# XportL

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

- name: io.xportl/xportl
- version: 1.2.0
- connection class: R0 (autonomous)
- trust: 81/100 flags: no-repository
- quality: 85/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.xportl%2Fxportl
- tools: https://api.protogrid.dev/v1/servers/io.xportl%2Fxportl/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

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


## Trust

- hygiene: 80
- liveness: 94
- freshness: 100
- provenance: 55
- drivers: +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.

## Quality 85/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 93 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 6 of 6 tools declare readOnlyHint or destructiveHint
- warn `tools.directory_hints`: 1 of 6 tools declare all four hints; missing: check_cluster_compatibility (destructiveHint); get_xportl_overview (destructiveHint); calculate_fabric_degradation_cost (destructiveHint); …
- pass `tools.token_cost`: about 2,916 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 1 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 6, about 2,916 tokens to load them all
- tool set hash: e2589aa0dda1f06c36ab48aa8e01c1b9
- tools last changed: 2026-10-19T09:03:46.133Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.xportl/xportl.svg)](https://protogrid.dev/servers/io.xportl/xportl)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-19 `recommend_checkpoint_interval` added
  - 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.
- 2026-10-19 `calculate_fabric_degradation_cost` changed (description, inputSchema)
  - 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: 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.
- 2026-10-19 `analyze_nccl_benchmark` changed (description)
  - 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: 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.
- 2026-10-19 `get_xportl_overview` changed (description, inputSchema)
  - 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: 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: https://api.protogrid.dev/v1/servers/io.xportl%2Fxportl/changes

## Remotes

- https://xportl.io/mcp (streamable-http, auth none, reachable true, uptime30d 0.85714287)

## Packages

_none_

## Tools (6)

- `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 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`: 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`: 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`: 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`: 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.