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.
-
@joseph0926/plan-loopgithub.com/joseph0926/plan-loopupdated this year
MCP server for Claude-Code and Codex async collaboration with CLI setup
npm MIT -
morpheus-mcpgithub.com/evo-hydra/morpheus-mcpupdated this year
Plan state management and phase gate enforcement for AI dev loops via MCP
pypi MIT -
A Multi Agent System for planning perfect trip, using LangGraph, MCP, Supervisor, Guardrails, and Human in the loop concept.
Apache-2.0 -
claude-redlinegithub.com/switchbm/claude-redlineupdated this year
An interactive Human-in-the-Loop (HITL) review tool for Claude. Opens a local UI to 'redline' specifications and plans before code is written.
MIT ★ 2 -
MCP-native planning & memory system for Claude Code. Features real-time plan→code→document→reflect loops, conflict detection, and enterprise hardening.
npm MIT -
Turn Claude Code into a plan-execute-validate loop with parallel work, intelligent retry, and memory
MIT ★ 35 -
Product-Led Growth (PLG) analysis toolkit that detects tech stacks, plans growth loops and builds the loop iteratively.
npm MIT ★ 129 -
shared-brainstormgithub.com/mohitmayank/shared-brainstormupdated this year
Bring your teammates into your AI coding agent's planning loop. An MCP server that routes your agent's design questions to a shared web page where teammates discuss in their browser — no install, no signup. Works with Claude Code, Codex, OpenCode & Gemini CLI.
npm NOASSERTION ★ 15 -
@planningo/duulgithub.com/planningo/duulupdated this year
DUUL — Dual-phase Upfront-plan & Unit-verify Loop. MCP server for LLM peer review of plans and code.
npm MIT -
A CLI-first autonomous coding agent where the actor never grades itself. Every edit is grounded in your repo's real topology and verified by an independent deterministic grader (drift, lint, verify-task, intent) before it ships. Closed-loop: comprehend → plan → execute → critique → replan. Also a passive MCP harness.
go Apache-2.0 ★ 25 -
claude-codexgithub.com/ching-kuo/claude-codexupdated this year
Claude Code workflow integrating OpenAI Codex as an MCP server — plan, implement, and review loops with smart routing between Claude and Codex.
MIT ★ 24 -
sdd-harnessgithub.com/jackson1996vn/sdd-harness-v2updated this year
Autonomous architect→plan→code→test→review→security-review loop exposed as a local MCP server
pypi MIT -
orbit-agentgithub.com/Skilux/orbit-agentupdated this year
Orbit — a closed-loop campaign agent for lean marketing teams. Cross-MCP orchestration (Loomi read + custom Bloomreach write-MCP) in a goal→plan→execute→monitor→iterate loop with a human-approval gate. Loomi Connect AI Hackathon, Track 6.
NOASSERTION -
Personal AI strategist & mentor — goals-first planning with an agentic loop. .NET 10 + Model Context Protocol (MCP)
MIT ★ 2 -
cascade-bot-mcpgithub.com/ctreitges/cascade-bot-mcpupdated this year
npx wrapper that launches the Cascade-Bot MCP server (Python). Multi-agent Plan→Implement→Review loop for Claude Code.
npm MIT -
Local-first MCP server to audit, draft, and plan LinkedIn profile improvements — human-in-the-loop, official API only, no scraping or automation
MIT ★ 1 -
Validated analytics agent for CSV/Excel. LLMs plan - as a JSON plan or a bounded tool-calling loop - while deterministic pandas/scipy/DuckDB computes and re-verifies every number. No arbitrary code execution: the model only selects audited operations.
MIT ★ 4 -
🤖 Multi-agent AI dev team in Python: turns a feature request into a planned, coded and tested project. LLM agents for planning, backend, frontend, QA & security; a verifier runs real tests and loops failures back. FastAPI dashboard, MCP server, pytest, CI.
MIT -
AI-native chaos engineering orchestrator for Kubernetes — autonomous planning loop, DPv2-compatible engines (NetworkPolicy + Envoy fault injection), and MCP tools for arena/SUT/baseline.
Apache-2.0 ★ 2 -
Marty: an AI teacher on the MartyGraphics engine. An MCP server and a research-plan-author-check-repair loop that turn a question into a checked 3D lesson. Early preview.
Apache-2.0 ★ 1 -
Stable v1: AIAG core quality tools (FMEA, SPC, Control Plan, MSA/Gage R&R) as a closed loop over a shared typed core, callable by hand or by AI agents via MCP + Agent Skills.
★ 4 -
clonstgithub.com/capritora/clonstupdated this year
Adversarial AI code review for Claude Code: an MCP server that has your plans and code critiqued by OpenAI Codex (via your ChatGPT subscription, no API keys), in a ping-pong loop until consensus.
MIT ★ 1 -
**GridMind is an AI-driven power distribution grid operations console and incident response platform. It pairs deterministic physical simulation with sandboxed multi-agent orchestration (Operations, Safety, Planning), enforcing strict human-in-the-loop approval gates, live MCP tools, and immutable SQLite audit trails to prevent cascading blackouts
-
Agentic AI system for building Digital FTEs ( Full-Time-Equivalent ). Uses watchers, Claude-based reasoning, and MCP integrations to monitor Gmail, WhatsApp, and LinkedIn. Generates tasks, plans workflows, drafts actions, and routes approvals via human-in-the-loop. Local-first architecture enabling scalable, 24/7 automation for business operations.
