# Free Agent Tools (remote · free-agent-tools.vercel.app)

21 free no-auth tools: pitch roast, Kyushu discount, Japan visa fee, luggage, tax-free.

- Trust score: 76/100 (medium)
- Change this week: +1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- remote · `free-agent-tools.vercel.app`: 76/100 (this document), [markdown](https://verifymcp.io/servers/sean0007-free-agent-tools/free-agent-tools.md), [page](https://verifymcp.io/servers/sean0007-free-agent-tools/free-agent-tools)

## Channel facts

- Endpoint: `https://free-agent-tools.vercel.app/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.5.0`

## 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 2026-10-17.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - 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**: 63/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 6082 tokens (~253/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**: 47/100
  - Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "japan_tax_free_refund_check" implies "refund" and declares readOnlyHint instead, contradicting what its own name says it does.
  - An AI judge read all 25 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Free Agent Tools MCP server?

Free Agent Tools is a hosted endpoint at https://free-agent-tools.vercel.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http sean0007-free-agent-tools 'https://free-agent-tools.vercel.app/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "sean0007-free-agent-tools": {
      "url": "https://free-agent-tools.vercel.app/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "sean0007-free-agent-tools": {
      "type": "http",
      "url": "https://free-agent-tools.vercel.app/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.sean0007-free-agent-tools]
url = "https://free-agent-tools.vercel.app/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sean0007-free-agent-tools": {
      "type": "remote",
      "url": "https://free-agent-tools.vercel.app/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add sean0007-free-agent-tools --url 'https://free-agent-tools.vercel.app/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  sean0007-free-agent-tools:
    url: "https://free-agent-tools.vercel.app/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "sean0007-free-agent-tools": {
      "Transport": "http",
      "Url": "https://free-agent-tools.vercel.app/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add sean0007-free-agent-tools -t streamable-http -u 'https://free-agent-tools.vercel.app/mcp'
```

### Other

```json
{
  "mcpServers": {
    "sean0007-free-agent-tools": {
      "type": "http",
      "url": "https://free-agent-tools.vercel.app/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.

### 2026-10-17 (score 76, 0)

- [functional regression] Schema quality: 230 → 253
- [functional] Server version: 1.7.0 → 1.8.0
- [functional] New tool “japan_dual_pricing_check”

### 2026-10-16 (score 76, 0)

- [functional regression] Schema quality: 204 → 230
- [functional] Server version: 1.6.0 → 1.7.0
- [functional] New tool “japan_tb_screening_check”

### 2026-10-15 (score 76, 0)

- [functional regression] Schema quality: 172 → 204
- [functional] Server version: 1.5.0 → 1.6.0
- [functional] New tool “japan_customs_allowance_check”

### 2026-10-14 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-13 (score 75, −1)

- [functional regression] Schema quality: 138 → 172
- [functional regression] Schema quality: 138 → 156
- [functional] Server version: 1.4.0 → 1.5.0
- [functional] Server version: 1.3.0 → 1.4.0
- [functional] New tool “kyushu_travel_discount_check”
- [functional] New tool “japan_luggage_check”

### 2026-10-12 (score 76, +1)

- [functional regression] Schema quality: 2268 → 2634
- [functional] Server version: 1.2.1 → 1.3.0
- [functional] New tool “japan_visa_fee_check”

### 2026-10-10 (score 75, −1)

- [functional] Destructive annotations: pass → 0
- [functional] Server version: 1.1.0 → 1.2.1
- [functional] New tool “japan_tax_free_refund_check”

### 2026-10-07 (score 76, +1)

- [functional regression] Schema quality: 1927 → 2124
- [functional] Server version: 1.0.0 → 1.1.0
- [functional] New tool “roast_pitch”

## MCP tools (24)

### `score_business_idea_moat` (~211 tokens)

Score a business idea (MOAT: fund, fix, or flee)

Score a business idea on Margin, Operations, Advantage, and TAM (1-10 each). 30+ = FUND IT, 20-29 = FIX IT, under 20 = FLEE IT. Returns the weakest factor, how to fix it, and red flags from pain / money / willingness-to-suffer checks. Educational rule of thumb, not financial advice.

