Tollmint
Per-call data for agents: graded behavioural science, dark-pattern detection, web fetch, geocode.
| Endpoint | https://api.tollmint.com/mcp (streamable-http) |
|---|---|
| Registry version | 0.1.0 |
| Now | 24 tools · grade D (57) · pin ts_7f483ad3238ccbad93b931c0169a1cbb · protocol 2025-06-18 |
| First / last listed | 2026-11-01 00:23 UTC / 2026-11-01 00:23 UTC |
| Grade over time | 2026-11-01: D (57), 24 tools |
Is this your server? Own a server? ToolFit hosted watch re-checks it every 24 h ($0.25 per 30 days) or 6 h ($0.60) and sends you an HMAC-signed webhook when its tools or grade change: POST https://api.youraitools.co/toolfit/v1/watch. To opt out, see About & opt-out.
Tools: tollmint_catalog tollmint_quote psych_dark-pattern-detect psych_cognitive-load psych_trust-signals psych_effects psych_biases psych_dark-patterns psych_enforcement psych_heuristics psych_cta-score content_ai-score design_ai-slop-detect web_fetch verify_compliance-scan ref_geocode legal_ai-disclosure legal_claims legal_subscriptions legal_messaging legal_accessibility legal_scraping psych_page-audit content_humanize
tollmint_catalog | List every Tollmint product with its price, sourcing class, evidence grading, latency SLO and input schema. Free — this call costs nothing. Call it first to see what is available and what it costs. params: none |
tollmint_quote | Get the exact price of a specific call before making it. Free — this call costs nothing. The quoted price is binding: you will never be charged more than it. params: product*, input |
psych_dark-pattern-detect | Scan a live page or raw HTML for deceptive design. Returns each detected pattern with the evidence quoted from the markup, the regulation it trips, and the honest alternative. Fully deterministic — no model call, so results are reproducible and the same page always scores the same. Returns a clean/review/fail verdict suitable for gating a deploy. Names the patterns that need a full user flow to as params: url, html, jurisdiction, fail_above_severity |
psych_cognitive-load | Measure the mental effort a page demands before a decision can be made: form fields, competing choices, interactive density, and reading burden. Deterministic and reproducible — the same markup always scores the same, so the number is usable for tracking a page over time or against a competitor. Choice count is weighted logarithmically per Hick's law rather than linearly, which is the law's most c params: url, html |
psych_trust-signals | Check which trust signals a page carries and which it omits — pricing visibility, privacy and terms, contact routes, cancellation terms. Each gap is returned with the inference a visitor draws from its absence, because under ambiguity aversion missing information is read as adverse rather than neutral: a hidden price is inferred to be a high one. Deterministic, model-free, and reproducible. Costs params: url, html |
psych_effects | Query a curated corpus of behavioural science effects. Every entry carries its canonical citation, replication status (robust / mixed / contested / failed), effect size, and boundary conditions. Effects that failed replication are included and labelled, not hidden — filter with actionable_only to exclude them. Free — this call costs nothing. No account or payment required. params: domain, replication_status, actionable_only, max_manipulation_baseline, search, limit, offset |
psych_biases | Cognitive biases with their mechanism, the conditions that trigger them, documented countermeasures, and an exploitation-risk score. Every entry carries its citation and replication status. Use to audit a decision process, to harden a system against manipulation, or to check your own reasoning. Free — this call costs nothing. No account or payment required. params: domain, replication_status, actionable_only, search, limit, offset |
psych_dark-patterns | Deceptive-design taxonomy with the regulation each pattern trips (EU DSA Art. 25, UCPD, FTC ROSCA and the Negative Option Rule), the signals that detect it in markup or copy, a severity score, and the honest alternative that achieves the same business goal. Use before shipping conversion changes, or to audit a competitor. Free — this call costs nothing. No account or payment required. params: category, min_severity, jurisdiction, search |
psych_enforcement | Regulatory enforcement actions over deceptive interface design, each citing the regulator’s own document: the law and article, the company, the penalty, and what was actually on the screen. Includes dismissals, vacated rules and findings of lawfulness, which mark where the line sits and which fine-only lists omit. Also reports patterns prohibited but never enforced, and cases excluded for want of params: pattern, jurisdiction, outcome, boundary_only, min_penalty |
psych_heuristics | Interaction-design laws with their formulae, sources, and design implications — Fitts, Hick, Jakob, Tesler, Doherty. Includes the common misapplications, since these are misquoted more often than they are wrong. Separate from the effects corpus because these are engineering constraints, not contested empirical claims. Free — this call costs nothing. No account or payment required. params: search, with_formula |
psych_cta-score | Score call-to-action text against a curated behavioural-science corpus. Checks verb framing (outcome versus effort), friction words introduced at the point of commitment, hedging, ownership framing, and length — each finding citing the effect it rests on and that effect's replication status, so a recommendation grounded in a contested result is visibly weaker than one grounded in a robust one. Sep params: text*, context, surrounding_text |
content_ai-score | Measure how mechanically a piece of text reads across 19 stylistic signals: sentence-length variance (burstiness), em-dash rate, negative parallelism, copula avoidance, the characteristic AI vocabulary cluster, hedged superlatives, significance inflation, puffery, vague attribution, over-signposting, formatting tics, and more. Returns a per-sentence breakdown naming which signal each one tripped. params: text*, include_sentences |
