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 enforcing client-mandated development workflows with audit trails, state persistence, and compliance reporting
MIT -
@ikani.samani/workrailgithub.com/iconza98/workrailupdated this year
Personal hardened fork of WorkRail (step-by-step workflow enforcement for AI agents via MCP)
npm MIT -
MCP workflow enforcement server -- guides Claude and other AI agents through structured, step-by-step tasks without skipping steps or cutting corners
npm MIT ★ 4 -
dev-workflow-mcp-serverstale
MCP server to enforce development workflow discipline
npm MIT -
MCP server to enforce development workflow discipline
npm MIT -
Graph-based workflow enforcement and persistent memory for AI coding agents. Define structured workflows in YAML. Enforce them at tool boundaries via MCP. Build a persistent knowledge graph that grows with every query and knows when its sources have changed.
npm MIT ★ 10 -
@contexter/mcp-servergithub.com/sumeetgdoshi/context-engine-mcpupdated this year
MCP server that enforces Research → Plan → Validate workflow for AI coding
npm MIT -
smart-agent-workflow-mcpgithub.com/vjrivmon/smart-agent-workflow-mcpupdated this year
The only MCP that enforces tests before merge. Full-cycle development automation with testing gates, workflow orchestration, knowledge graph memory, and context health tracking.
npm MIT -
A Model Context Protocol (MCP) server that enforces disciplined Test-Driven Development workflows
pypi MIT -
odin-workflowgithub.com/Plazmodium/odin-workflowupdated this year
Specification-driven workflow runtime for AI coding agents. Odin enforces an 11-phase delivery process with specialized phase/support agents, strict phase-agent proof, adaptive complexity, eval and review gates, semantic learnings, PostgreSQL-backed state, release tracking, and dashboard visibility.
npm MIT -
MCP server that enforces GAIN-Coding workflow gates as code — guiding the agent through reviewed, policy-compliant interactions.
MIT -
behavior-harnessgithub.com/rennanbastosc-source/chatbotrdoupdated this year
BehaviorHarness — OpenCode plugin + MCP server that enforces agent workflow gates (preflight, domain-check, prohibited-check, verify)
npm MIT -
A deterministic development harness for Claude Code — MCP workflow engine, enforcement hooks, YAML workflows, and multi-agent consensus (Claude + Codex + Antigravity/Gemini)
go MIT ★ 4 -
mcp-worktree-guardgithub.com/paolino/mcp-worktree-guardupdated this year
MCP server enforcing git worktree-per-branch workflow
-
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 -
Governed AI execution platform for enterprise agents, durable workflows, policy enforcement, integrations, evaluation and operations.
Apache-2.0 ★ 1 -
eng-discipline-mcpactive
MCP server that enforces a structured, senior-engineer workflow on AI coding assistants: requirements, architecture, data model, and security review must all pass before any code is written.
npm MIT -
Rapid-Dev-Guide-MCPgithub.com/Rajkumar-Sony/Rapid-Dev-Guide-MCPupdated this year
MCP server for structured AI-assisted development. Enforces setup, rules, and validation workflows to improve code quality and consistency.
NOASSERTION -
utf8-mcpupdated this year
UTF8-MCP local server that enforces UTF-8 text workflows
npm ISC -
A comprehensive Kanban workflow system with MCP server for Claude Code - enforces TDD, prevents fallbacks, and ensures complete implementations
★ 1 -
devtools-mcpgithub.com/hitoshura25/devtools-mcpupdated this year
A TypeScript monorepo containing platform-specific MCP servers that provide reliable, enforced quality gates for AI agent development workflows.
npm Apache-2.0 -
MCP server: research-to-report workflow — plan_research, fetch_and_score (explainable 0-100 source scoring), build_report, check_report (citation coverage enforced)
MIT -
universal-spec-mcpgithub.com/ahmedelpannann/universal-spec-mcpupdated this year
A spec-driven engineering assistant MCP server — enforces Requirements → Design → Tasks workflow before any code is written. Works with Cline, Cursor, VS Code, Windsurf, Claude Desktop, and IBM Bob.
MIT ★ 1 -
Empower teams and individuals to build their own tools and workflows using their favorite AI agent, backed by a shared database that enforces security and business rules.
-
A comprehensive Model Context Protocol (MCP) server that provides intelligent NIST 800-53r5 compliance checking, automated code analysis, and standards enforcement for modern development workflows. Built using the official MCP Python SDK with real standards content from williamzujkowski/standards.
pypi MIT ★ 3 -
MCP-powered, agentic commit workflow: AI agents (Claude Code, Cursor) and developers commit through your team rules. Checked, formatted and enforced on every commit.
npm MIT -
Durable AI agent/workflow platform — Postgres-authoritative execution, typed tools, exact-action approvals, bounded agents, MCP, multi-agent, hierarchical budgets, OpenTelemetry. Model proposes, Forge enforces.
