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.
-
cc-plan-reviewgithub.com/zhcsyncer/cc-plan-reviewupdated this year
MCP server for human review of Claude-generated plans with web UI
MIT -
plan-boostgithub.com/nixo/plan-boostupdated this year
MCP server for collaborative plan review — create plans, get feedback, and iterate with a rich UI
npm MIT -
md-feedbackgithub.com/yeominux/md-feedbackupdated this year
Browser-first markdown plan review. Start local web review in one command, then let your agent continue through MCP.
npm NOASSERTION ★ 5 -
Catch the bad plan before you spend the tokens. Cross-LLM peer review via MCP.
npm MIT ★ 2 -
flikt-mcpgithub.com/flikt-ai/flikt-mcpupdated this year
MCP server for Flikt.AI — browse plan-review results, ask questions, export RFIs, and start reviews from Claude
pypi MIT License -
Multi-model adversarial plan review — orchestrates AI agents to critique and refine implementation plans
npm MIT -
konsiliogithub.com/edzillion/konsilioupdated this year
Konsilio MCP server runs draft plans through a multi-persona architectural review.
npm Unlicense -
Annotate is an MCP server and GUI for immutable Markdown plan revisions, one review per revision, and feedback back to the agent
-
@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 -
@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 -
MCP-Codex-reviewergithub.com/MarcEspuna/MCP-Codex-reviewerupdated this year
MCP server integrating OpenAI Codex as a plan and code reviewer for Claude Code
★ 1 -
plan-bridgegithub.com/amartinawi/plan-bridgeupdated this year
MCP server for structured plan/implement/review workflows between AI coding agents (Claude Code + OpenCode)
MIT ★ 1 -
Local MCP server for auditable, plan-linked Git commit review views
pypi MIT License -
mcp-plan-generationgithub.com/DabiK/mcp-plan-generationupdated this year
PlanFlow — MCP server to create, validate and review implementation plans with GitHub Copilot in VS Code
-
vibecode-booster-mcp-kitgithub.com/yigitkonur/vibecode-booster-mcp-kitupdated this year
Web-connected MCP toolkit for vibe coders: research tools, smart code planning, instant code review. Get unstuck fast and ship code at warp speed.
npm MIT -
tf-review-mcpgithub.com/sanjeevkkansal/tf-review-mcpupdated this year
MCP server that reviews Terraform plans for blast radius, stateful destroys, and public-exposure changes. Complements hashicorp/terraform-mcp-server.
pypi -
Claudemcpgithub.com/snakeying/Claudemcpupdated this year
Codex → Claude 的 MCP 接口,用 Claude Code 做 review / plan / 架构分析。Expose Claude Code as an MCP server so Codex can offload review, planning, and architecture analysis.
MIT ★ 1 -
triage-aigithub.com/wyman101/triage-aiupdated this year
Collaborative AI triage for code, plans and architecture — Claude, Gemini and Codex independently analyze then merge findings with consensus scoring. Security audits, bug hunts, plan reviews, second opinions. Claude Code skill + MCP server.
npm MIT -
Planning-stage: turns captured ideas (GitHub, GitLab, Jira via MCP) into OpenSpec changes and reviewable PRs through Interlock.
-
@codemoot/mcp-servergithub.com/katarmal-ram/codemootupdated this year
MCP server for multi-model AI code review, planning, debate, and memory (experimental)
npm MIT -
Deterministic code graph for reviewing changes: blast radius, QA plans, and MCP tools for coding agents
cargo MIT OR Apache-2.0 -
Daily planning and time tracking for people who bill their hours — estimate, run a timer, log to Jira, review where the month went. Laravel 12 + Vue 3 + Inertia, with an MCP server for Claude Code.
MIT -
brainregiongithub.com/fanghaoling/brainregionupdated this year
BrainRegion is an AI collaboration infrastructure designed for review, consultation, planning, and memory.
Apache-2.0 ★ 3 -
claude-codex-teamgithub.com/ndcorder/claude-codex-teamupdated this year
MCP server that bridges Claude Code to GPT Codex for adversarial brainstorming, code review, and implementation planning
npm MIT ★ 2 -
Local-native Context Engine MCP server for codebase indexing, semantic retrieval, planning, and review workflows.
★ 48 -
claude-code-companiongithub.com/anhtaiH/claude-code-companionupdated this year
Codex plugin and MCP companion for read-only Claude Code review, diagnosis, and planning.
Apache-2.0 ★ 1 -
@chogwanghyung/codex-ai-bridge-mcpgithub.com/chogwanghyung/codex-mcpupdated this year
MCP bridge for Codex to ask Claude, Gemini, and Antigravity for planning, review, QA, and implementation advice.
npm MIT -
ai-bridgegithub.com/AmirReza-Nasiri/ai-bridgeupdated this year
Cross-platform Rust MCP server that gives Claude Code a warm Codex peer for plan, implementation, and diff review.
