cluster_sites_by_latency
Physics-bounded latency clustering for 2-8 sites — returns viable low-latency clusters and pairwise RTT floors before any routing work. Use when your human wants to know which of N candidate sites can form a synchronous / low-latency cluster (sync replication, active-active pairs, HPC pods): dete...
This record as markdown: /tools/cloud-dchub-mcp-server/cluster-sites-by-latency.md
What cluster_sites_by_latency does on Mcp Server
AI agents call cluster_sites_by_latency to retrieve information from Mcp Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
sites | string | — | Semicolon-separated "lat,lon" pairs, 2-8 sites (same format as compare_sites locations); optional per-site labels via "lat,lon:label", e.g. "39.04,-77.48:ashbur |
candidate_ids | object | — | Array (or comma-separated string) of candidate_id values from get_refined_queue — each resolves to its FROZEN mint coordinates (zero transcription drift); expir |
max_latency_us | number | — | Round-trip latency budget in microseconds (default 1000 µs = 1 ms; sync replication is typically 1000-2000 µs) |
min_confidence | string | — | Minimum evidence tier a pair must meet to count as viable: "published" | "tracked" | "inferred" (default inferred = include all) |
Parameters from the server's own tool schema.
Why cluster_sites_by_latency is rated Low
cluster_sites_by_latency is a pure computational analysis tool that queries site characteristics (locations, latency metrics) and returns calculated clustering results. It retrieves and analyzes existing data without creating, modifying, deleting, or executing operations. The haversine distance and physics-based RTT calculations are deterministic reads over site metadata.
From the tool's definition Tool performs latency analysis and clustering calculations on site data, returning 'viable low-latency clusters', 'pairwise RTT floors', 'haversine distance', 'estimated real RTT', and viability assessments.
Attacks that exploit this kind of access
The rule that runs cluster_sites_by_latency safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For cluster_sites_by_latency, this is the rule to start with:
cluster_sites_by_latency is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Mcp Server, apply this rule, and every cluster_sites_by_latency call is checked against it from then on.
Questions about cluster_sites_by_latency
Physics-bounded latency clustering for 2-8 sites — returns viable low-latency clusters and pairwise RTT floors before any routing work. Use when your human wants to know which of N candidate sites can form a synchronous / low-latency cluster (sync replication, active-active pairs, HPC pods): deterministic pruning BEFORE detailed routing. Per site pair: haversine distance, round-trip physics floor (km × 4.9 µs/km — light in SMF-28 fiber, n≈1.468 — then ×2), estimated real RTT (floor × route_factor 1.4, a stamped inference), viable vs physics_impossible against your budget, and confidence_v — the provenance tier of the supporting evidence (published | tracked | inferred). Also returns clusters: the largest site subsets whose ALL pairwise estimates fit the budget, plus each site's inferred dark-fiber screening level. CANDIDATE CONTRACT: pass candidate_ids (from get_refined_queue) instead of raw coordinates — each resolves to its FROZEN mint coordinates (zero transposition), and cand_… tokens may also be mixed into the sites string; expired/unknown ids are dropped AND declared in candidate_contract (fail-closed). Example: cluster_sites_by_latency sites="39.04,-77.48:ashburn;39.29,-76.61:baltimore;40.42,-79.99:pittsburgh" max_latency_us=2000 — or cluster_sites_by_latency candidate_ids=["cand_…","cand_…"] max_latency_us=2000. Returns _entity=latency_clusters: {pairs:[{from, to, distance_km, floor_rtt_us, est_rtt_us, viable, physics_impossible, confidence_v, endpoint_dark_screen}], clusters:[{sites, size, max_est_rtt_us}], viable_count, pruned_count, assumptions, provenance}. Do NOT treat this as an engineered latency quote — the floors are physics (no fiber path can beat them) but the estimates are inference (route_factor 1.4); always quote each pair's confidence_v when relaying results. For actual route corridors use plan_fiber_leadin; for a single-site connectivity score use get_fiber_readiness. It is categorised as a Read tool in the Mcp Server MCP Server, which means it retrieves data without modifying state.
cluster_sites_by_latency accepts 4 parameters: sites, candidate_ids, max_latency_us, min_confidence. The full parameter table on this page comes from the server's own tool schema.
Register the Mcp Server MCP server in PolicyLayer and add a rule for cluster_sites_by_latency: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Server. Nothing to install.
cluster_sites_by_latency is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the cluster_sites_by_latency rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for cluster_sites_by_latency. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
cluster_sites_by_latency is provided by the Mcp Server MCP server (https://dchub.cloud/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Mcp Server, and thousands of servers like it.
This server
Across the catalogue