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.
-
kanboard-mcpgithub.com/bivex/kanboard-mcpupdated this year
A Model Context Protocol (MCP) server written in Go that empowers AI agents and Large Language Models (LLMs) to seamlessly interact with Kanboard. It transforms natural language commands into Kanboard API calls, enabling intelligent automation of project, task, and user management, streamlining workflows, and enhancing productivity.
MIT ★ 29 -
Noesisgithub.com/chetan0220/Noesisupdated this year
Noesis is an AI‑Powered Data Analysis Platform which streamlines data science workflows by combining Large Language Models with the Model Context Protocol (MCP). It offers automated exploratory analysis, data transformation, data cleaning and data vizualization
★ 1 -
Wwise-MCP is a Model Context Protocol (MCP) server that enables large language models (LLMs) to interact with the Wwise Authoring application. It exposes a set of tools built on a custom Python WAAPI library, allowing MCP clients such as Claude or Cursor to automate and compose complex, multi-step Wwise workflows.
Apache-2.0 ★ 79 -
Atom of Thoughtsgithub.com/kbsooo/MCP_Atom_of_Thoughtsno update data
Enhance your applications with intelligent thought processing capabilities. Leverage advanced language models to generate, analyze, and manipulate ideas seamlessly. Transform your workflows with powerful context-aware interactions.
smithery -
Model Context Protocol Serverno update data
Integrate your applications with real-world data and tools seamlessly. Access files, databases, and APIs while leveraging the power of language models to enhance your workflows. Simplify complex interactions and automate tasks with a standardized approach.
smithery -
Workday MCP Serverno update data
Enable seamless integration of Workday data and services with language models through a standardized protocol. Facilitate dynamic access to Workday resources, tools, and prompts to enhance automation and contextual understanding. Streamline workflows by bridging Workday's enterprise capabilities with AI-driven applications.
smithery -
GitHub Projectsgithub.com/devassistantai/mcp-servers/tree/main/src/github-projects#readmeno update data
Manage GitHub Projects V2 efficiently by interacting with the GitHub Projects API through a set of powerful tools. Perform project, item, task, field, and view management operations seamlessly from your language model or client. Enhance your workflow with tested, production-ready capabilities for project automation and organization.
smithery -
workflows-mcpgithub.com/qtsone/workflows-mcpupdated this year
MCP server for DAG-based workflow execution with YAML definitions and LLM collaboration
pypi AGPL-3.0-or-later -
Collaborate on one ComfyUI workflow with an LLM agent through the official Comfy MCP. Multilingual UI (EN/JA/ZH/KO), live screen sync, Apache-2.0.
Apache-2.0 -
financial-mcp-pocgithub.com/masahirosakae/financial-mcp-pocupdated this year
Business evaluation workflow PoC using MCP and local LLMs
-
DFA-based workflow MCP server for guiding LLM task completion
npm MIT -
MCP server providing workflow guidance and next-step instructions for LLM development workflows
pypi MIT -
Python framework + local Studio for reliable LLM workflows: typed files in your repo, pre-run checks, experiments and evals, MCP server for coding agents
pypi NOASSERTION ★ 4 -
dyntoolstale
A Model Context Protocol server providing dynamic workflow tools for LLM interaction
pypi MIT -
sudwe3-n8n-mcpgithub.com/sudwe3/n8n-mcp-serverupdated this year
MCP server for n8n workflow automation - search templates, nodes, manage workflows with any LLM agent
npm MIT -
FlowForge MCP Server - Connect LLMs to FlowForge workflow automation platform
npm MIT -
@path58/n8n-mcpgithub.com/tsvika58/n8n-workflow-validatorupdated this year
The smartest and fastest n8n MCP server — validate, fix, and discover workflows inside your LLM
npm MIT -
@path58/p58-n8ngithub.com/tsvika58/p58-n8nupdated this year
The smartest and fastest n8n MCP server — validate, fix, and discover workflows inside your LLM
npm SEE LICENSE IN LICENSE -
MCP server that allow LLM in agent mode builds n8n workflows for you
npm MIT ★ 52 -
midasgithub.com/omarkhandji-commits/midasupdated this year
Self-hosted AI agent for safe LLM workflows: approvals, receipts, budget controls, local dashboard, CLI, Ollama, and MCP.
