# Tollmint (remote · api.tollmint.com)

Per-call data for agents: graded behavioural science, dark-pattern detection, web fetch, geocode.

- Trust score: 63/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `api.tollmint.com`: 63/100 (this document), [markdown](https://verifymcp.io/servers/com-tollmint-gateway/api.md), [page](https://verifymcp.io/servers/com-tollmint-gateway/api)

## Channel facts

- Endpoint: `https://api.tollmint.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## 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 2026-08-03.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 24 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 62/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 4828 tokens (~201/item across 24 items; 24 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 91/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 73% of tool parameters carry a description.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http com-tollmint-gateway https://api.tollmint.com/mcp
```

### Codex

```toml
[mcp_servers.com-tollmint-gateway]
url = "https://api.tollmint.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-tollmint-gateway": {
      "type": "remote",
      "url": "https://api.tollmint.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-tollmint-gateway --url https://api.tollmint.com/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-tollmint-gateway:
    url: "https://api.tollmint.com/mcp"
```

### Other

```json
{
  "mcpServers": {
    "com-tollmint-gateway": {
      "type": "http",
      "url": "https://api.tollmint.com/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.

### 2026-08-03 (score 63, +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.

### 2026-08-01 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 61, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 61, −1)

- [security] Tool “legal_ai-disclosure” rewrote its description, which is the text the model reads
- [security] Tool “legal_accessibility” rewrote its description, which is the text the model reads
- [security] Tool “legal_claims” rewrote its description, which is the text the model reads
- [security] Tool “legal_messaging” rewrote its description, which is the text the model reads
- [security] Tool “legal_scraping” rewrote its description, which is the text the model reads
- [security] Tool “legal_subscriptions” rewrote its description, which is the text the model reads
- [security] Tool “psych_biases” rewrote its description, which is the text the model reads
- [security] Tool “psych_dark-patterns” rewrote its description, which is the text the model reads
- [security] Tool “psych_effects” rewrote its description, which is the text the model reads
- [security] Tool “psych_enforcement” rewrote its description, which is the text the model reads
- [security] Tool “psych_heuristics” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 3863 → 4828
- [functional] Schema quality: excellent → good
- [functional] New tool “content_humanize”
- [functional] New tool “psych_cta-score”
- [functional] New tool “psych_page-audit”
- [functional] New tool “verify_compliance-scan”

### 2026-07-29 (score 62, +6)

- [security improvement] HTTPS: unverified → pass
- [security improvement] HSTS header: fail → pass
- [functional regression] Schema quality: 145 → 193
- [functional improvement] Tool coverage: 56% → 70%
- [functional improvement] Stability: unverified → 0.03
- [functional] Schema quality: good → excellent
- [functional] New tool “legal_accessibility”
- [functional] New tool “legal_ai-disclosure”
- [functional] New tool “legal_claims”
- [functional] New tool “legal_messaging”
- [functional] New tool “legal_scraping”
- [functional] New tool “legal_subscriptions”
- [functional] New tool “psych_enforcement”

### 2026-07-28 (score 56)

First indexed and scored.

## MCP tools (24)

### `tollmint_catalog` (~51 tokens)

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.

### `tollmint_quote` (~73 tokens)

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.

Input parameters:

- `input` (object): The input you intend to send
- `product` (string, required): Product id, e.g. "psych/effects"

### `psych_dark-pattern-detect` (~199 tokens)

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 assess rather than implying the site is clean. Costs $0.030000 per call.

Input parameters:

- `fail_above_severity` (integer): Sets verdict to "fail" when any pattern meets or exceeds this severity. Useful in CI.
- `html` (string): Raw HTML, if you already have it. Takes precedence over url.
- `jurisdiction` (string): Filter findings to a jurisdiction, e.g. "EU" or "US". Omit for all.
- `url` (string): Page to analyse. Fetched respecting robots.txt.

### `psych_cognitive-load` (~139 tokens)

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 common misapplication. Costs $0.025000 per call.

