# XportL (remote · xportl.io)

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

- Trust score: 79/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `xportl.io`: 79/100 (this document), [markdown](https://verifymcp.io/servers/io-xportl-xportl/xportl.md), [page](https://verifymcp.io/servers/io-xportl-xportl/xportl)

## Channel facts

- Endpoint: `https://xportl.io/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.2.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 75/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1985 tokens (~330/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 57/100
  - Stability observed for 17 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the XportL MCP server?

XportL is a hosted endpoint at https://xportl.io/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

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

### Cursor

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

### VS Code

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

### Codex

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

### opencode

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

### OpenClaw

```bash
openclaw mcp add io-xportl-xportl --url 'https://xportl.io/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-xportl-xportl:
    url: "https://xportl.io/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "io-xportl-xportl": {
      "Transport": "http",
      "Url": "https://xportl.io/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add io-xportl-xportl -t streamable-http -u 'https://xportl.io/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 76, 0)

- [security regression] DNSSEC: unverified → fail

### 2026-10-29 (score 76, +1)

- [security regression] DNSSEC: fail → unverified

### 2026-10-27 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-22 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (6)

### `get_xportl_overview` (~105 tokens)

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.

Input parameters:

- `topic` (string): Section to return. Default 'all'.

### `analyze_nccl_benchmark` (~379 tokens)

NCCL Benchmark Analyzer

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.

Input parameters:

- `collective` (string): Collective that was benchmarked. Default all_reduce.
- `expected_busbw_gbs` (number): Expected healthy bus bandwidth in GB/s, e.g. from an acceptance test. Overrides the line-rate reference; required to judge single-node runs.
- `fabric` (string): Inter-node fabric and per-port speed. Use 'other' with link_gbps for anything else.
- `gpus_per_node` (integer): GPUs per node. Detected from raw_output when omitted; default 8.
- `link_gbps` (number): Per-NIC link speed in Gb/s. Overrides the speed implied by fabric.
- `nics_per_node` (integer): Compute-fabric NICs per node (rails). Default: one per GPU.
- `nodes` (integer): Number of nodes in the run. Detected from raw_output when omitted.
- `raw_output` (string): Raw stdout of an nccl-tests or rccl-tests run (e.g. all_reduce_perf -b 8 -e 8G -f 2 -g 1). Paste it unchanged; rank/host lines are used to detect node count.
- `results` (array): Alternative to raw_output: measured points as {size_bytes, busbw_gbs}.

### `calculate_fabric_degradation_cost` (~390 tokens)

Fabric Degradation Cost Calculator

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.

Input parameters:

- `bandwidth_loss_pct` (number): Collective bus bandwidth lost while degraded, vs. healthy. Measure with nccl-tests (see analyze_nccl_benchmark). Default 40.
- `comm_share_pct` (number): Share of a healthy training step spent in collective communication that is NOT overlapped with compute. Typically 10 to 40% for large-scale training. Default 25.
- `degraded_time_pct` (number): Share of running time the fabric is degraded (flapping links, congestion, bad cables/optics, misrouted paths). Default 10.
- `gpu_count` (integer, required): Total GPUs in the cluster (or in the jobs being analyzed).
- `gpu_hour_cost_usd` (number): Actual fully-loaded cost per GPU-hour in USD (amortized hardware + power + facility, or cloud rate). Strongly preferred over the default.
- `gpu_model` (string): GPU model, used only to pick a default cost per GPU-hour when gpu_hour_cost_usd is not given.
- `recovery_pct` (number): Recovery scenario: share of the degradation-induced throughput loss you expect to recover by detecting and acting on degradation sooner. A planning assumption, not a measured XportL result. Default 2…
- `training_run_days` (number): Optional: planned wall-clock length of one training run on this cluster, to show how many days degradation adds to it.