MIT ★ 1 -
Minimum sufficient context for LLMs. A local RAG context optimizer exposed through MCP, with Render Workflows-powered threshold calibration.
MIT -
Maestro MCP Server - Enhanced Workflow Orchestration for LLM Intelligence Amplification with HTTP/SSE transport
npm MIT -
@iflow-mcp/jnmetacode-agency-orchestratorgithub.com/jnmetacode/agency-orchestratorupdated this year
Multi-agent YAML workflow engine — 211 AI roles, auto DAG parallelism, zero code. One sentence → multiple AI roles collaborate → complete plan in minutes. 10 LLM providers, 7 need no API key.
npm Apache-2.0 -
Store, query, and create YAML workflow playbooks for LLM agents via MCP. STDIO or Streamable HTTP.
npm Apache-2.0 ★ 32 -
MCP server, written in Java 21 and compiled to a GraalVM native image, that reduces LLM token consumption in agentic coding workflows.
-
Agentic AI multi-agent application with local LLM (Ollama) and MCP server support. 45 agents, 50 workflows, fully offline. Jaspal 9891156880
★ 1 -
WIP / incomplete - not production-ready. n8n-style visual node workflows powered by AI agents, OpenRouter LLMs and native local MCP tools.
Apache-2.0 -
TGP (Task Gate Protocol): gated step-by-step workflow engine for LLM agents. YAML stages, engine-checked gates, live web canvas, CLI, HTTP API, and MCP.
MIT -
LLM and MCP workflow automation project for seller backend operations, logistics waybill creation, and browser-based process automation.
-
steplockgithub.com/l0kifs/steplock-ai-skill-executorupdated this year
An MCP server gatekeeper runtime that enforces step-by-step AI skill execution with output verification, ensuring stable and reliable agent workflows regardless of LLM compliance.
pypi MIT License Copyright (c) 2026 Sergei Konovalov -
AI-powered Chief of Staff that uses LLMs to triage emails, generate contextual replies, and execute approved email and calendar workflows.
★ 1 -
Open-source Django REST backend for the DARE Platform, with multi-LLM chat, RAG, MCP tools, AI workflows, and usage tracking.
NOASSERTION ★ 8 -
An LLM writes the workflow once; after that it runs on its own. A local MCP server that turns the tools you already have into typed, replayable Python workflows -- with a confirm gate, a dry run and a journal.
MIT -
A recipe-driven WaaS platform for ComfyUI that turns complex workflows (Image, Audio, Video, 3D) into intuitive Gradio UIs, high-level semantic APIs, and MCP tools for LLMs & AI Agents.
Apache-2.0 ★ 117 -
Contract-driven coding workflow: the strong model plans and accepts, your local LLM does the coding. 25 MCP tools + 6 skills, 8 agent hosts (ZCode, Claude Code, Codex, VS Code, DSH, pi, omp, opencode). Local-first, no telemetry.
MIT -
flowengine-n8n-workflow-buildergithub.com/ami3466/flowengine-mcp-n8n-workflow-builderupdated this year
Build n8n workflows from text using AI. Connect to Claude, Cursor, or any LLM to generate and validate n8n workflows with expert knowledge and intelligent auto-fixing. Built by FlowEngine. Now with real node parameter schemas from n8n packages!
npm SEE LICENSE IN LICENSE -
@iflow-mcp/flowengine-cloud-flowengine-n8n-workflow-buildergithub.com/flowengine-cloud/mcp-n8n-workflow-builder-flowengineupdated this year
Build n8n workflows from text using AI. Connect to Claude, Cursor, or any LLM to generate and validate n8n workflows with expert knowledge and intelligent auto-fixing. Built by FlowEngine. Now with real node parameter schemas from n8n packages!
npm SEE LICENSE IN LICENSE -
No-code visual node editor for AI workflows and small local tools: describe each node in plain words, AI writes its code or prompt, wire nodes into a graph and run it offline with a local LLM. Local-first, no telemetry, no account. Source-available, free for noncommercial use.
