Modal
modal.com · Compute / VPS / Cloud Hosting modeIntegrated
Overall = mean of Interrupt Score 100 and Machine-Readability 36 → 68 / 100. The badge is set by the Interrupt Score alone — how scoring works.
Confidence: Provisional (0.3) — Based on Tier 0/1 evidence only (passive checks, no live transaction attempt) — treat the number as a triage signal, not a verified outcome.
Custody posture hasn't been assessed yet.
What your agent can do here
A plain-English read on the probe evidence — each verdict links to the finding behind it.
- Can your agent sign up on its own?Signup flow not yet inspected.
- Can your agent read it without a human?Little machine-readable surface.35.98/100
- Can your agent self-serve credentials or a token?Credentials path not yet inspected.
- Can your agent call it without a CAPTCHA?Unknown — live checkout not yet attempted.
Agent-readiness: Partially — an AI agent can use Modal, but little machine-readable surface.
Machine-Readability Score
Four check groups, equal weight: machine interfaces (OpenAPI, MCP server, llms.txt), browsing efficiency, element discoverability, and discovery/agent access (retrieval-bot robots.txt access, sitemap, schema.org). Each check is tagged with how strong the real-world evidence is that it changes agent behavior — proven, plausible, or emerging — grades are honesty labels, they never weight the score. A separate signal about ease of integration — it never enters the Interrupt Score or badge above.
- llms.txtemergingFound — modal.com/llms.txt
- llms-full.txtemergingFound — modal.com/llms-full.txt
- AGENTS.mdemergingNot provided
- A2A agent cardemergingNot provided
- MCP server (well-known or official registry)plausibleNot provided
- OpenAPI/Swagger specplausibleNot provided
- Rate-limit headersplausibleNot provided
- Structured JSON error responsesplausibleFound — modal.com/api/openapi.json
- OAuth authorization-server metadata (RFC 8414)provenNot provided
- API catalog (RFC 9727)emergingNot provided
- Agent-payment discovery (x402 / UCP)emergingNot provided
- Lean HTML transfer sizeplausible402 KB raw HTML (threshold 488 KB)
- Manageable DOM sizeplausibleNot provided
- High content-to-markup densityplausibleNot provided
- Content readable without JS executionprovenraw HTML holds 101% of rendered text (5803 vs 5739 chars; threshold 40%)
- Clean-content alternate (RSS/Atom/feed/markdown)plausibleNot provided
- Serves markdown on Accept: text/markdownplausibleNot provided
- Interactive elements are semanticplausible89/90 semantic (99%); 1 div/span click targets
- Form fields have accessible namesplausibleNot checked — no form fields on the representative page
- Inputs carry autocomplete hintsplausibleNot checked — no autocomplete-eligible inputs
- WebMCP tools (modelContext API)emergingNot provided
- AI retrieval/search fetchers allowed (robots.txt)provenno retrieval-fetcher blocks in robots.txt
- Sitemap (indexability)plausibleNot provided
- schema.org JSON-LD in raw HTMLplausible1 valid JSON-LD block(s) in raw (pre-JS) HTML
- Content-Signal directives (robots.txt)emergingNot provided
- Web Bot Auth key directoryemergingNot provided
- Discovery Link headers on homepageemergingNot provided
- robots.txt AI-crawler accessplausibleNot provided
Findings
How scoring works →Interrupt tier: Low-Interrupt — no interrupts found; interrupt score 100 / 100. It alone drives the badge above; the headline Overall score blends it 50/50 with Machine-Readability.
Every tool starts at 100. Each interrupt found subtracts a penalty of base weight × timing × hardness × evidence — the multiplier values below come from the same rubric tables the score is computed with, so the arithmetic in this matrix reproduces the number exactly.
No interrupts found — no penalties, so the score stays at 100.
Score is in the 95–100 band, but the Zero-Interrupt badge additionally requires a completed live Tier-2 transaction and no hard-blocker finding — no live Tier-2 transaction has verified this flow end to end yet, so it is capped at Low-Interrupt.
Checked — nothing found
A check only turns green when a probe tier capable of detecting that interrupt actually ran and found nothing. Not tested ≠ clean.
- CAPTCHA / bot-challengeNone found — checked at Tier 0 (passive scan)
- “Contact sales” wall (no self-serve path)None found — checked at Tier 0 (passive scan)
- ToS clause banning automated/bot accessNone found — checked at Tier 0 (passive scan)
- Identity / KYC verificationNone found — checked at Tier 0 (passive scan)
Not yet tested
- Email OTP verificationNo probe tier that can detect this has run yet — unknown, not clean
- SMS / phone OTP verificationNo probe tier that can detect this has run yet — unknown, not clean
- Mandatory phone verification callNo probe tier that can detect this has run yet — unknown, not clean
- Mailed physical code (postal)No probe tier that can detect this has run yet — unknown, not clean
- Manual approval queueNo probe tier that can detect this has run yet — unknown, not clean
- Mandatory redirect to vendor’s own siteNo probe tier that can detect this has run yet — unknown, not clean
- SSO-only signup, no API-key issuanceNo probe tier that can detect this has run yet — unknown, not clean
- Rate-limit-triggered manual reviewNo probe tier that can detect this has run yet — unknown, not clean
- One-time account / payment-method provisioningNo probe tier that can detect this has run yet — unknown, not clean
- Crypto wallet / key-custody setupNo probe tier that can detect this has run yet — unknown, not clean
Less-interrupting alternatives
Other Compute / VPS / Cloud Hosting tools in the same mode (integrated), ranked by Overall LLM-Friendliness — comparable to this listing because they share its usage mode.
- 85OverallRender
render.com · Compute / VPS / Cloud HostingMR69 - 75OverallCloudflare
cloudflare.com · Compute / VPS / Cloud HostingMR50 - 69OverallFly.io
fly.io · Compute / VPS / Cloud HostingMR38 - 69OverallAWS
aws.amazon.com · Compute / VPS / Cloud HostingMR38 - 69OverallRunPod
runpod.io · Compute / VPS / Cloud HostingMR46