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.
-
@swarmfeed/clawhub-skillupdated this year
Social platform for AI agents — post, browse feeds, engage, and search. Ships an MCP server.
npm MIT -
@aiwerk/mcp-server-clawhubgithub.com/aiwerk/mcp-server-clawhubupdated this year
ClawHub.ai skill catalog MCP server — search, browse, download skills; publish/delete when authenticated
npm MIT -
Daily intelligence report on the AI Agent Skill ecosystem — scrapes ClawHub, skills.sh and more, computes normalized popularity scores, generates HTML reports. MCP server included.
-
MCP server for security-vetting third-party AI agent extensions before installation — Claude skills, ClawHub plugins, agent tool packs. v1.1: agent-config trust-boundary scanner (AGENTS.md / .cursor/rules.md / .claude/CLAUDE.md / .gemini/config / git hooks) addressing CVE-2026-26268. Outputs 0-100 risk score + BLOCK/REVIEW/CAUTION/CLEAN buckets.
pypi MIT License -
World's first AI-powered Yahoo Finance integration. 68 tools for stocks, ETFs, crypto, forex and commodities: prices, history, fundamentals, ratios, earnings and estimates, dividends, options, holders, news, movers and calendars. MCP server (uvx yfinance-ai), OpenClaw skill and OpenWebUI tool, with thousands of downloads on ClawHub and OpenWebUI.
MIT ★ 12 -
AI-powered SEC EDGAR integration. 23 tools for 10-K, 10-Q, 8-K, proxies, IPOs, 13D/13G, Form 4 insiders, 13F holdings and XBRL financials, plus full-text search and reading inside any filing. MCP server (uvx sec-finance-ai), OpenClaw skill and OpenWebUI tool, with thousands of downloads on ClawHub and OpenWebUI.
MIT ★ 3 -
Native XMemo cloud-memory provider for OpenClaw agents: long-term memory, semantic recall, TODOs, snapshots, and audit tools.
npm -
@cly-org/switchbot-openclaw-skillgithub.com/chenliuyun/switchbot-skillupdated this year
OpenClaw plugin that drives @switchbot/openapi-cli >= 3.3.0. Exposes 6 MCP tools (devices_list/status/describe/command, scenes_list/run) for SwitchBot smart-home control.
npm MIT -
W-2 event staffing data for AI agents — coverage, rates, lead times, and compliance for 300+ US/CA markets. MCP server, agent skills, and open schemas.
MIT ★ 1 -
@sarveshsea/memoiregithub.com/sarveshsea/m-moireupdated this year
Design memory and UI quality tools for coding agents: Codex, Claude Code, Cursor, OpenCode, Hermes, OpenClaw, MCP, Figma, shadcn/ui, and Tailwind.
npm MIT -
다이소·편의점 재고와 생활 정보를 AI에서 바로 조회하세요. 설치·API 키 없는 공개 MCP, 웹 링크 조회, CLI·Skill을 지원합니다.
go MIT ★ 350 -
OsmO: AI phone calls and AI receptionist for ChatGPT, Claude, Grok, Cursor, Gemini and any MCP client. Agent skills, plugins and MCP config.
MIT ★ 3 -
arc-security-mcpgithub.com/arcself/arc-security-mcpupdated this year
AI agent security: scan skills for 25 attack classes + runtime monitoring (EDR for AI agents). Real-time scanning, behavioral anomaly detection, session monitoring, exfiltration alerts. 1,316+ findings from 450+ audits. OWASP Agentic AI Top 10 mapped.
npm MIT -
CyberLens AI MCP server for website, repository, and CLAW/OpenClaw skill security scanning from AI assistants.
npm MIT ★ 1 -
Ironheights: The Immune System for AI Agents. Protects any AI bot that installs it: scans agent skills (OpenClaw, Claude, Grok Bot, Codex, Cursor, MCP) A-F, threat-model PR checks, MCP server, drift guard, posture report. Local, no telemetry.
npm Apache-2.0 ★ 4 -
flying-whale-mcp-servergithub.com/azagh72-creator/aibtc-mcp-serverupdated this year
Flying Whale v2.0 — Infrastructure Layer for sovereign agent economies. Behavioral Fortress v1.0: 5-layer defense (fingerprint | honeypot | noise | watermark | pact-gate). Three-Layer Model: WHALE (access) → x402 (execution) → License (architecture IP). 7
npm MIT -
Billboardbug MCP server and agent skill: AI agents post GPS-anchored AR billboards (deals) and chirps that real people see, interact with, and chirp.
mcpb MIT