MIT -
MCP server bridging Claude Code and OpenAI Codex CLI for plan-execute-review workflows
npm MIT -
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 -
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 -
lauras-mcpgithub.com/rfi-irfos/call-lauraupdated this year
lauras-core stdio MCP server — review_plan (free) + review_team (Laura's 15-agent team) over Laura Serna Gaviria's Human-AI Co-Evolution framework plus RFI-IRFOS's own lenses.
cargo LicenseRef-BSL-1.1 -
Free, open-source SQL Server execution plan analyzer — cross-platform GUI + CLI with 30 analysis rules, missing index detection, SSMS extension. Built-in MCP server for AI-assisted plan review.
nuget MIT ★ 251 -
A board where an agent draws its plan as a flowchart and you review it node by node, over WebMCP. Built for the WebMCP Challenge.
MIT -
Review what your agent makes. Your agent publishes its plan, page, or app over MCP; you comment on the exact spot, and it publishes the next version. Built with ViteHub.
NOASSERTION ★ 9 -
MCP server that brings senior-QA discipline to AI coding assistants — test planning, TDD, mutation testing, code review.
pypi Apache-2.0 ★ 7 -
Codex plugin: let ChatGPT plan and review while Codex executes — save Codex quota with the ChatGPT subscription you already have.
MIT ★ 1 -
Multi-model review gate for AI coding agents: other vendors' models review the plan before it is built and the diff after, over MCP. Native-AOT server + VS Code extension.
MIT ★ 13 -
تمهيد — ground work for execution: turn a project description into a validated, execution-ready planning & handoff package for Claude Code. Relational package store (SQLite ⇄ canonical JSONL), MCP-only writes, schema-enforced quality gates, HTML review surface. Successor of Keystone.
MIT -
uimax-mcpgithub.com/prembobby39-gif/uimax-mcpupdated this year
UIMax MCP — Turns Claude Code into a frontend expert that reviews and fixes your UI automatically. Free for Pro plan users.
npm MIT ★ 10 -
Codex (OpenAI) as an independent second opinion inside Claude, Claude Code and Cowork: parallel plans, critiques, code and diff reviews, red-teaming. Read-only sandbox.
MIT -
Plan stale and merged branch cleanup: keep / review / delete per branch, with reasons.
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.
-
Spend tokens on judgment, not typing. An MCP-native autonomous SDLC pipeline: frontier models plan and review, local models implement — engineering discipline on a $20/month budget.
AGPL-3.0 ★ 5 -
MCP server and CLI for second opinions: lets Claude Code, Codex and Cursor consult Codex, Claude, Gemini, Grok and local Ollama models for code review and plan debate
npm MIT ★ 20 -
UX review for apps built with AI, inside the agent you already use. Connects Codex, Claude Code, Cursor, Windsurf or Gemini CLI to the Phyll engine; the AI work stays on your own plan.
npm MIT -
A typed, reviewable pre-PR for every user story, before any code is written. F# plan model, MCP server, and a GitHub Agentic Workflow that files it as an issue and checks the PR against it.
MIT -
Multi-LLM development harness — local-first, test-gated, honest by construction. Requirements→spec→plan→build→review→release with real verification gates; operable by humans, CLI, desktop, or other agents via MCP.
mcpb Apache-2.0 ★ 11 -
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 -
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.
-
Review a Terraform/OpenTofu plan over MCP, read-only: summary, risk-ranked changes (database destroys, open firewall rules, IAM broadening), attribute diffs, replace explanations, plan comparison. Secrets masked in two layers.
MIT -
Rebar can block work until an AI plan review passes, require signed completion verification before close, and reconcile its event-sourced ticket record with Jira across CLI, Python, and MCP. GitHub is a read-only mirror. Code review runs in Gerrit.
pypi Apache-2.0 ★ 5 -
MCP server for Google Antigravity CLI (agy): delegate long tasks to Gemini 4 Orchestrator in a git worktree, get read-only plans and reviews, digest whole codebases — from Claude Code, Cursor or any MCP client
npm MIT ★ 2 -
Read, edit, compile, and review your Overleaf projects through your own signed-in session: from Claude, Codex, Cursor, or any MCP client, from the command line, or from TypeScript. No Git integration or premium plan needed.
npm MIT ★ 7 -
scrub-mcpgithub.com/zombat/scrub-mcpupdated this year
A 22-tool MCP server and CI-ready CLI that cuts cloud LLM token usage on code quality tasks. Deterministic tools handle what they can. A local LLM (via DSPy) handles the rest. Cloud models plan and review. Nothing else.
★ 1 -
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 -
Independent student demo: an MCP server on synthetic dental-plan data that lets an AI agent verify benefits for a batch of patients, with plan-clause citations and a human review queue.
MIT -
Local CLI/MCP bridge that lets Codex delegate compact review, research, and planning tasks to ChatGPT Web.
MIT ★ 5 -
Markdown → reviewed slide plan → on-brand slide visuals. MCP server for Claude Code with approval gates and pluggable visual systems
MIT ★ 1 -
Baton Agent Orchestrator — jev CLI + web dashboard that turns ideas into reviewed, tested code. Multi-provider dispatch (Claude Code, Codex, OpenRouter) across plan-validate-code-test-integrate, with autonomy modes, cost-aware routing, Kanban board, fleet view, browser preview with takeover, MCP servers, recursive learning and a quality gate.
Apache-2.0