Input parameters:

- `html` (string): Raw HTML, if you already have it. Takes precedence over url.
- `url` (string): Page to analyse. Fetched respecting robots.txt.

### `psych_trust-signals` (~133 tokens)

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 $0.025000 per call.

Input parameters:

- `html` (string): Raw HTML, if you already have it. Takes precedence over url.
- `url` (string): Page to analyse. Fetched respecting robots.txt.

### `psych_effects` (~158 tokens)

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.

Input parameters:

- `actionable_only` (boolean): Return only effects safe to act on without human review (robust and mixed)
- `domain` (string)
- `limit` (integer)
- `max_manipulation_baseline` (integer): Exclude effects whose inherent manipulation risk exceeds this threshold
- `offset` (integer)
- `replication_status` (array)
- `search` (string)

### `psych_biases` (~138 tokens)

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.

Input parameters:

- `actionable_only` (boolean): Exclude effects that failed replication. Defaults true — countering a non-existent bias wastes effort.
- `domain` (string)
- `limit` (integer)
- `offset` (integer)
- `replication_status` (array)
- `search` (string)

### `psych_dark-patterns` (~140 tokens)

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.

Input parameters:

- `category` (string)
- `jurisdiction` (string): Filter to patterns regulated in a jurisdiction, e.g. "EU" or "US"
- `min_severity` (integer)
- `search` (string)

### `psych_enforcement` (~281 tokens)

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 a primary source. Use to tell whether a design choice has cost anyone money, and where. Free — this call costs nothing. No account or payment required.

Input parameters:

- `boundary_only` (boolean): Return only outcomes that bound the rule — dismissals, vacated rules, findings of lawfulness. These say what is permitted, which fines cannot.
- `jurisdiction` (string): Substring match: "EU", "UK", "US-federal", "US-state", "France", "India".
- `min_penalty` (integer): Minimum penalty in the record currency. Rows with no penalty are excluded.
- `outcome` (string)
- `pattern` (string): Pattern to look up. Accepts our taxonomy ids (roach-motel, fake-urgency, hidden-costs, trick-wording, forced-continuity) or enforcement terms (drip-pricing, preselected-consent, obstruction, privacy-…

### `psych_heuristics` (~99 tokens)

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.

Input parameters:

- `search` (string)
- `with_formula` (boolean)

### `psych_cta-score` (~229 tokens)

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. Separately flags urgency language the surrounding copy does not support, which is a regulatory exposure rather than merely a conversion cost. Deterministic: the same text scores identically every time, so two variants can be compared without sampling noise. Does not predict a conversion lift, because the corpus does not support that precision. Costs $0.012000 per call.

Input parameters:

- `context` (string): What the page is asking for, if it helps. e.g. "B2B SaaS signup, no card required".
- `surrounding_text` (string): Copy immediately around the CTA. Used to detect unsupported urgency claims.
- `text` (string, required): The call-to-action text, e.g. "Start your free trial".

### `content_ai-score` (~169 tokens)

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. Deterministic and model-free, so before-and-after comparisons across an edit are meaningful. NOT an AI detector — it reports stylistic properties, never authorship, and returns no verdict or probability. Authorship classifiers are unreliable and disproportionately misjudge non-native English writers. Costs $0.004000 per call.

Input parameters:

- `include_sentences` (boolean)
- `text` (string, required)

### `design_ai-slop-detect` (~212 tokens)

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 quotes the markup that produced it and names the move that breaks the pattern. Deterministic and model-free. Reports template convergence, never authorship — the same fingerprint appears in human sites built from the same tutorials. Costs $0.025000 per call.

Input parameters:

- `fail_above_score` (integer): Set a verdict of "fail" above this score. Useful for gating a design review in CI.
- `html` (string): Raw HTML, if you already have it. Takes precedence over url.
- `url` (string): Page to analyse. Fetched respecting robots.txt.

### `web_fetch` (~200 tokens)

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 clean extraction from a guess. Honours robots.txt; refuses private addresses and pages behind authentication. Costs $0.003000 per call.

