MCP Servers & Agent Skills – Find, Compare & Submit

The Model Context Protocol (MCP) and agent skills give AI assistants standardized ways to interact with external tools and services. MCP servers connect AI models to real-world data and actions, while agent skills add reusable capabilities — all with security and user control.
Learn more about the protocol →

Why MCP Servers & Agent Skills?

Enhanced Capabilities
MCP servers and agent skills let AI assistants interact with databases, cloud services, and APIs — expanding their ability to help with real-world tasks.
Secure Architecture
Built with security-first design, ensuring controlled access and protecting sensitive information across servers and skills.
Universal Standard
A unified protocol that works across different AI models and services, with servers and skills sharing a consistent integration experience.
Developer Friendly
Easy to implement and extend, with a growing ecosystem of community-contributed servers and skills for various services.

MCP Servers & Agent Skills

Submit your MCP server or agent skill

URL *
Title *
Description *
Keywords

optional

💻
ScamVerify
AI-powered scam and threat verification MCP server. Check phone numbers, URLs, text messages, and emails against aggregated threat intelligence from government complaint databases, malicious URL feeds, threat indicator databases, and carrier analysis. Returns risk scores, verdicts, confidence levels, and detailed signals. 8 tools, OAuth 2.1 + API key auth, Streamable HTTP transport.
💻
AML Watcher
AML Watcher MCP Server enables AI agents and agentic workflows to query AML Watcher's continuously updated compliance databases through a standardized MCP key. Get instant, structured access to 215+ sanctions regimes, 2.6M+ PEP profiles, and global risk intelligence spanning 235+ countries and territories. With multilingual search in 80+ languages and refresh cycles as fast as every 15 minutes, teams can apply jurisdiction-specific rules and risk appetite in real time. Purpose-built for compliance automation, no heavy integrations, predictable pricing, and machine-readable responses ready for AI decisioning.
💻
2O — Human Intelligence API for AI Agents
Connects AI agents to human domain experts for fact verification, empathy review, and real-world observation. 9 MCP tools. USDC payments on Base.
💻
Roundtable
Multi-model AI debate platform. Run structured discussions where GPT-4o, Claude, Gemini, DeepSeek, and 200+ other models debate your question, then a moderator synthesizes all perspectives into actionable insight. Provides 6 tools: consult, review_code, debug, architect, plan_implementation, assess_tradeoffs.
💻
402.bot Discovery Oracle
Discover and inspect live agent APIs. Search ranked endpoints, inspect trust and payment telemetry, and analyze agent usage through a read-only MCP surface built for x402 and agent API discovery.
💻
SiliconBridge
Human-in-the-loop API for AI agents. Routes CAPTCHAs, 2FA codes, identity checks, and approval gates to real human operators who solve them in under 60 seconds. REST API with webhook callbacks. Python SDK: pip install siliconbridge
💻
OpenClaw MCP Ecosystem (9 Remote Servers)
9 remote MCP servers on Cloudflare Workers. streamable-http transport, zero install. Servers: json-toolkit, regex-engine, color-palette, timestamp-converter, prompt-enhancer, openclaw-intel, fortune, moltbook-publisher, agentforge-compare. 25+ tools. Config: {"mcpServers":{"json-toolkit":{"url":"https://json-toolkit-mcp.yagami8095.workers.dev/mcp"},"regex-engine":{"url":"https://regex-engine-mcp.yagami8095.workers.dev/mcp"},"color-palette":{"url":"https://color-palette-mcp.yagami8095.workers.dev/mcp"},"timestamp-converter":{"url":"https://timestamp-converter-mcp.yagami8095.workers.dev/mcp"},"prompt-enhancer":{"url":"https://prompt-enhancer-mcp.yagami8095.workers.dev/mcp"},"openclaw-intel":{"url":"https://openclaw-intel-mcp.yagami8095.workers.dev/mcp"},"fortune":{"url":"https://openclaw-fortune-mcp.yagami8095.workers.dev/mcp"},"moltbook-publisher":{"url":"https://moltbook-publisher-mcp.yagami8095.workers.dev/mcp"},"agentforge-compare":{"url":"https://agentforge-compare-mcp.yagami8095.workers.dev/mcp"}}}
💻
Neural Memory
Biologically-inspired memory for AI agents. Spreading activation, Hebbian learning, 24 synapse types, memory lifecycle, contradiction detection, cross-language recall. 28 MCP tools. Zero LLM dependency.
💻
imessage-mcp
25 read-only tools for searching, analyzing, and exploring your entire iMessage history on macOS. Includes full-text search, conversation threads, contact analytics, temporal heatmaps, Spotify Wrapped-style year reviews, streak tracking, read receipts, reactions, reply threads, edited messages, and more. All local, privacy-first.
💻
DrainBrain MCP Server
Solana token rug-pull detection via ML ensemble (XGBoost + GRU temporal). 4 tools: scan, batch_scan, health, compare. Free tier available.

Frequently Asked Questions

What is an MCP server?
An MCP server is a lightweight service that exposes tools and resources to AI assistants via the Model Context Protocol.
How do I publish my MCP server or agent skill?
Click the Submit button, paste your GitHub URL, and fill in the details. We support both MCP servers and agent skills.
What are agent skills?
Agent skills are reusable instruction sets that give AI coding assistants specialized capabilities — like code review, migration guides, or deployment workflows. They’re typically distributed as SKILL.md files hosted on GitHub.
Which AI assistants support MCP servers?
Claude Desktop, Cursor IDE, Windsurf, OpenAI Agent SDK, and others that implement the protocol.
MCP vs. OpenAI “function‑calling” — what’s the difference?

Scope: OpenAI function‑calling is an API‑specific JSON protocol that lets ChatGPT call developer‑defined functions inside a single request cycle. MCP is an open, transport‑agnostic protocol that works with any LLM or IDE and supports persistent state, resource streaming and multi‑tool suites.

Transport: Function‑calling occurs over HTTPS. MCP supports STDIO for local processes and Server‑Sent Events for remote servers, enabling CLI‑level latency and bi‑directional progress events.

Security model: Function‑calling inherits the security context of the backend service. MCP adds tool‑level capability descriptors, allowing clients to review & approve each server before use.

Bottom line: choose MCP when you need an open ecosystem where any LLM, IDE or agent framework can reuse the same server; choose function‑calling for quick single‑model prototypes on OpenAI.

Are MCP servers safe to run locally?
Yes—each tool declares required environment variables and permissions up front; clients prompt you to approve before execution. For extra safety, run servers in Docker or point to hosted endpoints.
How does MCP compare to other AI interoperability protocols?
MCP is focused on context and data delivery between AI models and external systems, while protocols like Google’s Agent2Agent (A2A) target agent-to-agent communication. MCP is designed to complement, not replace, other standards in the AI ecosystem.