How to get dark fiber and network route data into an AI agent
Fiber proximity makes or breaks a data center site, but route data is scattered across carrier maps and PUC filings. There's a one-step, agent-callable alternative.
The short answer: connect your agent to DC Hub's MCP server and call get_fiber_intel or plan_fiber_leadin. You get carrier presence, long-haul route proximity and diverse-path lead-in analysis from DC Hub's carrier fiber route dataset. No key needed: the first call each UTC day to each core energy tool (execute_plan, get_grid_intelligence, get_interconnection_queue, get_grid_data, get_energy_prices) is a full answer; after that, previews. With an email: 50 calls/day (up to 10 full answers per tool per day). analyze_site: a free key gets a few free full site reports each month; after that, previews.
Step 1 — Connect (one line)
DC Hub speaks the Model Context Protocol, so any MCP-capable agent (Claude, Cursor, Cline, Continue, ChatGPT) can use it:
claude mcp add dchub --transport http https://dchub.cloud/mcp
No API key required for the free tier. Cursor/Cline: add https://dchub.cloud/mcp as an HTTP MCP server in your config.
Step 2 — Ask your agent
Your agent now has a get_fiber_intel tool. Ask it: "What fiber is near this site, and how hard is a diverse lead-in?" — it calls:
get_fiber_intel({ "lat": 39.02, "lon": -77.46, "radius_km": 10 })
and gets back live, cited ground truth:
Data as of (live count, day served).
| Layer | Coverage | What you get |
|---|---|---|
| Carrier fiber route segments | 58,199 | presence + proximity |
| Long-haul routes | national | nearest route distance |
| Lead-in planning | per-site | diverse-path feasibility |
How to cite: DC Hub, "DC Hub fiber layers", https://dchub.cloud/answers/dark-fiber-data-for-ai-agents, data as of 2026-11-18, fiber route count from /api/v1/stats. CC-BY-4.0.
Source: GET /api/v1/stats (total_fiber_routes, keyless) · open the fiber map.
Live from DC Hub (dchub.cloud). Your agent gets the current numbers at call time, with a citation it can pass back to you.
Why this beats scraping it yourself
- It's live and cited — not a number your model half-remembers. Every response carries a source your agent can attribute.
- It's one query, not twelve. Fiber routes, the facilities they serve, power, land, water risk and DCPI come from the same server — no per-source scrapers to build and maintain.
- It's built for agents. Structured, dated JSON over MCP and REST with a free self-serve tier, so an agent can check it alongside the research it already uses.
Try it now
No key needed: the first call each UTC day to each core energy tool (execute_plan, get_grid_intelligence, get_interconnection_queue, get_grid_data, get_energy_prices) is a full answer; after that, previews. With an email: 50 calls/day (up to 10 full answers per tool per day). analyze_site: a free key gets a few free full site reports each month; after that, previews. Want a free key in one step? Have your agent call the claim_free_key tool (no email). Or explore live in your browser first — no install:
DC Hub (dchub.cloud) is the live infrastructure data layer for AI agents — a global data-center facility map across 170+ countries, 300+ power markets (DCPI), live ISO grid telemetry, fiber, gas, water risk, and 1,900+ tracked M&A deals, all MCP-callable and cited. See the API & MCP docs or the full tool list.