-
magiclane-mcp-serverno update data
The Magic Lane Model Context Protocol (MCP) Server enables any AI agent or application to become a geospatially intelligent assistant, capable of acting as a reliable companion for pedestrians, cyclists, and drivers alike. Built on top of Magic Lane's advanced mapping and routing technology, this TypeScript-based MCP server empowers AI agents to: - Understand and process geospatial data - Interpret user intent in a spatial context - Deliver accurate, contextually relevant navigation guidance By leveraging Magic Lane's global map data and real-time geospatial intelligence, the MCP Server enables deeply personalized navigation and trip-planning experiences through core tools: - Intelligent Search: find addresses, points of interest (POIs), or coordinates with intelligent search capabilities and POI category filtering. - Smart Routing: generate optimized routes between multiple waypoints with support for various transport modes, route preferences, and dynamic POI integration. - Round Trip Planning: create circular routes that start and end at the same location, perfect for jogging routes, cycling loops, or delivery runs. - Reverse Geocoding: convert geographic coordinates into detailed address information including street name, city, state, country, and postal code. - Isochrone Analysis: calculate reachability polygons showing areas accessible within specific time or distance constraints. - Route Visualization: create visual map images of calculated routes, isochrones, and round trips for immediate geographical context and presentation. - Geofence Management: create, manage, and query geographic boundaries for asset monitoring, location-based alerts, and spatial analysis with support for polygons, circles, and rectangles. - Interactive Map: Display an interactive vector tile map directly inside the conversation using MapLibre GL JS and MagicLane vector tiles. Supports location views, route visualization, isochrone overlays, round trip routes, search result markers, geofence areas, and custom coordinate paths — with one or many overlays per map and pan/zoom interactions. The map functionalities can be visualized as high-quality map images through our new beta feature to generate custom map views with markers, bounding boxes, or location-centered areas without route calculation, complementing route visualization for routes, isochrones, and round trips. Together, these capabilities enable AI agents to act as true geospatial copilots - understanding spatial context, anticipating user needs, and optimizing every journey with precision and ease.
smithery -
cc-plan-reviewgithub.com/zhcsyncer/cc-plan-reviewupdated this year
MCP server for human review of Claude-generated plans with web UI
MIT -
@securedevops/mcp-devops-plangithub.com/securedevops/mcp-devops-planupdated this year
A Model Context Protocol (MCP) server for DevOps Plan work item management
npm ISC -
A daemon that runs Claude Code routines on a schedule and within the plan's usage limits, with an API, MCP and CLI
pypi MIT -
@uzbekswe/planuigithub.com/uzbekswe/planuiupdated this year
Structured review workflows for AI coding agents — Claude Code, Codex CLI, and any MCP-compatible assistant. Annotate, approve, and copy structured feedback on AI-generated plans.
npm MIT -
Tree-native workspace for human and agent execution: plan, run and review long AI tasks as an editable tree, via MCP in your existing agent tools.
-
Provider-neutral MCP server for software engineering: requirements, goals, milestones, portable implementation plans, verification and durable handover for coding agents, backed by SQLite.
Apache-2.0 ★ 2 -
Review & approve AI agent task plans in a ComfyUI-style node editor, right in your terminal (MCP server + TUI)
pypi MIT -
MCP server where AI reads freely but every write is a human-approved plan: diffs, budget caps, drift refusal, undo, audit log.
MIT -
Criterion Loom: meaning-first audit tools for Codex work—requirements, plans, diffs, and completion evidence via CLI, MCP, and a companion skill.
MIT -
Persistent project workflow for Codex that connects intent, sources, plans, tools, evidence, and continuity, with a read-only Windows Studio.
MIT -
Human-approved AI triage for a 401(k) service desk: PII tokenization, call-type classification, plan and payroll record checks, routing, and a code-enforced close guard. MCP servers and a an AI agent(Claude).
-
librariangithub.com/ivankwongtszfung/librarianupdated this year
A decision library for AI agent sessions. Agents submit plans and ADRs over MCP; you read, comment, and green- or red-light them; every verdict — including every rejection — becomes memory the agents can query. Local-first, MIT.
MIT ★ 1 -
gui-agent-frameworkgithub.com/sjkncs/gui-agent-frameworkupdated this year
Modular block-based GUI automation framework combining VLM vision, LLM planning, Playwright browser control, and pyautogui desktop automation. Includes food review crawler with multi-agent collaboration and MCP server.
-
Your agent wants to touch prod. Shadow Run lets it break a clone first: every risky plan runs on a full clone of prod in a microVM on Vultr, and a person approves what it really did, not what it says, before it reaches the real database.
MIT -
Open source phone MCP server for Claude and ChatGPT: let an AI agent place calls and send SMS through Twilio with plan then confirm codes, dry run by default, number allowlists, calling-hour guards and an audit log. For developers and agencies building AI agents that use the phone. Python, self-hosted, MIT.
MIT ★ 2