MIT ★ 2