{
  "markdown": "<!-- mcp-name: me.route6/netid -->\n\n<p align=\"center\">\n  <img src=\"https://route6.me/brand/route6-icon.png\" alt=\"Route6\" width=\"96\" height=\"96\">\n</p>\n\n<h1 align=\"center\">Route6 — Agent Network Identity (MCP server)</h1>\n\n<p align=\"center\">\n  <b>Give your AI agent its own internet identity — a real public IPv6, a hostname, and a private network to reach other agents.</b>\n</p>\n\n<p align=\"center\">\n  <a href=\"https://route6.me\">route6.me</a> ·\n  <a href=\"https://docs.route6.me\">docs</a> ·\n  <a href=\"https://route6.me/pricing\">pricing</a> ·\n  <a href=\"https://github.com/route6me/examples\">examples</a>\n</p>\n\n---\n\nRoute6 is the networking layer for autonomous AI agents. Your organisation gets a dedicated public IPv6 /64, and each agent its own address in it, a `*.on.route6.me` DNS hostname, inbound port forwarding with TLS, and private mesh networking with other agents — all controlled by the agent itself through **23 MCP tools**. Free tier, no card required.\n\n**MCP registry:** `me.route6/netid` (remote server, domain-verified) · **Endpoint:** `https://gw.route6.me/mcp`\n\n## Quick start\n\n**1. Get an API key** — free account at [route6.me](https://route6.me) (no card).\n\n**2. Connect your MCP client** to the remote server:\n\n```json\n{\n  \"mcpServers\": {\n    \"route6\": {\n      \"url\": \"https://gw.route6.me/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_ROUTE6_API_KEY\"\n      }\n    }\n  }\n}\n```\n\nTransport is **streamable HTTP**; auth is the `Authorization: Bearer <key>` header. That's the whole setup — outbound HTTPS only, works behind any corporate firewall or NAT.\n\n### Claude Code\n\n```bash\nclaude mcp add --transport http route6 https://gw.route6.me/mcp \\\n  --header \"Authorization: Bearer $ROUTE6_API_KEY\"\n```\n\nOr install the full plugin (skill + tool reference): `/plugin marketplace add route6me/claude-plugin`\n\n### Cursor\n\n[![Add to Cursor](https://img.shields.io/badge/Add_to-Cursor-black?logo=cursor)](cursor://anysphere.cursor-deeplink/mcp/install?name=route6&config=eyJ1cmwiOiJodHRwczovL2d3LnJvdXRlNi5tZS9tY3AiLCJoZWFkZXJzIjp7IkF1dGhvcml6YXRpb24iOiJCZWFyZXIgWU9VUl9ST1VURTZfQVBJX0tFWSJ9fQ==)\n\nOne click, then replace `YOUR_ROUTE6_API_KEY` with your key. Or add the JSON block above to `~/.cursor/mcp.json`.\n\n### Cline / Continue / any MCP client\n\nUse the JSON block above (remote streamable-HTTP server + Bearer header). Detailed per-client guides: [docs.route6.me](https://docs.route6.me).\n\n### Optional: local helper clients\n\n```bash\nnpm i -g @route6/agent     # or: pip install route6\n```\n\nThe lite clients add an inbound HTTP/2 tunnel (`route6 tunnel start`) so your agent can *receive* traffic at its hostname from behind NAT. The MCP endpoint stays `gw.route6.me/mcp` either way.\n\n### Pro (Docker — full WireGuard tunnel)\n\n`docker compose up` with the [`route6me/netid`](https://hub.docker.com/r/route6me/netid) image (compose file from the dashboard) puts a real public /64 directly on the container's network stack. MCP endpoint becomes `http://localhost:3000/mcp`. Both paths expose the same tools.\n\n## Tools (28 total — 7 free · 17 Agent · 28 Team)\n\n| Tier | Tools |\n|------|-------|\n| **Free** (7) | `identity (action: get)` · `identity (action: set_ipv6)` · `identity (action: check_reputation)` · `net (action: ping)` · `net (action: traceroute)` · `net (action: dns_resolve)` · `web_fetch` |\n| **Agent $9/mo** (+10) | `hostname_register` · `port_forward (action: create)` · `port_forward (action: delete)` · `port_forward (action: list)` · `port_forward_tls` · `web_search` · `web_browse` · `scrape` · `smtp_allowlist` · `plan_upgrade` — plus `web_fetch` gains JS rendering + screenshots |\n| **Team $29/mo** (+11) | `team_status` · `team_ping` · `team_chat` · `team_whiteboard` · `team_task` · `team_project_task` · `team_roles` · `team_capability` · `team_events` · `team_metrics` · `team_loop` |\n\nWhat agents do with them:\n\n- **Get a public identity** — a dedicated, routed (not NATed) public IPv6 /64 from Route6's own ASN and IP space; rotate or pin any address inside it instantly.\n- **Be reachable** — register `my-agent.on.route6.me`, forward ports with real TLS; webhooks and OAuth callbacks that survive restarts (ngrok, but a permanent agent-native identity).\n- **Fetch the web cleanly** — `web_fetch`/`web_search`/`scrape` from the agent's own IP; DNS64/NAT64 handles IPv4 sites transparently.\n- **Form a private team mesh** — WireGuard mesh between agents plus a coordination layer: chat, shared KV whiteboard, task queues, roles, human-approved project tasks, and `team_loop` — a continuous receive loop so other agents (or humans in the dashboard) can push work to a connected agent in ~1s.\n\n## Facts worth knowing\n\n- **Free tier is permanent** — 7 tools, dedicated /64, 250 MB/mo, no card.\n- **Own infrastructure** — Route6 runs its own ASN and provider-independent address space; the abuse contact, WHOIS, and rDNS are ours. SMTP is blocked by default (allowlist, capped). No traffic inspection, no content logging.\n- **Not a proxy, not a VPN** — a network identity layer purpose-built for autonomous agents.\n- Operated by M3T Projekt d.o.o. · [Privacy](https://route6.me/legal/privacy) · [Terms](https://route6.me/legal/terms)\n\n---\n\n*This repository is the registry listing page for the Route6 MCP server (the server itself is a hosted remote). Docs: [docs.route6.me](https://docs.route6.me) · Usage examples: [route6me/examples](https://github.com/route6me/examples)*\n",
  "bytes": 5435,
  "sha": "f91243c1b19f288dce890eed49189497e9d1043c0e75fa1bd0797c53b300811d",
  "repo_slug": "route6me/mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_me_route6_netid_f800f071/readme"
}