design_ai-slop-detect | Score how closely a page matches the documented 2025-2026 AI/template design fingerprint: the Tailwind indigo-violet gradient, a default sans with no display pairing, the badge/hero/three-card/steps/testimonial/pricing skeleton, glassmorphism, uniform border radii, emoji feature bullets, round-number social proof with no attribution, and abstract illustration in place of the product. Each finding params: url, html, fail_above_score |
web_fetch | Fetch a URL and return the main content as clean markdown, with navigation, cookie banners, footers, and related-post chrome removed. Extracts title, byline, publication date, and excerpt. Content detection is driven by link density rather than class names, so it survives CSS refactors. Reports how much of the page was retained and whether it had to fall back to the full body, so you can tell a cl params: url, html, include_links, max_words |
verify_compliance-scan | Check marketing copy, or a live page, against 225 curated regulatory rules covering AI-content disclosure, advertising claim substantiation, subscriptions and price display, unsolicited messaging, accessibility, and automated data collection. Every finding cites the instrument and article plus a primary-source URL, and reports whether that URL resolved when the corpus was built. Crucially it also params: url, html, text, jurisdiction, areas |
ref_geocode | Convert a free-form address or place name into coordinates with normalised address components, a calibrated confidence score, and precision classification (rooftop / street / locality / region / country). Deduplicates OSM elements and flags ambiguous queries with the competing alternatives. Data from OpenStreetMap. Costs $0.000800 per call. params: query*, limit, country_codes |
legal_ai-disclosure | Binding obligations worldwide to disclose, label, or watermark AI-generated content — EU AI Act Art. 50, California SB 942 and AB 2013, China’s 2025 labelling Measures, South Korea’s AI Basic Act, India’s 2026 IT Rules. Each row gives the exact trigger condition, what must be done, the exemptions, the penalty ceiling, and whether anyone has been enforced against yet. Includes forward dates for obl params: jurisdiction, status, dead_only, verified_only, search, limit |
legal_claims | Which marketing claims legally require evidence, and what evidence suffices. Covers superlatives, health and efficacy, "free", environmental and carbon-neutral claims, reference and "was/now" pricing, "up to X%", reviews and testimonials, country of origin, guarantees, and AI-capability claims. Each row gives the regulator’s own evidentiary standard, the common way advertisers fail it, and enforce params: jurisdiction, status, dead_only, verified_only, search, limit |
legal_subscriptions | Rules on subscription sign-up, auto-renewal, cancellation, and total-price display across US federal, US states, EU, UK, France and Germany — with the numbers: how many days before renewal a reminder is due, how many clicks cancellation may take, what must be in the price. Critically, it records that the FTC’s "Click-to-Cancel" rule was vacated on 2025-07-08 before it ever took effect, along with params: jurisdiction, status, dead_only, verified_only, search, limit |
legal_messaging | When a commercial email, SMS, or call may lawfully be sent, by channel and jurisdiction. The field that matters is consent_model: the US is opt-out for email, Canada and the EU are opt-in, and Germany applies opt-in to B2B while France and the Netherlands do not. Applying the US model abroad is a breach. Includes opt-out deadlines, permitted calling hours, whether a private right of action exists params: jurisdiction, status, dead_only, verified_only, search, limit |
legal_accessibility | Accessibility duties and the cases brought under them: ADA Titles II and III, Section 508, the European Accessibility Act in force since 2025-06-28, EN 301 549, UK and Canadian regimes — with the WCAG version and conformance level each one actually incorporates, the microenterprise and undue-burden carve-outs, and compliance dates still ahead. Enforcement rows include the FTC’s $1M action against params: jurisdiction, status, dead_only, verified_only, search, limit |
legal_scraping | What courts have actually held about scraping, crawling, and training-data acquisition. Answers questions in the form an engineer asks them: does ignoring robots.txt create liability, does a browsewrap bind a bot, is public data outside the CFAA. Records binding scope honestly — a Ninth Circuit holding is not US law — and tracks the full history of hiQ v LinkedIn, which is routinely cited as makin params: jurisdiction, status, dead_only, verified_only, search, limit |
psych_page-audit | Audit a live page or raw HTML for conversion psychology. Returns measured cognitive load, detected dark patterns with the specific regulation each trips and the evidence found in the markup, a trust-signal gap list, and ranked findings tied to graded behavioural effects. Findings may only cite effects from our corpus, and citations are attached from our data rather than generated — so a reference params: url, html, goal, jurisdiction |
content_humanize | Rewrite text for tone, cadence, and brand voice while preserving meaning exactly. Returns a before/after analysis: burstiness, hedge and transition density, abstract-noun ratio, plus the specific sentences that read mechanically and which signals they tripped. Reports signals the rewrite failed to clear rather than hiding them. Declines academic manuscripts and requests to defeat AI detection — en params: text*, intended_use*, voice, reading_level, preserve_meaning |
Entries describe changes in tool definitions. They are not statements about a server, its quality or its author. The grade measures how the tool definitions fit model providers (token cost, schema compatibility, confusable names) as scored by the ToolFit engine at the time of the listing. JSON: append .json. Opt-out: how or hello@youraitools.co.