Input parameters:

- `html` (string): Raw HTML, if you already have it. Takes precedence over url.
- `include_links` (boolean): Keep inline links as markdown. Disable to cut tokens when only prose matters.
- `max_words` (integer): Truncate the markdown at this many words. Truncation is reported.
- `url` (string): Page to analyse. Fetched respecting robots.txt.

### `verify_compliance-scan` (~284 tokens)

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 returns what is NOT law: rules commonly believed to be in force that were vacated, enjoined, or superseded — the FTC Click-to-Cancel rule, the California election-deepfake statutes, the DOT ancillary-fee rule. A scanner built by prompting a model asserts all three as live and sends you to rewrite compliant copy. Dead rules never enter the analysis and are reported separately with the reason they died. Reports rule conflicts and citations; does not determine liability. Costs $0.035000 per call.

Input parameters:

- `areas` (array): Limit the scan to these rule sets. Omit to check every one.
- `html` (string): Raw HTML, if you already have it. Takes precedence over url.
- `jurisdiction` (string): Restrict to rules for this jurisdiction. "any" checks all of them.
- `text` (string): Marketing copy to check. Supply this, or a url, or html.
- `url` (string): Page to analyse. Fetched respecting robots.txt.

### `ref_geocode` (~118 tokens)

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.

Input parameters:

- `country_codes` (array): ISO 3166-1 alpha-2 codes to restrict the search
- `limit` (integer)
- `query` (string, required): Free-form address or place name

### `legal_ai-disclosure` (~303 tokens)

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 obligations already enacted but not yet biting, and records the California election-deepfake laws that were struck down in 2025 and are still widely cited as live. Query before shipping generated content into a jurisdiction. Free — this call costs nothing. No account or payment required.

Input parameters:

- `dead_only` (boolean): Return only rules that are NOT live law — vacated, superseded, or still proposed. These are the rules most often wrongly believed to be in force.
- `jurisdiction` (string): Substring match, e.g. "EU", "UK", "US-federal", "California", "Germany".
- `limit` (integer)
- `search` (string): Free-text over summary, instrument and detail.
- `status` (string): Filter to one lifecycle state.
- `verified_only` (boolean): Only rows whose source URL resolved when last checked. Off by default: many primary sources (courts, national gazettes) block automated checkers, so "blocked" is not "bad".

### `legal_claims` (~278 tokens)

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 enforcement with penalties where it exists. Also records five widely repeated "you can’t say that" rules that no instrument actually supports. Free — this call costs nothing. No account or payment required.

Input parameters:

- `dead_only` (boolean): Return only rules that are NOT live law — vacated, superseded, or still proposed. These are the rules most often wrongly believed to be in force.
- `jurisdiction` (string): Substring match, e.g. "EU", "UK", "US-federal", "California", "Germany".
- `limit` (integer)
- `search` (string): Free-text over summary, instrument and detail.
- `status` (string): Filter to one lifecycle state.
- `verified_only` (boolean): Only rows whose source URL resolved when last checked. Off by default: many primary sources (courts, national gazettes) block automated checkers, so "blocked" is not "bad".

### `legal_subscriptions` (~297 tokens)

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 the vacated DOT ancillary-fee rule and the twice-delayed UK subscription regime. A model working from training data will assert all three as live law. Free — this call costs nothing. No account or payment required.

Input parameters:

- `dead_only` (boolean): Return only rules that are NOT live law — vacated, superseded, or still proposed. These are the rules most often wrongly believed to be in force.
- `jurisdiction` (string): Substring match, e.g. "EU", "UK", "US-federal", "California", "Germany".
- `limit` (integer)
- `search` (string): Free-text over summary, instrument and detail.
- `status` (string): Filter to one lifecycle state.
- `verified_only` (boolean): Only rows whose source URL resolved when last checked. Off by default: many primary sources (courts, national gazettes) block automated checkers, so "blocked" is not "bad".

