AI & Agents MCP Servers for Zed

Multi-agent framework with persistent expert sessions and context isolation — MCP server for Claude Code

Analyzes codebases with tree-sitter and generates AGENTS.md files for AI coding agents.

Model Context Protocol (MCP) server for AgentStandard — browse and install certified AI agent packages

AgisHub — 34 pay-per-call tools for AI agents over x402 (USDC on Base). No API key, no signup.

MCP server for markdown CRUD operations on specification documents

AIOProductOS Agent — an MCP server that turns Claude Code, Cursor, or Codex into an assignable Backend/Frontend/Mobile/QA teammate inside

MCP server for AIProx Workflows — create and run multi-agent pipelines from Claude Desktop. Pay per execution in sats.

MCP server for AIRC protocol - Agent Identity & Relay Communication

MCP server for the aman AI companion ecosystem — identity, tools, workflows, guardrails, evaluation

plan_exact_design_extraction and extract_exact_design_document are tools to use @arc/design's exact-first pipeline directly in arc-mcp

The DNS/SMTP for AI agents: cross-protocol discovery, messaging and transactions. No middleman fees.

Adaptive Retrieval-Augmented Self-Refinement MCP Server — a closed-loop system that lets LLMs iteratively verify and correct their own

Ask-Me MCP Server - Human-in-the-Loop Model Context Protocol Server

MCP server for Assay Discovery and trust infrastructure tools.

AI Universal Runtime Architecture (AURA) - AI context management with intelligent model recommendations and standalone task management for

AI coding agent orchestration at scale. Karpathy optimization loops, multi-agent pipelines, DAG dependencies, autoscaling workers. Claude

mcp-bento is a composable Model Context Protocol (MCP) gateway that lets you hydrate a single HTTP endpoint with tools and prompts coming

Boundary MCP - a decision-making thinking engine that exposes reality's structure rather than giving advice

MCP server that connects to an OpenAI-compatible AI agent

MCP server letting an AI agent submit actions for multi-party human approval via Byliner. Cannot approve, reject, or delegate — by design.

Armor for your AI agent. Security verification, goal anchoring, drift detection, and session grading for OpenClaw and MCP-compatible agents.