- `utilization_pct` (number): Share of hours the GPUs are running distributed jobs. Default 80.

### `check_cluster_compatibility` (~315 tokens)

Cluster Compatibility Check

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.

Input parameters:

- `collective_library` (array): Collective communication libraries in use. Default ['nccl'].
- `deployment` (string, required): Where the cluster runs.
- `fabrics` (array, required): Every interconnect the GPU jobs use, e.g. ['infiniband','nvlink']. efa = AWS Elastic Fabric Adapter.
- `gpu_count` (integer): Total GPUs, for context.
- `gpu_vendor` (string, required): GPU vendor.
- `host_access` (string): Can you run a privileged agent on the GPU hosts? eBPF needs root or CAP_BPF/CAP_PERFMON. 'none' = fully managed service with no host access.
- `host_os` (string): Host operating system on the GPU nodes.
- `linux_kernel` (string): Host kernel version as printed by `uname -r`, e.g. '5.15.0-105-generic'. Leave empty for non-Linux hosts or if unknown.
- `orchestrator` (string): Job scheduler / orchestrator, for context.

### `recommend_checkpoint_interval` (~252 tokens)

Checkpoint Interval Advisor

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.

Input parameters:

- `checkpoint_write_minutes` (number, required): Time training is blocked while a checkpoint is written, in minutes. With asynchronous checkpointing, use only the blocking part.
- `current_interval_minutes` (number): Current checkpoint interval in minutes, to compare against the recommendation.
- `gpu_count` (integer, required): GPUs in the training job.
- `gpu_hour_cost_usd` (number): Cost per GPU-hour in USD. Default 2.75.
- `job_mttf_hours` (number): Measured mean time between job-interrupting failures for a job this size, in hours. If omitted, it is estimated from Meta's published 2024 cluster reliability data.
- `restart_minutes` (number): Time from a failure to training resuming: detection, rescheduling, process start and checkpoint load, in minutes. Default 20.

### `request_enterprise_demo` (~281 tokens)

Request an 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.

Input parameters:

- `cluster_gpus` (integer): Approximate number of GPUs in the cluster(s).
- `company` (string, required): Company or organization.
- `email` (string, required): Work email address.
- `fabric` (string): Fabric(s) and GPU types, e.g. 'NDR InfiniBand + NVLink, H100'.
- `interest` (string, required): What they want from XportL.
- `name` (string, required): The person's full name.
- `phone` (string): Phone number, optional.
- `role` (string): Job title, e.g. 'Director of ML Infrastructure'.
- `summary` (string, required): What they need in a few sentences: cluster, symptoms, workloads, timeline, and any results from this conversation (benchmark status, cost estimate, compatibility verdict).
- `user_confirmed` (boolean, required): Must be true. Only set it after showing the user exactly what will be sent and the user agreed to share it with XportL.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/io-xportl-xportl/xportl#diagnostics

## Score history

- 2026-11-05: 79
- 2026-11-04: 79
- 2026-11-03: 78
- 2026-11-02: 78
- 2026-11-01: 77
- 2026-10-31: 77
- 2026-10-30: 76
- 2026-10-29: 76
- 2026-10-28: 75
- 2026-10-27: 75
- 2026-10-26: 74
- 2026-10-25: 74
- 2026-10-24: 73
- 2026-10-23: 73
- 2026-10-22: 73
- 2026-10-21: 72
- 2026-10-20: 72
- 2026-10-19: 71

## Common questions

### What is the XportL MCP server?

XportL is an MCP server listed in the public MCP registry as io.xportl/xportl. GPU fabric tools: NCCL benchmark analysis, degradation cost, cluster compatibility, XportL facts. This page covers its hosted endpoint (https://xportl.io/mcp).

### Is the XportL MCP server safe to use?

XportL scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the XportL MCP server expose?

XportL exposes 6 tools: get_xportl_overview, analyze_nccl_benchmark, calculate_fabric_degradation_cost, check_cluster_compatibility, recommend_checkpoint_interval, request_enterprise_demo. Their descriptions and schemas cost roughly 1,722 tokens of context every time the server is loaded.

### Does the XportL MCP server require authentication?

No. We connected to XportL without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the XportL MCP server still maintained?

XportL is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://xportl.io/mcp
- Website: https://xportl.io/mcp-server/
- Changelog RSS feed: https://verifymcp.io/servers/io-xportl-xportl/xportl.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-xportl-xportl/xportl.json
- HTML version of this page: https://verifymcp.io/servers/io-xportl-xportl/xportl