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.
-
@pushary/agent-hooksactive
Human-in-the-loop (HITL) for AI agents: ask a person for approvals or answers by push notification. One command connects Claude Code, Codex, Cursor, Gemini CLI and more.
npm MIT -
content-hooks-mcpupdated this year
Content Hooks MCP for creators and AI agents. Short-form content mechanics: 10 hook styles with failure modes, script structures for 5 formats, retention engineering, CTA rules, hook + script auditing. Receipts over hype.
npm MIT -
content-hooks-mcpgithub.com/closermethod/content-hooks-mcpupdated this year
Content Hooks MCP for creators and AI agents. Short-form mechanics: 10 hook styles with failure modes, script structures for 5 formats, retention engineering, CTA rules, hook + script auditing. Receipts over hype.
★ 1 -
Don't let your coding agent say "done" until the tests actually pass. Zero-LLM Stop hook, CLI, MCP server and GitHub Action for Claude Code, Codex, Cursor, Gemini CLI, Copilot CLI and 7 more agents.
MIT ★ 1 -
throngletsgithub.com/shangri-la-0428/throngletsupdated this year
Local AI substrate for agents with sparse signals, hooks, and optional adapters
pypi MIT -
coding-ethosgithub.com/paudley/coding-ethosupdated this year
Policy-as-code enforcement for AI agents with MCP, CEL, Git hooks, SARIF, and static-analysis guardrails.
pypi AGPL-3.0-only -
Policy-as-code enforcement for AI agents: MCP server, CEL policies, git hooks, SARIF, and static analysis guardrails.
AGPL-3.0 -
axiom-reflexgithub.com/vdalhambra/axiom-reflexupdated this year
Hooks, skills, agents, and MCPs that make Claude Code more autonomous and reflex-driven. Built for AI-first solo founders.
NOASSERTION ★ 2 -
50 Uniswap v4 hooks with Foundry tests, a TypeScript SDK, an MCP server for agents and a 3D docs site.
Apache-2.0 ★ 8 -
Delegate coding work from Claude Code to a local pi agent — MCP tools with mid-run steer/abort, plus per-project discipline hooks.
MIT ★ 4 -
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 -
Verify each git tree once. A stack-agnostic verification queue and cache for parallel coding agents: bounded concurrency, per-tree result cache, request coalescing, CLI for git hooks and an MCP server for agents. Rust.
MIT ★ 2 -
Delivery gates for AI coding agents: breaks your code on purpose and reports the breaks no test noticed. Seven languages via tree-sitter, on Windows, macOS and Linux. Git hook, CI step or MCP server.
npm Apache-2.0 -
touch-grassgithub.com/nalediym/touch-grassupdated this year
A Claude Code plugin that teaches your AI agent to remind you to go outside. Weather-aware, sunset-aware, session-aware. Ships an MCP server + SessionStart hook + skill.
MIT ★ 2 -
Claude Code security plugin and agentskills.io skill pack for securing LLM agents: threat modelling, config audits, prompt injection review, MCP server review, incident lookup, security evals, Semgrep rules, guard hooks and an incident-database MCP server.
MIT -
Project rules for AI coding agents. An MCP server gives Claude Code, Codex CLI and Antigravity the rules for the files they are about to edit; AST checks run in a git pre-commit hook and in CI (aegis check). Zero dependencies, Python 3.9+, Apache-2.0.
Apache-2.0 ★ 4 -
@bambushu/scargithub.com/bambushu/scarupdated this year
Failure memory for AI agents - briefing hooks + optional MCP server
npm MIT -
Agent Guides plugin for Claude Code: walk Skills, walk-observer audit hooks, and the guide MCP server.
MIT -
OpenAI Codex integration for Signetry: MCP server + lifecycle-hook guard to govern coding-agent changes. Split from signetry-plugins.
Apache-2.0 -
One Add teaches your agent Nika: skills, commands, hooks, an MCP oracle.
AGPL-3.0 ★ 3 -
Keep your agents from hallucinating their way to the finish by hooking them into provable results.
npm MIT ★ 2 -
Durable, local Maildir mailbox for agents in different CLI harnesses (Claude Code, Codex, others): routing, acks, an orchestrator lease and wake-up hooks.
Apache-2.0 -
Coordinate AI coding agents (Claude Code, Cursor) through a shared FalkorDB import graph: claims, conflict checks, memory, an MCP server and editor hooks.
npm MIT -
Shared memory for Claude Code sessions. The plugin, hooks, MCP tools and CLI that connect your agents to Bellek.
Apache-2.0 -
Undo a coding agent turn, including shell commands and untracked files, via hooks, a CLI, and an MCP server
npm MIT -
Complete toolkit to supercharge Claude Code CLI - 10 skills, 9 agents, 3 MCP servers, 6 hook scripts, and optimized config templates
-
A deterministic development harness for Claude Code — MCP workflow engine, enforcement hooks, YAML workflows, and multi-agent consensus (Claude + Codex + Antigravity/Gemini)
MIT ★ 4 -
push-bridgegithub.com/Isco0819/push-bridgeupdated this year
Approve your AI coding agent's risky commands from your phone — Claude Code hook + MCP (Codex/Gemini/Cursor).
MIT -
On-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search.
npm MIT ★ 212 -
Persistent memory for AI coding agents. Local SQLite + UserPromptSubmit hook — matched beliefs in the prompt before the model sees it. Deterministic, auditable, no embeddings, no cloud.
pypi MIT -
Toll MCP server: 28 tools for AI agents on Robinhood Chain: coin, pre-sign, agent and hook checks, Stock Token data (remote, https://t0ll.xyz/mcp, no auth)
NOASSERTION -
Cross-agent core memory in local Markdown, with MCP tools, native hooks, and installers for Codex, Claude Code, Grok, and more.
