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. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. 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.
-
Read-only MCP server for MuleSoft Anypoint Platform: application logs, Monitoring Archive search, Runtime Manager, API Manager and Exchange.
npm Apache-2.0 -
mcp-ptystale
MCP server for PTY session management with Bun runtime
npm -
MCP server manager for DeepSeek Harness: manage MCP servers from the Web settings page, stored globally in $DSH_HOME/mcp-servers.json, connected/disconnected at runtime.
npm MIT -
aura-mcp-serverupdated this year
AI Universal Runtime Architecture (AURA) - AI context management with intelligent model recommendations and standalone task management for any MCP-compatible IDE
npm MIT -
janee-mcp-demogithub.com/lucamorettibuilds/janee-mcp-demoupdated this year
Demo MCP server using Janee for encrypted secrets management. Shows how AI agents can securely access API keys at runtime.
★ 1 -
visflow-mcpupdated this year
VisFlow stdio MCP runtime for company-managed agent plugins
npm UNLICENSED -
mcp-servergithub.com/jolterjs/mcp-serverupdated this year
Official Model Context Protocol (MCP) Server for Jolter runtime and toolchain manager
MIT ★ 1 -
skill-forgegithub.com/gtm-k/skill-forgeupdated this year
Local-first skill runtime + visual manager for local/open LLMs — source agentskills.io skills and inject the right one at runtime into LM Studio, MCP hosts, and any OpenAI-compatible proxy.
Apache-2.0 -
@dsh-mixxed/dsh-client-ui-settings-mcpgithub.com/dsh-mixxed/dsh-client-ui-settings-mcpupdated this year
MCP server manager for DeepSeek Harness: manage MCP servers from the Web settings page, stored globally in $DSH_HOME/ui-settings-mcp.json, connected/disconnected at runtime.
npm MIT -
Unified MCP server for managing local model runtimes (Ollama, LM Studio, and more): provider-agnostic discovery, lifecycle, hardware-fit, and delegated inference.
npm NOASSERTION -
zvault-cligithub.com/vanitascaesar1/zvaultupdated this year
ZVault CLI — AI-native secrets manager. Import .env files, inject secrets at runtime, MCP server for AI coding assistants
cargo MIT OR Apache-2.0 -
super-productivity-local-gobridgegithub.com/CameronBrooks11/super-productivity-local-gobridgeactive
Single-binary MCP server and CLI that lets AI agents manage Super Productivity tasks over its local REST API — no plugin, no Node runtime, and no way for it to delete a task.
go MIT ★ 3 -
mcp-sidecargithub.com/lsequeiraa/mcp-sidecarupdated this year
A lightweight, cross-platform MCP server for managing background processes. Built in Go for single-binary distribution with zero runtime dependencies.
npm MIT -
High-performance Minecraft server management panel & control plane built with Rust and React. Features 19 server runtimes, live console & telemetry, Modrinth integration, SHA-256 verified streaming backups, automated schedules, and native MCP support for AI-assisted server ops.
★ 2 -
Coding-agent orchestration and MCP context runtime with governed repository execution, bounded tool results, and multi-agent session management.
npm MIT -
helix-controlgithub.com/Kimosabey/helix-controlupdated this year
Agentic Infrastructure Orchestrator and MCP Runtime for autonomous DevOps and system management.
MIT -
chromeshipupdated this year
Build, run, and monetize Chrome extensions from one local studio with managed runtimes, backend integrations, a CLI, dashboard, and MCP server.
npm UNLICENSED -
uCore host/core daemon for the uDosGo ecosystem. Python aiohttp host runtime with extension registry, surface management, MCP bridge, snack orchestration, and GitHub automation.
-
This plugin demonstrates dynamic tool list management in hyper-mcp. It showcases how a plugin can modify its tool list at runtime and notify the MCP server about these changes.
Apache-2.0 -
TP-Link Omada MCP server with automatic API discovery, validated read/write tools, network diagnostics, and runtime management for stdio and Docker.