### `legal_messaging` (~286 tokens)

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 (the difference between a regulator fine and a class action), and the FCC one-to-one consent rule vacated a day before it took effect. Free — this call costs nothing. No account or payment required.

Input parameters:

- `dead_only` (boolean): Return only rules that are NOT live law — vacated, superseded, or still proposed. These are the rules most often wrongly believed to be in force.
- `jurisdiction` (string): Substring match, e.g. "EU", "UK", "US-federal", "California", "Germany".
- `limit` (integer)
- `search` (string): Free-text over summary, instrument and detail.
- `status` (string): Filter to one lifecycle state.
- `verified_only` (boolean): Only rows whose source URL resolved when last checked. Off by default: many primary sources (courts, national gazettes) block automated checkers, so "blocked" is not "bad".

### `legal_accessibility` (~283 tokens)

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 an accessibility overlay vendor and a case where a site running an overlay was sued anyway, plus defence wins that mark the limits. Free — this call costs nothing. No account or payment required.

Input parameters:

- `dead_only` (boolean): Return only rules that are NOT live law — vacated, superseded, or still proposed. These are the rules most often wrongly believed to be in force.
- `jurisdiction` (string): Substring match, e.g. "EU", "UK", "US-federal", "California", "Germany".
- `limit` (integer)
- `search` (string): Free-text over summary, instrument and detail.
- `status` (string): Filter to one lifecycle state.
- `verified_only` (boolean): Only rows whose source URL resolved when last checked. Off by default: many primary sources (courts, national gazettes) block automated checkers, so "blocked" is not "bad".

### `legal_scraping` (~276 tokens)

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 making scraping legal and which hiQ ultimately lost on contract. Covers the EU text-and-data-mining exceptions and their opt-out. Free — this call costs nothing. No account or payment required.

Input parameters:

- `dead_only` (boolean): Return only rules that are NOT live law — vacated, superseded, or still proposed. These are the rules most often wrongly believed to be in force.
- `jurisdiction` (string): Substring match, e.g. "EU", "UK", "US-federal", "California", "Germany".
- `limit` (integer)
- `search` (string): Free-text over summary, instrument and detail.
- `status` (string): Filter to one lifecycle state.
- `verified_only` (boolean): Only rows whose source URL resolved when last checked. Off by default: many primary sources (courts, national gazettes) block automated checkers, so "blocked" is not "bad".

### `psych_page-audit` (~191 tokens)

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 is never invented. Names the patterns a static page cannot assess rather than implying the site is clean. Costs $0.120000 per call.

Input parameters:

- `goal` (string): What this page is meant to achieve, e.g. "free trial signups from CTOs"
- `html` (string): Raw HTML, if you already have it. Takes precedence over url.
- `jurisdiction` (string): Regulatory lens for dark-pattern flags. EU is strictest.
- `url` (string): Page to audit. Fetched respecting robots.txt.

### `content_humanize` (~217 tokens)

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 — enforced by structural checks on the submitted text, not by a policy the caller self-certifies against. Costs up to $0.026000 (metered per 1k_output_tokens; you are charged only for units used).

Input parameters:

- `intended_use` (string, required): Declared purpose. Recorded for analytics; it is not the safeguard. Requests are gated on document structure and supplied context, not on this value.
- `preserve_meaning` (boolean)
- `reading_level` (integer): Target US grade level for the rewrite
- `text` (string, required)
- `voice` (string): Target voice description, or a profile from content/brand-voice/extract

## Diagnostics

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

## Score history

- 2026-08-03: 63
- 2026-08-02: 62
- 2026-08-01: 62
- 2026-07-31: 61
- 2026-07-30: 61
- 2026-07-29: 62
- 2026-07-28: 56

## Links

- Remote endpoint: https://api.tollmint.com/mcp
- Repository: https://github.com/Iyonx/tollmint
- Website: https://tollmint.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-tollmint-gateway/api/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-tollmint-gateway/api/changelog.json
- HTML version of this page: https://verifymcp.io/servers/com-tollmint-gateway/api