Skip to content

XportL

by xportl.io · remote · no sign-in to list tools · v1.2.0 · published by io.xportl

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

Final · 1Changes · 3
CompareRegistry entry

6 tools: 1 do something that can't be undone, 3 change things and 2 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

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

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

6 tools

Can't be undone 1Claude Code: ask
  • request_enterprise_demoSends the user's contact details and cluster summary to the XportL enterprise team to arrange a technical assessment or demo deployment.No findings

    Why it is in this group

    • The name "request_enterprise_demo" says "request": a word for a change.
    • The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
    Description, as the server wrote it
    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 what will be sent, and get their explicit agreement. Never call it without that agreement or with made-up details.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Changes things 3Claude Code: ask
  • calculate_fabric_degradation_costEstimates what silent fabric degradation (slow NCCL collectives, flapping links, congestion) costs a GPU cluster: throughput lost, GPU-hours and dollars per year, idle-GPU equivale…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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 and a sensitivity table. All assumptions are inputs with stated defaults.

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
  • check_cluster_compatibilityChecks 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…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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. Anything not on the published list is reported as 'review', never as supported.

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
  • recommend_checkpoint_intervalRecommends 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'…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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 wasted per day at the recommended and current intervals, and the daily saving.

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
Only reads 2Claude Code: allow
  • analyze_nccl_benchmarkAnalyzes nccl-tests / rccl-tests results (paste raw all_reduce_perf output, or give size/busbw points).No findings

    Why it is in this group

    • The name "analyze_nccl_benchmark" says "analyze": a word for reading.
    Description, as the server wrote it
    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 bandwidth, dips as message size grows and unstable run-to-run results, with likely causes. Returns a health status and a bandwidth-loss figure for calculate_fabric_degradation_cost.

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
  • get_xportl_overviewReturns 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 fabri…No findings

    Why it is in this group

    • The name "get_xportl_overview" says "get": a word for reading.
    Description, as the server wrote it
    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 links to the engineering guides on xportl.io.

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.2.0. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__xportl__get_xportl_overview",
      "mcp__xportl__analyze_nccl_benchmark"
    ],
    "ask": [
      "mcp__xportl__calculate_fabric_degradation_cost",
      "mcp__xportl__check_cluster_compatibility",
      "mcp__xportl__recommend_checkpoint_interval",
      "mcp__xportl__request_enterprise_demo"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as xportl. Review it before you use it.