MIT ★ 10 -
The runtime your AI agent deploys to one MCP call gives a live container with Postgres, S3 storage, and a public URL. Create, deploy, exec, and manage apps.
npm MIT -
MCP server and MODX Revolution 2.8.x / 3.x component for safe AI-agent management, with a shared modular runtime, backups, audit hooks, and dependency analysis
MIT ★ 5 -
Semantic package manager and MCP server for semantic index bundles. Install .sembundle archives, query symbol graphs and docs, and surface intelligence directly to GitHub Copilot — compiled to a single Rust binary, no Python runtime required.
MIT -
hurricane-vr-mcpgithub.com/happysisyphuspro/hurricane-vr-mcpupdated this year
Adds an hvr_manage tool to MCPForUnity for HurricaneVR — inspect grabbables/sockets/hand grabbers, assemble grabbable and interactable-door prefabs, bake hand poses, and drive runtime state (teleport, force-release, lock/unlock doors) via reflection, with no hard compile dependency on HurricaneVR.
MIT -
AegisGate MCP — Standalone Model Context Protocol security server with 23 security layers, vendored ONNX runtime, neural threat detection (L3). SSE streaming. Session management. Zero module dependencies. Multi-arch (amd64/arm64). Apache 2.0.
oci Apache-2.0 -
SharpInfergithub.com/JPaulDuncan/SharpInferupdated this year
A pure C# LLM inference engine built from scratch — no Python, no llama.cpp bindings, no ONNX Runtime. SharpInfer loads GGUF and Safetensors models directly, dequantizes weights in managed code, and runs the full transformer forward pass natively on .NET 8.
MIT ★ 6 -
tuningengines-cligithub.com/cerebrixos-org/tuning-engines-cliupdated this year
Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles p
npm MIT -
MCP server that drafts ISO management-system documents clause by clause (Annex SL): grounding on the client's Word documents, exact-fidelity .docx output, change tracking and a runtime fidelity guard. Clause 4 complete (ISO 9001/14001/45001/37001).
MIT -
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 -
PostgreSQLgithub.com/antonorlov/mcp-postgres-server#readmeno update data
Connects an agent to a PostgreSQL database: local, Docker, managed Postgres on RDS, Neon and Supabase, or a database that is only reachable through an SSH bastion. **Reaches the database you actually have.** Built-in SSH tunneling with a pinned host key, and eight named failure codes that say which phase broke. One `DATABASE_URL` is the whole setup. **Sees the whole database.** `list_schemas`, plus a schema argument on `list_tables` and `describe_table`, so it is not stuck in `public`. **Tells you what broke.** Failures come back carrying the SQLSTATE or SSH code with a hint, so the agent corrects itself instead of retrying blindly. **Respects the context window.** Results carry a byte budget with an explicit `truncated` flag, so a large table does not flood the model. **Writes are off by default**, and refused by PostgreSQL itself rather than by a client-side SQL filter: every read runs inside a `BEGIN READ ONLY` transaction, so the rule survives views, rules and functions. Turn them on with `PG_ALLOW_WRITE=true`. MIT, four runtime dependencies, Node 20 or newer. Also on npm as `mcp-postgres-server` and in the official MCP Registry as `io.github.antonorlov/mcp-postgres-server`.
smithery -
Runtime CLI, MCP server, local connector, and Codex plugin artifact for Prime Coder.
npm SEE LICENSE IN LICENSE -
A Codex plugin and local MCP runtime for context-bounded image generation and inspection.
Apache-2.0 ★ 97 -
Durable, policy-scoped semantic context for AI agents via MCP: source authority, state reconciliation, SQLite persistence, and local demos.
npm GPL-3.0 -
MCP server for AI agent orchestration - spawn, manage, and coordinate multiple AI agents
npm MIT -
master-controlgithub.com/N1ghthill/master-controlupdated this year
Local-first runtime for controlled Linux host operations with an MCP interface, policy, approvals, and auditability.