-
This project implements a Zero Trust framework on GCP, automating access control and policy enforcement. It uses n8n for workflows, enhanced by an MCP server and LLMs for intelligent, adaptive security decisions and automated remediation
Apache-2.0 ★ 2 -
A security-first TypeScript/Node.js MCP server for simulated AWS, Azure, and GCP infrastructure, demonstrating policy enforcement, human approval workflows, auditability, and safe agent-driven operations.
MIT -
vellegithub.com/PStryder/velleupdated this year
Velle is an MCP server that gives Claude Code the ability to prompt itself. It injects text into the terminal as user input via Win32 console APIs, enabling autonomous multi-turn workflows. self-prompting chains, 2-step slash command introspection, configurable turn limits, cooldown enforcement, and audit logging.
Apache-2.0 ★ 1 -
storymappergithub.com/TomAtAP/storymapperupdated this year
An opinionated ticketing harness where a human and an AI agent plan the same backlog together — a live User Story Map + Kanban board with an MCP server. Every agent move shows up in the browser instantly; every human edit flows back. Enforced DoR/DoD, configurable workflows, full revision history.
npm Apache-2.0 ★ 2 -
taskflow-mcpgithub.com/pinkpixel-dev/taskflow-mcpupdated this year
A task management Model Context Protocol (MCP) server that helps AI assistants break down user requests into manageable tasks with subtasks, dependencies, and notes. Enforces a structured workflow with user approval steps.
npm MIT ★ 30 -
Server-enforced workflow discipline for AI agents. An MCP server providing persistent work items, dependency graphs, quality gates, and actor attribution. Schemas define what agents must produce — the server blocks the call if they don't. Works with any MCP-compatible client.
oci MIT ★ 214 -
newrelic-mcpgithub.com/karldane/newrelic-mcpno update data
A Go-native MCP (Model Context Protocol) server for the New Relic observability platform, providing comprehensive access to APM, infrastructure, logs, traces, alerts, dashboards, synthetics, workflows, notifications, service levels, tags, entities, and workloads — all through a single GraphQL endpoint. Overview 55 registered MCP tools covering the full NerdGraph API surface Safety-first design: every tool carries EnforcerProfile metadata (risk, impact, resource cost, PII flag, idempotency) for automated policy enforcement via MCP Bridge Write protection: all mutation tools gated behind a -write-enabled flag; disabled by default Multi-region: US and EU data center support (NEWRELIC_REGION=us|eu)
smithery -
Deep-research-agentgithub.com/jakkapat-kingthong/Deep-research-agentupdated this year
Production-grade agentic research system with schema-enforced verifiable citations to eliminate AI hallucination. Built with LangGraph & FastMCP.
MIT ★ 2 -
A working starter pack for running Claude Code as a verified pipeline: S-Kai plans, I-Kai builds, V-Kai adversarially verifies, R-Kai researches. Ships the real role skills, craft playbooks, brief/handoff templates, a harness-enforced dispatch hook, and a local semantic-memory MCP server. MIT.
NOASSERTION ★ 1 -
ARCLinearGitHub-MCPgithub.com/arclabs-studio/ARCLinearGitHub-MCPupdated this year
MCP Server that integrates Linear (issues) and GitHub (repos) for Claude Desktop/Code, enforcing branch naming and commit message conventions
MIT -
Intelligent orchestration platform for AI coding tools — routes tasks to the best model, learns from outcomes, and enforces quality through multi-model consensus
npm MIT -
A kanban board your coding agents drive over MCP — strict enforced flows, atomic claim/lease, full audit trail. Ask your agent: "Do I need this? https://github.com/galvani/kanban-pro"
AGPL-3.0 -
Human approval requests for agent actions: expiring, single-use decisions. Trusted executors must enforce the gate; not a same-user security boundary.
npm MIT -
SSH for AI agents (Claude Code, Codex, Cursor) where reads run freely and every change needs a signed human approval that the server itself enforces.
Apache-2.0 -
Your AI on rails, on your terms — an open-source Claude Code plugin that enforces every process as it happens, so your AI can't fake the work. Free, on the subscriptions you already pay for.
MIT ★ 6 -
plangithub.com/kylejtobin/planupdated this year
A control plane for trustworthy AI agents: write product judgment once, then enforce it through typed MCP tools, git gates, demolition-first stories, evidence-judged checkboxes, and zero-trust monitoring. Ships with Claude Code and Cursor plugins, Agent Skills, and a FastMCP server.
NOASSERTION ★ 5