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.
-
Generate, preserve, and verify lean AGENTS.md, RUNBOOK.md, and machine-readable repo context for AI coding agents.
MIT ★ 5 -
mcp-http-agent-mdgithub.com/benhaotang/mcp-http-agent-mdupdated this year
MCP server to store AGENTS.md and kanban per project, make scratchpads and spawn subagents for immediate tasks
MIT ★ 6 -
🔌 Exposes AGENTS.md Linter over MCP — validates the cross-vendor coding-agent spec. Security smells + consistency lint. MIT. By MEOK AI Labs.
NOASSERTION -
agent-tools-md-mcpgithub.com/TimothyVang/agent-tools-md-mcpupdated this year
AI coding-agent tool routing guide and local TOOLS.md MCP server for Codex, Claude Code, Office/PDF, GitHub, browser automation, and MCP workflows
MIT -
Stop reintroducing yourself to AI. An open protocol for portable user preferences and context across Claude, Cursor, Windsurf, Codex, Gemini and any AGENTS.md agent. MCP server + CLI.
npm MIT ★ 4 -
Markdown notes your AI agents can read and write. This is the open-source image-hosting core of static.md.
★ 1 -
Zero-dependency preflight CI linter, GitHub Action, SARIF analyzer & MCP server for CLAUDE.md, AGENTS.md, SKILL.md, .mcp.json & prompt caches
MIT -
md-feedbackgithub.com/yeominux/md-feedbackupdated this year
MCP server for markdown plan review — companion to the MD Feedback VS Code extension. AI agents read annotations, mark tasks done, evaluate quality gates, and generate session handoffs. 27 tools for Claude Code, Cursor, and other MCP-compatible clients.
npm SUL-1.0 -
Verified AGENTS.md and project memory for AI coding agents (Claude Code, Cursor, Copilot, Codex, Gemini, Windsurf, Cline). Git-checked context docs, MCP server, zero dependencies.
npm MIT -
Lint your AI agent context files (CLAUDE.md, AGENTS.md, etc.) against your codebase
npm MIT ★ 12 -
Local dashboard, CLI and MCP server for AI coding agents: watch Claude Code and Codex edit live, track session cost, verify the work is done and safe to ship, review risky changes, and keep CLAUDE.md/AGENTS.md true.
npm MIT -
claude-initgithub.com/horiastanxd/claude-initupdated this year
One command generates AI context files (CLAUDE.md, AGENTS.md, Cursor/Windsurf/Cline, GEMINI.md, Copilot, Aider, Junie, Warp) for any repo. CLI + MCP, 100% local.
npm MIT ★ 1 -
MCP server for LynxPrompt — manage AI prompts, AGENTS.md and CLAUDE.md files via the Model Context Protocol
npm GPL-3.0-or-later -
rulestack-mcpactive
RuleStack MCP server from Compound Labs. Searches real AGENTS.md, CLAUDE.md and Cursor rules files from public repositories, scored for quality. No key and no signup.
npm UNLICENSED -
Linter for AI agent context files and MCP configs: CLAUDE.md, AGENTS.md, .cursorrules, .mcp.json - catches broken paths, wrong commands, leaked secrets
npm MIT -
MCP Server for LynxPrompt — browse, search, and manage AI configuration blueprints (AGENTS.md, CLAUDE.md) via MCP
npm GPL-3.0 ★ 2 -
Read-only linter for CLAUDE.md, AGENTS.md, SKILL.md and agent rules files: vendor limits, tokens loaded per session, hidden instructions and invisible characters, and files Claude Code or Codex never read. Claude Code plugin, MCP server, CLI, GitHub Action and pre-commit hook. No network. MIT.
npm MIT -
Free, local memory and rules hub for AI coding tools: persistent memory for Claude Code, Codex, Cursor and Gemini CLI. One SQLite store over MCP, REST and CLI. Rules sync to CLAUDE.md and AGENTS.md. claude-mem alternative.
npm Apache-2.0 ★ 10 -
Project rules for AI coding agents (Claude Code, Codex CLI, Antigravity): MCP server, AGENTS.md bootstrap, AST checks, pre-commit hook and CI gate
pypi Apache-2.0 -
@agent-lint/mcphttps://gitlab.com/bsamilozturk/agentlintupdated this year
Read-only MCP server for keeping AGENTS.md, CLAUDE.md, rules, skills, workflows, and plans structured, current, and codebase-aware.
npm MIT -
Shared project rules and memory for AI coding agents. Decisions, rules and failed approaches in one JEVMEM.md in your repo, read by Claude Code, Cursor and Codex, with a guard that checks Claude's commands before they run.
npm MIT ★ 151 -
Tell your coding agent which dependencies changed after its training cutoff. Diffs types and changelogs, writes a short block into AGENTS.md / CLAUDE.md.
npm MIT ★ 109 -
Bind documentation claims to tiered code fingerprints. Catch stale CLAUDE.md, AGENTS.md and docs at write time inside Claude Code and Codex, with a tamper-evident history.
npm MIT ★ 3 -
Local MCP server that audits your git changes against the repo's own AI rules (AGENTS.md, CLAUDE.md, .cursorrules, Copilot, Kiro, skills) and returns a compliance table or an HTML report.
npm MIT -
One common memory for every AI coding tool and agent framework. Compile rules and memory out to CLAUDE.md, AGENTS.md, Cursor, Copilot, Gemini and more, or serve it live over MCP and a local daemon. Local-first, with SDKs for TypeScript, Python, Go and Rust.
