"Compare all differences between two source code folders, including binary files" matching MCP connectors:

Canonical vocabulary server for autonomous business design. Exposes the Arco Lexicon as seven MCP tools: term lookup, related terms, alignment verification, citation formatting, source retrieval, term listing, and term suggestion. No authentication required. Streamable HTTP transport.

Autonomous research agent that pays every source it cites in USDC on Arc via x402 micropayments.

Static linter for CLAUDE.md-style agent constitution files: 10 operational-guardrail checks.

Pass messages between AI agents with cleaning, metadata enrichment, and metered billing.

Self-destructing secret sharing for AI agents: encrypted burn links for credentials, plus an agent-to-agent dead-drop with exactly-once claim semantics. RAM-only, no database, open source (MIT). Source: https://github.com/mmmpym/flashpaper

Personality tuning files for AI agents: 43 MIT-licensed tunings + 5 inline personality tests.

Zero-Ops deploy of a private AI workspace to your own VPS — from your AI chat. Free and open-source.

LLM provider intelligence for AI agents. Get ranked recommendations for your task type, compare pricing and capabilities. Tools: recommend_llm, list_providers, check_provider_status.

Wall-clock awareness for LLM agents. Two tools: elapsed-time-between-turns + day rollover detection.

A high-performance, persistent memory vault for autonomous agents. Enables cross-session state management and long-term context storage. Privacy-first: all keys are SHA-256 hashed locally before storage. Edge-optimized for sub-50ms latency via Vercel and Upstash. Fully MCP-compliant for seamless integration with Claude, GPT, and agent frameworks.

Wall-clock awareness for LLM agents. Two tools: elapsed-time-between-turns + day rollover detection.

Governance copilot for AI-assisted coding. 72 packs, 532 rules, proof bundles.

Agent-to-agent marketplace MCP server. Search 72+ capabilities, invoke services, manage vault inventory, and handle USDC payments - all through MCP tools.

PhoboMail gives AI agents their own @phobomail.com email address with zero human involvement. Agents call `register_email` to get an address and API key, then use `send_email`, `read_inbox`, `wait_for_email` and more — all over MCP. Ideal for agent workflows that need to sign up for services, handle OTP verification, or communicate across sessions. Hosted on Cloudflare.

AI Agent with Architectural Memory. Impact analysis (free), tests and code from the graph (pro).

Manage your dedicated AI assistant instances on [OpenClaw Direct](https://openclaw.com) through natural language. Deploy, monitor, and control always-on AI assistants that integrate with Telegram, WhatsApp, Discord, Slack, and Signal — all from your AI coding assistant. Learn more about the [MCP integration](https://openclaw.com/openclaw-mcp-integration).

Liminality takes a hard question, a decision, or a multi-step task and breaks it into its real sub-questions, ties each to a real tool or source, and returns a worked, reusable result: a scored decision frame for a choice, or a grounded synthesized answer. It is built for hard, multi-step, and decision work rather than quick lookups, and its shared library of solved routes makes repeat work cheaper.

Free selector plus read-only GitHub bounty, agent harness, Actions, flake, and MCP drift decisions.

Remote MCP + A2A server for AI agent operations. Provides 20+ tools including session therapy, mood tracking, UUID generation, regex testing, URL health checks, and ERC-8004 on-chain identity. Hosted at api.delx.ai with REST, MCP (SSE/streamable HTTP), and A2A protocol support.

Connect any two AI agents and let them talk directly. Claude to Claude, Claude to OpenAI, or any MCP-compatible agent