Server providing Argo CD integration for MCP clients.
Nothing to run from here
XportL is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
6
tools declared
—
trust score
remote
at its publisher
—
calls last 7d
What it does
GPU fabric tools: NCCL benchmark analysis, degradation cost, cluster compatibility, XportL facts.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http xportl-mcp https://xportl.io/mcp
# 2 — ask your agent for something these tools do
# get_xportl_overview, analyze_nccl_benchmark, calculate_fabric_degradation_cost and 3 more
XportL costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
XPAll 1 server
xportl1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http xportl-mcp https://xportl.io/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
6 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| topic | string | no | Section to return. Default 'all'. |
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 heal
| Parameter | Type | Required | Notes |
|---|---|---|---|
| raw_output | string | no | 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 | no | Alternative to raw_output: measured points as {size_bytes, busbw_gbs}. |
| collective | string | no | Collective that was benchmarked. Default all_reduce. |
| fabric | string | no | Inter-node fabric and per-port speed. Use 'other' with link_gbps for anything else. |
| link_gbps | number | no | Per-NIC link speed in Gb/s. Overrides the speed implied by fabric. |
| nodes | integer | no | Number of nodes in the run. Detected from raw_output when omitted. |
| gpus_per_node | integer | no | GPUs per node. Detected from raw_output when omitted; default 8. |
| nics_per_node | integer | no | Compute-fabric NICs per node (rails). Default: one per GPU. |
| expected_busbw_gbs | number | no | Expected healthy bus bandwidth in GB/s, e.g. from an acceptance test. Overrides the line-rate reference; required to judge single-node runs. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| gpu_count | integer | yes | Total GPUs in the cluster (or in the jobs being analyzed). |
| gpu_model | string | no | GPU model, used only to pick a default cost per GPU-hour when gpu_hour_cost_usd is not given. |
| gpu_hour_cost_usd | number | no | Actual fully-loaded cost per GPU-hour in USD (amortized hardware + power + facility, or cloud rate). Strongly preferred over the default. |
| utilization_pct | number | no | Share of hours the GPUs are running distributed jobs. Default 80. |
| comm_share_pct | number | no | 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 | no | Share of running time the fabric is degraded (flapping links, congestion, bad cables/optics, misrouted paths). Default 10. |
| bandwidth_loss_pct | number | no | Collective bus bandwidth lost while degraded, vs. healthy. Measure with nccl-tests (see analyze_nccl_benchmark). Default 40. |
| recovery_pct | number | no | 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 25 |
| training_run_days | number | no | Optional: planned wall-clock length of one training run on this cluster, to show how many days degradation adds to 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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| fabrics | array | yes | Every interconnect the GPU jobs use, e.g. ['infiniband','nvlink']. efa = AWS Elastic Fabric Adapter. |
| gpu_vendor | string | yes | GPU vendor. |
| collective_library | array | no | Collective communication libraries in use. Default ['nccl']. |
| linux_kernel | string | no | Host kernel version as printed by uname -r, e.g. '5.15.0-105-generic'. Leave empty for non-Linux hosts or if unknown. |
| host_os | string | no | Host operating system on the GPU nodes. |
| deployment | string | yes | Where the cluster runs. |
| host_access | string | no | 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. |
| gpu_count | integer | no | Total GPUs, for context. |
| orchestrator | string | no | Job scheduler / orchestrator, for context. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| gpu_count | integer | yes | GPUs in the training job. |
| checkpoint_write_minutes | number | yes | Time training is blocked while a checkpoint is written, in minutes. With asynchronous checkpointing, use only the blocking part. |
| restart_minutes | number | no | Time from a failure to training resuming: detection, rescheduling, process start and checkpoint load, in minutes. Default 20. |
| job_mttf_hours | number | no | 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. |
| current_interval_minutes | number | no | Current checkpoint interval in minutes, to compare against the recommendation. |
| gpu_hour_cost_usd | number | no | Cost per GPU-hour in USD. Default 2.75. |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | The person's full name. |
| string | yes | Work email address. | |
| company | string | yes | Company or organization. |
| role | string | no | Job title, e.g. 'Director of ML Infrastructure'. |
| phone | string | no | Phone number, optional. |
| cluster_gpus | integer | no | Approximate number of GPUs in the cluster(s). |
| fabric | string | no | Fabric(s) and GPU types, e.g. 'NDR InfiniBand + NVLink, H100'. |
| interest | string | yes | What they want from XportL. |
| summary | string | yes | 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 | yes | Must be true. Only set it after showing the user exactly what will be sent and the user agreed to share it with XportL. |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install XportL or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
—Grade not published
No rule-by-rule report on file for this release
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
1.0.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish XportL can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.