NOASSERTION -
Agent skills for popup2026.com — drop-in SKILL.md package for Claude Code, Codex, Gemini, Cursor. Bundles the Popup Remote MCP server.
MIT ★ 1 -
统一管理本机所有 AI Agent 的记忆与会话:扫描 Qoder / Claude Code / Codex / Trae / ZCode / MiMo / Marvis,按项目归类,一键合并生成 AGENTS.md,支持 MCP 实时召回与会话导出迁移
MIT ★ 1 -
agent-orchestrationgithub.com/madebyaris/agent-orchestrationupdated this year
Agent Orchestration: MCP server enabling multi-agent collaboration with shared memory, task queue, resource locks, Cursor rules, and AGENTS.md workflows.
npm MIT ★ 21 -
Your agent calls real APIs. You sign in once. Authenticated execution and discovery layer for AI agents: SKILL.md, MCP, CLI, HTTP.
npm MIT ★ 8 -
verdoc-mcpgithub.com/verdochello/verdoc-mcpupdated this year
MCP server for Verdoc - deterministic AGENTS.md and repository analysis for coding agents, paid per call in USDC over x402. No account, no API key.
mcpb MIT ★ 1 -
Find which APIs of your pinned Python dependencies changed after your coding model's training cutoff, and give the agent short AGENTS.md / CLAUDE.md notes from a static API diff. No model calls, no API key. CLI, MCP server, Claude Code plugin, GitHub Action.
pypi MIT ★ 10 -
warmstartgithub.com/dadwritestech/warmstartupdated this year
Self-verifying operational manifest for coding agents. npx warmstart init discovers, runs, and honestly stamps your repo's dev-loop into AGENTS.md + an MCP server.
MIT -
codemapsgithub.com/promptsterhq/codemapsupdated this year
Local-first context engine that maps your repo for AI coding agents — six lenses (orient/locate/impact/guardrails/risk/security) over MCP + AGENTS.md
Apache-2.0 -
把一句游戏道具描述变成 16×16 像素风 SVG 图标的工程化工具链:规范校验、Pillow 导出 PNG、图库预览、102 条物品/UI 图标目录、动态 AGENTS.md 与 MCP server。Turn game item ideas into validated 16×16 pixel-art SVG icons: lint, PNG export, gallery preview, a 102-icon catalog, dynamic AGENTS.md, and an MCP server.
-
MCP server that makes a project's context (AGENTS.md), memory, and identity discoverable to any MCP client — via the Server Card _meta block and ai-catalog.json
npm MIT ★ 3 -
Aletheia: a free, local memory and rules hub for AI coding tools such as Claude Code, Codex, Cursor and Gemini CLI. One store any tool reads over MCP, REST or CLI; rules synced to CLAUDE.md, AGENTS.md, Cursor and more; export and import to move between to
npm Apache-2.0 -
The Reality Next Door — an open, cited worldbuilding commons: a post-extraction Seattle on the Salish Sea. Authored by LONGSHORE, an AI, in the open. Agents & humans welcome: start at AGENTS.md
NOASSERTION -
Kanbanana replaces sprawling, merge-conflict-prone markdown coordination files (BOARD.md, GPU_LOCK.md, SKILL.md) with an atomic SQLite-backed HTTP MCP server, A2A (/.well-known/agent.json) agent discovery & task dispatch, isolated Git worktree provisioning and FIFO feature locks
-
MCP server + prompt that turns any AI coding agent (Cursor, Claude Code, Cline, Kiro, Windsurf…) into your Digital Twin — generate a project-specific AGENTS.md and give every tool a shared, persistent memory of how you build.
★ 46 -
Bootstrap AI coding-agent config (Claude Code, Cursor, Copilot, Gemini CLI, AGENTS.md, Windsurf) for a repo by auto-detecting its stack and the tools in use — interactively, or driven by an AI agent over JSON or MCP.
npm MIT -
Connect any AI coding tool to 1,600+ production-ready prompts and real React/Tailwind components. Open MCP server + AGENTS.md — works in Claude Code, Cursor, Windsurf, VS Code, Codex, Zed and more. ~6x cheaper than generating from scratch.
MIT ★ 3 -
MCP server and Agent Skill for evidence-based design research. Searches curated website styles on styles.refero.design and extracts real design systems — colours, type scale, spacing, surfaces, dos and donts — as design.md, so a coding agent implements fr
npm MIT -
Per-repo memory, outcome telemetry, and a calibrated-confidence gate for Claude Code, with MCP and AGENTS.md projections so other AI coding tools can read its context. Notes survive sessions; success claims need test evidence; your reverts are remembered. Local-only, stdlib runtime.
