Model Context Protocol (MCP) Server Directory

Otari is Mozilla.ai's open-source LLM control plane with virtual keys, budgets, and built-in tools (code execution, web search). Portkey is an enterprise AI gateway with observability, guardrails, and managed hosting. Li...

Okta XAA (Extended AI Agent) is an identity-based security protocol that governs what AI agents can access, what actions they can take, and under whose authority. It uses ID-JAG (Identity-Justified Agent Grant) tokens to...

Autonomous procurement AI agents use large language models to execute end-to-end procurement workflows including supplier discovery, tender preparation, bid analysis, and contract negotiation. These agents reduce sourcin...

Codex CLI is OpenAI's open-source terminal coding agent with subagent support and sandboxed execution. Claude Code is Anthropic's CLI agent with the strongest SWE-bench scores. Gemini CLI is Google's fastest token-genera...

Microsoft Scout is an always-on AI agent that works continuously within Microsoft 365 without requiring user prompts. It monitors calendar, emails, deadlines, and project boards to proactively schedule meetings, prepare...

The AP2 Agent Payments Protocol is an open standard from Google that uses cryptographic Checkout and Payment Mandates to authorize AI agents to make purchases on behalf of users. It integrates with the Universal Commerce...

Bumblebee supply chain security refers to using Perplexity's open-source read-only inventory scanner to check macOS and Linux developer endpoints for known-bad packages, editor extensions, browser extensions, and MCP ser...

GitHub Copilot cloud agent is an autonomous coding agent that runs in a GitHub Actions-powered sandbox environment. When assigned a GitHub issue, it researches the repository, creates an implementation plan, writes code...

Google ADK vs Microsoft Agent Framework comparison evaluates two open-source agent orchestration frameworks for building and deploying multi-agent systems. Google ADK 2.0 uses a graph-based Workflow Runtime with explicit...

OpenCode coding agent tutorial runs OpenCode CLI v0.3 and DeepSeek-R1 (Local) using Ollama v0.5 to build a model-agnostic terminal assistant on a local machine. Unlike proprietary command-line assistants that require ext...

Semantic Router AI Agents use local embedding models and cosine similarity to match user intents to deterministic routes in under 4ms. By running route classification in-process with LangGraph JS, development teams bypas...

Pydantic AI vs LangChain comparison shows that Pydantic AI v0.1.0 offers superior type-safety and developer velocity for structured output tasks, while LangChain v0.4.0 remains highly effective for complex, modular tool...