Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

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

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

[mcp_servers.xportl]
url = "https://xportl.io/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "xportl": {
      "type": "remote",
      "url": "https://xportl.io/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "xportl": {
      "type": "http",
      "url": "https://xportl.io/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=xportl&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8veHBvcnRsLmlvL21jcCJ9"
}

{
  "servers": {
    "xportl": {
      "type": "http",
      "url": "https://xportl.io/mcp"
    }
  }
}

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

extensions:
  "xportl":
    enabled: true
    name: "xportl"
    type: streamable_http
    uri: "https://xportl.io/mcp"
    timeout: 300

Quality 85 / 100new

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene93 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations6 of 6 tools declare readOnlyHint or destructiveHint
warn
tools.directory_hints1 of 6 tools declare all four hints; missing: check_cluster_compatibility (destructiveHint); get_xportl_overview (destructiveHint); calculate_fabric_degradation_cost (destructiveHint); …
pass
tools.token_costabout 2,916 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stabilityn/a · weight 15

n/a
stability.changes, stability.rug_pulltool history recorded for 1 of the 7 days needed

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

6 tools, about 2,916 tokens to load them all · tool set e2589aa0dda1 · tools last changed 2026-10-19 · checked 2026-10-20 23:59 UTC

Tool changes

2026-10-19recommend_checkpoint_intervaladded
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.
2026-10-19calculate_fabric_degradation_costchangeddescription, input schema
before
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 (XportL publishes up to 40%) with a conservative case and a sensitivity table. All assumptions are inputs with stated defaults.
after · 91% of words in common
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.
2026-10-19analyze_nccl_benchmarkchangeddescription
before
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 100–800G), 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.
after · 97% of words in common
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.
2026-10-19get_xportl_overviewchangeddescription, input schema
before
Returns cite-ready facts about XportL from xportl.io: what it does, the problem it solves, the eBPF → ClickHouse → GNN → Rust enforcement architecture, supported fabrics/GPUs/collectives/kernels, use cases, FAQ and company details (parent company, stage, NVIDIA Inception, contacts).
after · 61% of words in common
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.

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 81 / 100

no-repository

provenance55

liveness94

freshness100

hygiene80

+dns-namespace +website +reachable +uptime-86% +updated-2d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://xportl.io/mcp` streamable-http	none	yes	86%	417 ms	2025-11-25	2026-10-20

Tools (6)

`analyze_nccl_benchmark`read-only	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.
`calculate_fabric_degradation_cost`read-only	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.
`check_cluster_compatibility`read-only	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.
`get_xportl_overview`read-only	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.
`recommend_checkpoint_interval`read-only	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.
`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 what will be sent, and get their explicit agreement. Never call it without that agreement or with made-up details.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "io.xportl/xportl",
  "title": "XportL",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://xportl.io/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.2.0",
  "websiteUrl": "https://xportl.io/mcp-server/",
  "description": "GPU fabric tools: NCCL benchmark analysis, degradation cost, cluster compatibility, XportL facts."
}