Apache-2.0 ★ 9 -
MCP server and Agent Skill for evidence-based design research. Searches curated website styles on styles.refero.design and extracts real design systems — colours, type scale, spacing, surfaces, dos and donts — as design.md, so a coding agent implements from measured evidence instead of inventing a visual direction.
npm MIT ★ 1 -
Drafting connector for Indian Civil Courts (property suits, partition, declaration, possession). STRICT SIX-AGENT PIPELINE: Reader → Format → Drafter → Verifier → Refiner → Overseer, producing six named artifacts (case-facts.md, format-shell.md, draft-v1.docx, verification-report.md, draft-v2.docx,
MIT -
Drafting connector for Indian Rent Controllers / Courts of Small Causes / Rent Authorities / Rent Tribunals. STRICT SIX-AGENT PIPELINE: Reader → Format → Drafter → Verifier → Refiner → Overseer, producing six named artifacts (case-facts.md, format-shell.md, draft-v1.docx, verification-report.md, dra
MIT -
Drafting connector for Indian Motor Accident Claims Tribunals. STRICT SIX-AGENT PIPELINE: Reader → Format → Drafter → Verifier → Refiner → Overseer, producing six named artifacts (case-facts.md, format-shell.md, draft-v1.docx, verification-report.md, draft-v2.docx, final-draft.docx). MANDATORY INVOC
MIT -
Drafting connector for Indian Labour forums (Labour Court / Industrial Tribunal / CGIT). STRICT SIX-AGENT PIPELINE: Reader → Format → Drafter → Verifier → Refiner → Overseer, producing six named artifacts (case-facts.md, format-shell.md, draft-v1.docx, verification-report.md, draft-v2.docx, final-dr
MIT -
Drafting connector for Indian contract drafting and dispute forums. STRICT SIX-AGENT PIPELINE: Reader → Format → Drafter → Verifier → Refiner → Overseer, producing six named artifacts (case-facts.md, format-shell.md, draft-v1.docx, verification-report.md, draft-v2.docx, final-draft.docx). MANDATORY
MIT -
Drafting connector for Indian Consumer Forums (District / State / NCDRC). STRICT SIX-AGENT PIPELINE: Reader → Format → Drafter → Verifier → Refiner → Overseer, producing six named artifacts (case-facts.md, format-shell.md, draft-v1.docx, verification-report.md, draft-v2.docx, final-draft.docx). MAND
MIT -
Drafting connector for Indian Banking forums (DRT / DRAT / NCLT / Civil Court). STRICT SIX-AGENT PIPELINE: Reader → Format → Drafter → Verifier → Refiner → Overseer, producing six named artifacts (case-facts.md, format-shell.md, draft-v1.docx, verification-report.md, draft-v2.docx, final-draft.docx)
MIT -
Drafting connector for Indian IP forums (Trademark Registry / Patent Office / IP Division of HCs). STRICT SIX-AGENT PIPELINE: Reader → Format → Drafter → Verifier → Refiner → Overseer, producing six named artifacts (case-facts.md, format-shell.md, draft-v1.docx, verification-report.md, draft-v2.docx
MIT -
Drafting connector for Indian Company-law forums (NCLT / NCLAT / High Court Company Bench). STRICT SIX-AGENT PIPELINE: Reader → Format → Drafter → Verifier → Refiner → Overseer, producing six named artifacts (case-facts.md, format-shell.md, draft-v1.docx, verification-report.md, draft-v2.docx, final
MIT -
Offline token-budget linter for agent context files — measures CLAUDE.md/AGENTS.md, finds dead references, returns a ranked plan.
npm MIT ★ 3 -
⚡ High-performance linter, cache-layout optimizer, and garbage collector for AI agent instruction files (AGENTS.md, CLAUDE.md, .cursorrules) in Rust.
MIT ★ 4 -
repo-seatbeltgithub.com/berkcangumusisik/repo-seatbeltupdated this year
A safety layer for AI coding agents. CLAUDE.md/AGENTS.md generator, MCP runtime guardrail, pre-commit hook, GitHub Action.
npm MIT ★ 8 -
Local CLI + stdio MCP context router for Claude Code, Codex, and Cursor. Stop bloating CLAUDE.md and AGENTS.md.
NOASSERTION -
Local MCP server that audits your git changes against the repo's own AI rules (AGENTS.md, CLAUDE.md, .cursorrules, Copilot, Kiro, skills).
npm MIT -
Bind documentation claims to code fingerprints. Catch stale CLAUDE.md, AGENTS.md and docs at write time inside Claude Code and Codex, with a tamper-evident history.
npm MIT -
Codify how you work. Every AI tool obeys. Markdown rules + cross-tool companion files (AGENTS.md/CLAUDE.md/.cursor/rules/.gemini) + Compliance Receipts for protocol-level enforcement of destructive ops. Reference implementation of CRP 1.0. Works on every
npm MIT