NOASSERTION -
mcp-server-cli-for-difygithub.com/RubyBlackbird/mcp-server-cli-for-difyupdated this year
Connect your Dify workspace to modern AI tools using this lightweight CLI and MCP server integration. Automate agent interactions, streamline workflow execution, and integrate customized LLM pipelines directly into local development setups and command-line environments.
NOASSERTION ★ 1 -
Blob-Beadsgithub.com/sdheer/Blob-Beadsupdated this year
Temporal Vault MCP: A local-first, security-hardened state management server for agentic workflows. Implements Content-Addressable Storage (CAS), Zstandard compression, and AES-256-GCM encryption to provide an auditable, "time-traveling" memory layer for LLM agents.
MIT -
Website to Clean Markdown, Vector RAG Chunks & llms.txt ($0.50/1k) — Includes 1-Click n8n Workflow, Make.com Blueprint & Claude MCP Server (https://apify.com/lucacelli/ai-ready-website-to-markdown-rag-crawler)
-
llm-sca-toolinggithub.com/grammy-jiang/llm-sca-toolingupdated this year
Evidence-first, LLM-augmented static code analysis: graph indexing, MCP server, audit workflows
pypi MIT -
MCP-QGISgithub.com/sergekostenchuk/MCP-QGISupdated this year
MCP/QGIS bridge for LLM-driven geospatial tool workflows
MIT ★ 10 -
mcp-councilgithub.com/epicsagas/mcp-councilupdated this year
MCP server for multi-LLM peer review and council deliberation workflow
cargo Apache-2.0 -
Importable n8n workflows: Telegram voice assistant, MCP tool-calling agent, Slack recipe bot and an LLM-powered ETL pipeline.
MIT -
llamator-mcp-servergithub.com/RomiconEZ/llamator-mcp-serverupdated this year
MCP server for llamator: automate LLM red teaming workflows
CC-BY-SA-4.0 ★ 4 -
mcp-server-vegalitegithub.com/Mavline/mcp-server-vegaliteupdated this year
LLM-connected data visualization workflow using Vega-Lite.
★ 1 -
knowledge-managerupdated this year
Git-native structured knowledge modules for LLM agent workflows via MCP.
pypi MIT -
MCP server exposing an n8n job-tracking pipeline to LLM clients, plus the workflows behind it.
MIT -
mcp-searxnggithub.com/muskats/mcp-searxngupdated this year
Experimental MCP to provide web search functionality for local LLMs, entirely developed using a local agent workflow.
MIT -
cntxgithub.com/whaleen/cntxupdated this year
File context management tool with web UI and MCP server for AI development workflows - bundle project files for LLM consumption
-
manasgithub.com/ninthhousestudios/manasupdated this year
Modular agent infrastructure in Rust — memory, perception, coordination, planning, code intelligence for LLM workflows
AGPL-3.0 ★ 1 -
SSH workflow helper for LLM agents
go MIT ★ 22 -
kartoza-mcpgithub.com/kartoza/kartoza-mcpupdated this year
Spatial-analytics MCP server: DBSCAN clustering for LLM workflows. Made by Kartoza.
NOASSERTION -
novelforge-agentgithub.com/zlx362211854/novelforge-agentupdated this year
Local-first long-form novel workflow engine for any MCP host (Claude Code, Codex CLI, …) or CLI. State machine + zod schemas + BM25 retrieval + persistent project state. No LLM dependency.
npm MIT -
🚀 Automate LLM red teaming workflows with the MCP server for LLAMATOR, featuring asynchronous job handling and seamless integration.
CC-BY-SA-4.0 ★ 2 -
Auditable context capsules for LLM handoffs, coding agents, and OpenCode MCP workflows.
MIT ★ 20 -
MCP server that lets Claude query ChatGPT, Perplexity, and Gemini for verification and comparison. Eliminates copy-paste workflow when you want multiple LLM perspectives on complex problems. Just tell Claude "ask the other LLMs" and get all responses automatically.
-
AI customer-support agent built on an MCP server and n8n workflows, with LLM tool calling
-
思源 AI 知识库插件(LLM-Wiki):侧栏问答、原文查询、知识整理、自定义 Skills 与 MCP 工具调用,保留实际写入记录。AI knowledge workflows for SiYuan.
★ 3