Apache-2.0 -
Local context management CLI and MCP tools for AI coding agents
npm MIT -
mcp-aws-managerupdated this year
AWS operations CLI and MCP server (SSM-only) for EC2/Lambda inventory, remediation, and runtime snapshots
npm MIT -
LifeOS — AI-native knowledge OS runtime, CLI scaffold, and MCP memory server
npm MIT -
devscopegithub.com/lpbird/devscopeupdated this year
Detect, install, and manage development environments. Scan & visualize all your local code projects. MCP-native.
npm MIT -
Private, local photo library: indexes your folders with on-device CLIP search, EXIF/GPS places and duplicate detection, and hands an AI agent compact, honestly ranked results plus a numbered contact sheet over MCP. Never touches your originals.
MIT -
irontology-mcpgithub.com/PromptExecution/irontology-mcpupdated this year
irontology - a memory safe rust Inference Runtime Ontology
-
AI-client-neutral fleet control plane. Source preview with read-only MCP, HTTP/Console, evidence-gated admission and optional device runtimes.
AGPL-3.0 -
Jeopsok (접속): safe-by-default stateless MCP 2026-07-28 remote runtime with permission profiles
MIT -
DebugBundle product source and runtime code.
npm Apache-2.0 ★ 7 -
CTXgithub.com/Alegau03/CTXupdated this year
CTX - Context Runtime Engine for Coding Agents
cargo ★ 146 -
MCP Device runtime.
npm MIT -
Lightweight RAG system for coding agents. Index your project docs, search them semantically, serve results over MCP — single binary, no runtime dependencies.
MIT ★ 27 -
The Biomimetic Context Engine & Neural Runtime for AI Coding Assistants
MIT ★ 93 -
macOS-native MCP runtime for fresh workspace state, bounded context, and retained execution evidence
npm Apache-2.0 -
Task & project runtime for teams and AI agents — one Go binary as CLI, HTTP API, Web Console and MCP server, backed by pure-Go SQLite.
Apache-2.0 -
exo-discordgithub.com/alxxpersonal/exo-discordupdated this year
Plug AI agents into Discord. Single Go binary with MCP server, full Discord management surface, and audit log. Native Claude Code channel injection + Codex app-server bridge. Official bot platform + OAuth 2.0 user-install only.
MIT -
Private local memory for any AI agent: Markdown database, SQLite search, MCP, zero runtime dependencies.
MIT ★ 9 -
Source-grounded MCP memory runtime and Obsidian-compatible vault template for LLM agents.
MIT ★ 76 -
Experimental zero-runtime-dependency MCP skill library with BM25 search and indexed Ed25519 status; clients must enforce that status.
npm Apache-2.0 ★ 1 -
Memory patrol + lexical recall + conversation gates for long-lived agents. Auditable SQLite kernels, CLI + MCP, zero runtime deps. 记忆巡检、召回打分与群聊接话决策内核;可审计、零依赖。
MIT ★ 1 -
notion-ai-implementationgithub.com/nutnutty/notion-ai-implementationupdated this year
ChatGPT Apps SDK + MCP runtime for autonomous conversation capture and controlled Notion sync across tasks, research, knowledge, and incidents.
-
Windows-local credential and quota broker (daemon, CLI, MCP server): DPAPI custody, transactional quotas, crash recovery. 3,781 tests per runtime on Python 3.12–3.14.
NOASSERTION -
An open protocol and Rust runtime for persistent, user-owned context and memory across AI applications. | 面向 AI 应用的持久上下文与记忆协议及 Rust 运行时,数据由用户持有。
MIT ★ 1 -
Self-hosted workspace and AI agent orchestration. Project boards, MCP, agent identities, runs, task claims, and a local runtime daemon.
MIT -
Lossless context-window swap for long-running Claude Code sessions: carry every word of the conversation, drop only runtime noise, switch in place. MCP-driven, fail-safe, human-confirmed.
MIT ★ 1