Itô Compute

Use the canonical Itô compute CLI or MCP server. ECC does not implement a parallel client, browser handoff, local simulation, reservation, workload runner, or inference server.

Install the canonical local package

ito-compute-cli is currently unpublished. Build it from its canonical repository instead of using npx, npm exec, or an unverified package:

git clone https://github.com/Ito-Markets/ito-cloud-runtime.git
cd ito-cloud-runtime/cli/ito-compute-cli
npm ci
npm run check

Set ECC_ITO_CLI_EXECUTABLE to the explicit absolute built entry:

/absolute/path/to/ito-cloud-runtime/cli/ito-compute-cli/dist/bin/ito.js

ECC never discovers this credential-bearing client through PATH. Inject ITO_API_KEY through 1Password or the launching process environment. Never put it in arguments, tracked files, MCP results, logs, or chat.

CLI workflow

Run ecc ito auth before the first operation.
Before ecc ito find, obtain explicit buyer authority to submit an RFQ.
- Require gpu, count, whole days, max-rate, nodes, gpus-per-node, storage-tb, start-window, form-factor, contract-type, fabric, region, and the split-fill decision.
- Require count == nodes * gpus-per-node; never derive topology.
- Use any only when the buyer explicitly accepts any fabric or region.
- Omitted --allow-split means false.

Run the live RFQ command:

ecc ito find \
  --gpu h200 \
  --count 8 \
  --nodes 1 \
  --gpus-per-node 8 \
  --days 30 \
  --storage-tb 1 \
  --start-window 2099-08-15 \
  --max-rate 3.00 \
  --form-factor bare_metal \
  --contract-type reservation \
  --fabric infiniband \
  --region us-east-1

Run ecc ito status to inspect RFQs and procurement orders. After an ambiguous transport failure, check status before repeating find.

Inventory prices are indicative. An RFQ is not reserved capacity. Treat a rate as fixed only when the canonical result contains a non-null firm quote.

MCP workflow

Build the canonical package, then configure the stdio server with an absolute path:

{
  "mcpServers": {
    "ito-compute": {
      "command": "node",
      "args": [
        "/absolute/path/to/ito-cloud-runtime/cli/ito-compute-cli/dist/bin/ito-mcp.js"
      ]
    }
  }
}

The server exposes only:

ito_auth
ito_find
ito_status

Use ito_auth, gather explicit buyer authority and every hard constraint, call ito_find, then poll with ito_status when needed.

Unsupported operations

The supported client surface cannot lock quotes, reserve capacity, execute workloads, qualify nodes through ECC, or serve inference. Do not invent additional tools or a purchase path. Do not substitute a browser or fixture when the local CLI is missing or a live operation fails. Report the missing capability and stop.

Files1

1 files · 1.0 KB

Select a file to preview

Overall Score

86/100

Grade

A

Excellent

Safety

88

Quality

85

Clarity

87

Completeness

82

Summary

The Itô Compute skill guides agents to query GPU inventory, submit RFQs (Request for Quote), and check procurement status through a canonical CLI or MCP server. It enforces strict authentication and prevents credential exposure by requiring environment-based API key injection and explicit build paths, avoiding package registry dependencies.

Static Analysis Findings

1 finding

Patterns detected by deterministic static analysis before AI scoring. Hover over any finding code for detailed information and remediation guidance.

Command Injection

SEC-011Dynamic Shell Eval

Shell eval/exec of dynamic content

SKILL.mdexec`

80% confidenceCWE-94: Code Injection

Detected Capabilities

git clone from external repositoryCLI execution (ecc ito auth, find, status)Environment variable injection (ITO_API_KEY)MCP server configuration and invocationAuthentication workflow

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

find gpu inventorysubmit compute rfqcheck rfq statush100 h200 capacityitô gpu pricing

Risk Signals

INFO

SEC-011: Shell exec of dynamic content detected (backtick syntax in markdown)

SKILL.md | inline code formatting

Referenced Domains

External domains referenced in skill content, detected by static analysis.

github.com

Use Cases

Find available H100/H200 GPU capacity across regions
Submit authenticated fixed-rate RFQ with buyer authority validation
Check RFQ and procurement order status after submission
Query live inventory pricing and node topology constraints
Validate split-fill and fabric/region constraints before RFQ

Quality Notes

Strong credential security discipline: API key injection via environment only, never in arguments/logs/chat
Clear scope boundaries: explicitly lists unsupported operations (quote locking, workload execution, inference)
Well-documented constraints: requires explicit buyer authority before RFQ, validates topology rules (count == nodes * gpus-per-node)
Practical workflow: auth → gather constraints → find → status polling with clear steps
Prevents package registry risks: mandates local build from canonical source rather than npm install
Clear error handling guidance: 'check status before repeating find' after transport failure
Excellent security posture: builds trust through transparency about what CLI does and does not support

Model: claude-haiku-4-5-20251001Analyzed: Jul 24, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

ito-compute