# rank_sites

Deterministic multi-site ranking/optimization under constraints — the normalization contract that lets you compare sites across separate analyze_site calls WITHOUT dropping into code. Pass candidates you already enriched (each an object with lat/lng + metric fields like risk_resilience, water_stress, fiber_km — pull these from analyze_site + get_refined_queue and pass site_evaluation_handoff through untouched), hard constraints, and weighted objectives; get back _entity=ranked_sites: top_k ranked with rank, objective_score, per-field normalized{} (0-100 relative to the set), and normalization_basis. objectives use SIGNED weights: +weight maximizes a field (e.g. risk_resilience:1), -weight minimizes it (e.g. water_stress:-0.6, fiber_km:-0.4). constraints are hard filters, fail-closed on a missing field. Use for "pick the best N sites under constraints"; for one site use analyze_site; to get the candidate set first use get_refined_queue. SCORING MECHANICS (2026-07-11): a candidate missing a validated objective is weight-RENORMALIZED over the objectives it carries and the gap is DECLARED in missing_objectives (never silently scored 0); a candidate carrying none scores null and ranks last. percentile=true fields without a population baseline fall back to RELATIVE in-batch scoring (basis reported per-objective in objective_status). CANDIDATE CONTRACT: candidates may be {candidate_id: "cand_…"} entries from get_refined_queue — frozen identity (lat/lng/capacity_mw/fiber_km/iso) loads from the mint, your metrics overlay the rest; expired/unknown ids are dropped AND declared in candidate_contract, never re-resolved.

Agent View of the PolicyLayer registry record for `rank_sites`. HTML page: https://policylayer.com/tools/cloud-dchub-mcp-server/rank-sites

## Facts

- Tool: `rank_sites`
- Server: Mcp Server (`https://dchub.cloud/mcp`) — https://policylayer.com/tools/cloud-dchub-mcp-server.md
- Homepage: https://github.com/azmartone67/dchub-mcp-server
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server CORS policy: *
- Server rate-limited: no
- Parameters: 8
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `top_k` | integer | no | How many top-ranked sites to return (1-50, default 3) |
| `absolute` | boolean | no | false (default) = min-max normalize within THIS batch (best-in-set, NOT stable across runs). true = score on a FIXED 0-100 scale for CROSS-RUN-STABLE, auditable |
| `candidates` | object | no | Array of candidate objects. PREFERRED: {candidate_id: "cand_…", <your metric fields>} using ids from get_refined_queue — frozen coordinates/capacity/fiber_km lo |
| `objectives` | object | no | Weighted objectives {field: signedWeight} — +weight maximizes, -weight minimizes. e.g. {"water_stress": -0.6, "fiber_km": -0.4}. Omit with shortlist_name to reu |
| `percentile` | boolean | no | true = score each objective as its PERCENTILE against the viable-site POPULATION ("better than X% of viable sites") — the strongest cross-run + cross-region com |
| `constraints` | object | no | Hard filters {field: {min?, max?}} — a candidate missing a constrained field is dropped (fail-closed). e.g. {"risk_resilience": {"min": 70}, "estimated_ttp_mont |
| `shortlist_name` | string | no | Alternative to candidates: re-rank a SAVED shortlist (created via save_to_shortlist) in one shot — loads its sites (scoped to your API key) + reuses their saved |
| `require_complete` | boolean | no | true = DROP any candidate missing one or more of your (validated) objectives — dropped candidates are DECLARED in excluded_incomplete, never silent. Default fal |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "rank_sites",
    "arguments": {}
  }
}
```

## Why rank_sites is rated Medium

An AI agent can call rank_sites faster than any human can review: one bad instruction and it creates or modifies resources in Mcp Server by the hundred, each call as confident as the last.

## Use case

AI agents use rank_sites to create or update resources in Mcp Server, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Server environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Mcp Server:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "rank_sites": {
      "limits": [
        {
          "counter": "rank_sites_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Mcp Server (78)

- `standing_intent` — Destructive — https://policylayer.com/tools/cloud-dchub-mcp-server/standing-intent.md
- `compare_sites` — Execute — https://policylayer.com/tools/cloud-dchub-mcp-server/compare-sites.md
- `rank_markets` — Execute — https://policylayer.com/tools/cloud-dchub-mcp-server/rank-markets.md
- `unlock_more_data` — Financial — https://policylayer.com/tools/cloud-dchub-mcp-server/unlock-more-data.md
- `ai_capacity_index` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/ai-capacity-index.md
- `analyze_parcel` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/analyze-parcel.md
- `analyze_site` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/analyze-site.md
- `cluster_sites_by_latency` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/cluster-sites-by-latency.md
- `compare_isos` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/compare-isos.md
- `deal_autopsy` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/deal-autopsy.md
- `discover_tools` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/discover-tools.md
- `export_dataset` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/export-dataset.md
- `fetch` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/fetch.md
- `find_alternatives` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/find-alternatives.md
- `get_agent_registry` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/get-agent-registry.md
- `get_backup_status` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/get-backup-status.md
- `get_changes` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/get-changes.md
- `get_climate_intel` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/get-climate-intel.md
- `get_composite_site_score` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/get-composite-site-score.md
- `get_dchub_recommendation` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/get-dchub-recommendation.md
- `get_disaster_risk` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/get-disaster-risk.md
- `get_energy_prices` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/get-energy-prices.md
- `get_facility` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/get-facility.md
- `get_facility_risk_delta` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/get-facility-risk-delta.md
- `get_fiber_intel` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/get-fiber-intel.md
- `get_fiber_readiness` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/get-fiber-readiness.md
- `get_gas_economics` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/get-gas-economics.md
- `get_gas_index` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/get-gas-index.md
- `get_gas_intelligence` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/get-gas-intelligence.md
- `get_global_power` — Read — https://policylayer.com/tools/cloud-dchub-mcp-server/get-global-power.md
- …and 48 more: https://policylayer.com/tools/cloud-dchub-mcp-server.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=cloud-dchub-mcp-server · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/cloud-dchub-mcp-server