AI and agents MCP servers

    MCP servers that give AI agents memory, reasoning tools, models and other agents to work with.

    This directory lists MCP servers, not LicenseSaaS listings. For software available for licensing and white-labeling, browse the marketplace.

    14365 servers

    • Agent Guardrail

      Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.

      Runs locally · Developer tools · AI and agents

    • Agent Guardrail MCP Server

      Action-level governance for AI agents -- control what they DO, not what they SAY

      Runs locally · AI and agents · Developer tools

    • Agent Guards

      All six agent guard suites in one local MCP server, with optional cloud intelligence.

      Runs locally · Developer tools · AI and agents

    • Agent Guestbook

      Read and verify the Blue Cloud Cyber agent guestbook, and sign one Ed25519 entry per UTC day.

      Runs locally · AI and agents

    • Agent Guild

      See and steer Claude Code, Codex, Antigravity, Grok, Docker Agent and shell sessions in Agent Guild.

      Runs locally · Developer tools · AI and agents

    • Agent Handoff MCP

      Bounded, auditable handoffs between AI agents through a local MCP server.

      Runs locally · AI and agents · Developer tools

    • Agent Harness

      MCP chaos-testing toolkit. Default: simulated demo. Configure proxy mode to test a real agent.

      Runs locally · Developer tools · AI and agents

    • Agent Harnesses

      Agent-harness picks, decision guides, setup templates, and skills; live GitHub/HN discovery.

      Runs locally · Developer tools · AI and agents

    • agent haven

      A place for AI agents: an open forum and direct messages encrypted in the agent's own client.

      Runs locally · AI and agents

    • Agent Immune

      AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening

      Runs locally · AI and agents · Developer tools

    • Agent Inbox

      A real email inbox for AI agents: human-approved sends, untrusted-by-default inbound.

      Runs locally · AI and agents · Communication

    • Agent Incident Reporter Mcp

      Signed, hash-chained, tamper-evident AI incident records. EU AI Act Article 73 serious-incident repo

      Runs locally · Developer tools · AI and agents · Deprecated

    • Agent Index

      P2P Agent Index MCP — publish and search decentralized web indexes over libp2p.

      Runs locally · Developer tools · Data and search

    • Agent Infra Mcp

      18 tools: agent memory, API drift detection, and HMAC-signed trust receipts

      Runs locally · AI and agents · Developer tools

    • Agent Intern

      Delegate from Claude Code to Gemini, Codex, Copilot, Cursor and opencode CLIs as sub-agents.

      Runs locally · Developer tools · AI and agents

    • Agent Interop Runtime

      Coordinate coding agents through a local MCP server while keeping accounts and workspaces separate.

      Runs locally · Developer tools · AI and agents

    • Agent JSON Reliability

      Deterministic inspect, safe repair, and JSON Schema validation for agent JSON. No LLM.

      Runs locally · AI and agents · Developer tools

    • Agent Knowledge

      Cross-session memory for AI agents - knowledge graph, scoring, semantic search

      Runs locally · AI and agents · Developer tools

    • Agent Lagoon Mcp

      Check your AI agent into a lobster resort archipelago. Chat, bottles, guilds. Watch live in 3D.

      Runs locally · Developer tools · Communication

    • Agent Lease

      Keep Claude Code and Codex off each other's files: hook-enforced path leases, presence, messages.

      Runs locally · Developer tools · AI and agents

    • Agent Link

      Bidirectional AI agent collaboration — spawn and communicate with any agent CLI

      Runs locally · Developer tools · AI and agents

    • Agent Loop Mcp

      Agentic memory manager. Install Skill: npx skills add meharajM/agent-loop-mcp

      Runs locally · AI and agents · Developer tools

    • Agent Lsp

      Language servers as 66 code-intelligence tools for AI agents, CI-verified on 32 languages.

      Runs locally · Developer tools · AI and agents

    • Agent Magnet

      Behavioral memory layer for AI tools. Learns preferences and context across Claude, Cursor, Codex.

      Runs locally · AI and agents · Developer tools

    • Agent Mail Gateway

      Self-hosted email for AI agents: own IMAP/SMTP mailbox per key, allow lists, calendar invites.

      Runs locally · AI and agents · Developer tools

    • Agent Mandate Verification

      Verify a proposed action against a signed Agent Mandate without executing or mutating accounts.

      Runs locally · Developer tools · AI and agents

    • Agent Marketplace

      A marketplace where AI agents find complementary agents, form teams, and complete real work.

      Runs locally · AI and agents · Communication

    • Agent MCP Gateway

      On-demand tool discovery for all your MCPs and per-subagent MCP controls to preserve context window.

      Runs locally · Developer tools · AI and agents

    • Agent Mcp Hub

      One MCP server bridging the Codex, Cursor, OpenCode, Claude, and Antigravity CLI agents

      Runs locally · AI and agents · Developer tools

    • Agent Memory

      Git-native project memory for AI coding agents: Markdown source of truth, reviewable, secret-safe.

      Runs locally · Developer tools · AI and agents

    Source: the official MCP Registry (registry.modelcontextprotocol.io). Entries are published by their owners and not checked by LicenseSaaS.