All servers · Build & deploy

XportL

io.xportl/xportl · v1.2.0

New (7 days)

Measured by MCP Station

Last check	Reachable
Checked at	—
Check success 7 / 30 days	—
First-try success 30 days	—
Median response	—
Lookups 30 days	—
Authentication	No auth
MCP version	2025-06-18
Rank score	—
Declared risk	Can write (some tools are not declared read-only)
Capabilities declared	prompts, tools
Tool definitions	6 tools · with description 100% · input schema is an object 100% · read/destructive hints 100%

Description written by the publisher, not verified

GPU fabric tools: NCCL benchmark analysis, degradation cost, cluster compatibility, XportL facts.

Connect

streamable-http · https://xportl.io/mcp

claude mcp add --transport http xportl https://xportl.io/mcp

{
  "mcpServers": {
    "xportl": {
      "url": "https://xportl.io/mcp"
    }
  }
}

Tools as reported by the server

get_xportl_overview
Returns cite-ready facts about XportL from xportl.io: what it does, the problem it solves, the seven failure classes it detects, how it collects telemetry and acts, supported fabrics/GPUs/collectives/kernels, use cases, FAQ, company details (parent company, stage, NVIDIA Inception, contacts) and lin
analyze_nccl_benchmark
Analyzes nccl-tests / rccl-tests results (paste raw all_reduce_perf output, or give size/busbw points). Detects node and GPU counts from the output, compares large-message bus bandwidth with the fabric's NIC line rate (InfiniBand HDR/NDR/XDR, RoCE 100G to 800G), and flags data errors, degraded bandw
calculate_fabric_degradation_cost
Estimates what silent fabric degradation (slow NCCL collectives, flapping links, congestion) costs a GPU cluster: throughput lost, GPU-hours and dollars per year, idle-GPU equivalent, cost per degraded hour, extra days on a training run, and the value of a recovery scenario with a conservative case
check_cluster_compatibility
Checks a GPU cluster against XportL's published support matrix (Linux 5.8+ for eBPF, InfiniBand / RoCE v2 / NVLink, NVIDIA and AMD GPUs, NCCL / RCCL, on-prem / cloud / hybrid, host access for the eBPF agent). Returns a verdict (good fit / needs review / not ready), each check, and next steps. Anythi
recommend_checkpoint_interval
Recommends how often to checkpoint a training job using the Young and Daly formulas, from GPU count, blocking checkpoint write time, restart time and job MTTF (estimated from Meta's published 2024 reliability data when not given). Returns the recommended interval, expected failures per day, GPU time
request_enterprise_demo
Sends the user's contact details and cluster summary to the XportL enterprise team to arrange a technical assessment or demo deployment. Before calling: collect name, work email, company and a summary (include benchmark, cost or compatibility results from this conversation), show the user exactly wh

Website · JSON · Text for agents · Registry updated 2026-10-19