MIT ★ 2 -
AI-powered development tools. 18 agents, 19 commands, 29 skills, 4 hooks, 1 MCP server for code review, research, design, and workflow automation.
MIT ★ 36 -
MechCPgithub.com/RsGoksel/MechCPupdated this year
Hardened MCP server giving AI agents real-browser automation: CDP-level control, dynamic Python hooks, full element cloning, AST-sandboxed for safe AI-supplied code.
MIT -
Cost-aware, local-first skill routing for AI agents. MCP server + CLI + Claude Code hook. Tested on 141 real skills.
MIT ★ 1 -
High-performance, calibrated non-autoregressive decision engine (<4ms CPU) powering dual-process agent reflexes, Antigravity IDE lifecycle hooks, MCP server, and OS automation.
-
Trace anything running - dynamic reverse engineering for AI agents. MCP server + CLI with evidence records: hooks, syscalls, memory, network. The dynamic half of REA.
MIT ★ 1 -
Local-first long-term memory for AI agents. MCP, hooks, and handoff across Cursor, Claude, and other IDEs — no cloud, no API keys.
MIT ★ 5 -
⚡ High-performance, compact Linear client & MCP server for AI agents. Reduces prompt context payload by 70–80% with persistent auth, CLI, skills & git hooks.
★ 2 -
Let your coding agents talk to each other: search every Claude Code / Codex / Gemini / Cursor session, message live sessions, claim files — CLI, MCP, hooks, HTTP/SSE, A2A.
pypi MIT -
Thin launcher for the tmgr CLI: MCP server and Claude Code / Codex hooks for phone push notifications and urgent alarms for AI agents via TMGR
npm MIT -
kerebromgithub.com/ulianbass/kerebromupdated this year
Local-first persistent memory for AI agents. One Go binary installs MCP, lifecycle hooks, and shared SQLite/FTS5 memory for Claude, Codex, Cursor, and more.
NOASSERTION -
codex-nexusgithub.com/moreih29/codex-nexusupdated this year
Codex CLI plugin for Nexus multi-agent orchestration — installs nexus-core's lead agent, subagents, nx MCP server, skills, and tag hooks (Codex v0.129+).
MIT -
Install gate for AI coding agents: blocks malicious, hallucinated and typosquatted packages (npm, PyPI, crates.io, Go) before Claude Code installs them. Hook + MCP server + CLI.
MIT -
On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.
npm MIT -
The pre-commit hook for agents — scan terms of service for risky clauses before your agent accepts them. 13 MCP tools, REST API, x402 pay-per-scan.
MIT ★ 1 -
Groundrule: your engineering standards, taught to every coding agent and checked on every PR. CLI, checks, packs, MCP server and hooks.
npm Apache-2.0 -
Your engineering standards, taught to every coding agent and checked on every PR. Open-source CLI, checks, packs, MCP server and hooks.
npm Apache-2.0 ★ 1 -
The transactional write gate for coding agents: Plan -> canonical Manifest -> set-level checks -> hash-gated two-phase apply. MCP server, CLI, PreToolUse hook, GitHub Action.
npm MIT -
Local-first developer tools for macOS that you share with your coding agent: code search, MCP servers, hooks and skills for Claude Code and Codex.
BSD-3-Clause ★ 2 -
Get a Telegram message when your AI agent (Claude Code, Codex, OpenCode, claude.ai) finishes. Open-source MCP server, hooks and CLI, plus a hosted multi-user service.
MIT -
engramgithub.com/claudettetheai/engramupdated this year
Production-grade persistent memory for AI agents. Hybrid BM25 + vector search, knowledge graph, lifecycle hooks. 250K+ memories. Built by an AI, for AIs.
MIT -
Turn PDFs, Office files and scans into token-lean Markdown for LLMs and coding agents. Local-first: web app, desktop, CLI, MCP server, Claude Code & OpenCode hooks.
Apache-2.0 -
ossmategithub.com/sunjin12/ossmateupdated this year
OSS Maintainer's co-pilot — every Claude Code extension surface (Skills, Subagents, Hooks, MCP, Plugin, Agent SDK, Cron) in one tool
MIT -
Local-only MCP server and CLI for AI agents to create video ad briefs, hooks, UGC scripts, storyboards, and AdsTurbo-ready prompts.
MIT ★ 2 -
claude-code-invoice-guardgithub.com/mikko-lab/claude-code-invoice-guardupdated this year
Deterministic guardrail (refuse, don't guess) for an LLM agent on a VAT-critical invoice workflow: skill + subagent + MCP server + PreToolUse hook. Portfolio/demo plugin.
MIT -
Local, on-device voice notifications for coding agents (Claude Code, Codex CLI) — MCP tool, CLI, and lifecycle hooks backed by a local TTS bridge.
MIT ★ 2 -
Message channel between the agent sessions on one Mac (Claude Code, Codex, Grok Bot): find a session, deliver a message, get receipts and replies. CLI, MCP plugins, hook, desktop app.
MIT -
outbound-engine-mcpgithub.com/closermethod/outbound-engine-mcpupdated this year
Outbound Engine MCP for AI agents and creators. One cold-outreach engine, any target: brand deals, UGC, newsletter sponsorships, jobs, podcasts. HOOK/BRIDGE/SOFT-ASK structuring, message auditing, follow-up ladder, reply playbook, red-flag detection.
-
Let your coding agents talk to each other: search every Claude Code / Codex / Gemini / Cursor session and message live sessions. CLI · MCP · hooks · HTTP/SSE · A2A.
MIT ★ 1