Input parameters:

- `advantage` (number, required): Hard-to-copy edge (distribution, data, expertise), 1-10.
- `margin` (number, required): Net margin potential, 1-10.
- `money` (boolean): Buyers have money to spend? Default true.
- `operations` (number, required): How easily it runs without the founder, 1-10.
- `pain` (boolean): Fixes a measurable pain? Default true.
- `suffer` (boolean): Founder willing to push through a long build? Default true.
- `tam` (number, required): Market size and proof that people buy, 1-10.

### `roast_pitch` (~197 tokens)

Roast a startup pitch (five judges, one verdict, one change)

Paste a startup pitch (one to five sentences). Five fictional judges (Seed VC, Skeptical Customer, CTO, Your Competitor, Growth Lead) score it 1-10 with a short roast line each, then it returns a verdict (FUND IT / SHARPEN IT / REWRITE IT / ROASTED / BURNT TO A CRISP), the one change worth the most points, detected issues and strengths, and a share URL with an OG image. Deterministic, transparent rubric (specific customer, pain, numbers, traction, wedge, distribution, buzzwords, 'X for Y', blockchain), not an AI opinion. For fun and practice, not investment advice.

Input parameters:

- `category` (string): Optional category. 'crypto' softens the blockchain penalty.
- `pitch` (string, required): The pitch, one to five sentences.
- `stage` (string): Optional stage. Later stages are judged harder on traction.

### `price_headroom_check` (~166 tokens)

Price headroom from close rate

Is the business underpriced? Uses sales close rate (80%+ = way underpriced, ~30% = about right, under 25% = sales problem) to suggest a price range, and computes the profit multiple of a price rise after losing some customers, plus the break-even customer loss.

Input parameters:

- `closeRate` (number, required): Percent of proposals or sales calls that close.
- `customersLost` (number): Percent of customers expected to leave after the rise. Default 20.
- `netMargin` (number): Net margin percent today. Default 15.
- `newPriceMultiple` (number): New price as a multiple of the old (1.5 = +50%). Default 1.5.
- `price` (number, required): Current price, any currency.

### `thirty_day_cash_check` (~126 tokens)

Do customers fund growth? (30-day cash)

Compares cash collected in a new customer's first 30 days with acquisition cost plus 30-day cost to serve. 2x+ = SELF-FUNDING, 1-2x = BREAK-EVEN, under 1x = CASH-HUNGRY. Returns the gap to 2x and tips.

Input parameters:

- `cac` (number, required): Customer acquisition cost.
- `cash30` (number, required): Cash collected from a new customer in their first 30 days.
- `cogs30` (number): Cost to serve that customer for 30 days. Default 0.

### `email_list_reactivation_value` (~113 tokens)

What is an old email list worth?

Estimates buyers and revenue from one offer to past customers in low / mid / high scenarios, with an optional partner revenue share.

Input parameters:

- `buyRate` (number): Expected percent of reached contacts who buy. Default 1.
- `contacts` (number, required): Number of past contacts.
- `orderValue` (number, required): Average order value of the offer.
- `partnerShare` (number): Optional partner revenue share percent. Default 0.
- `reachable` (number): Percent of contacts still reachable. Default 70.

### `hotel_ota_commission_calculator` (~185 tokens)

Hotel OTA commission and direct-booking savings

For hotels, ryokan, guesthouses, and B&Bs: yearly room revenue, commission paid to OTAs (Booking.com, Expedia, Agoda...), commission as a share of revenue (HIGH / MED / LOW), and net savings from moving a share of OTA bookings to direct. Any currency.

Input parameters:

- `adr` (number, required): Average daily rate per occupied room.
- `commission` (number): Average OTA commission percent. Default 18.
- `directCost` (number): Cost of a direct booking as percent of revenue. Default 3.
- `occupancy` (number): Average yearly occupancy percent. Default 70.
- `otaShare` (number): Percent of room revenue booked via OTAs. Default 60.
- `rooms` (number, required): Number of rooms.
- `shift` (number): Percent of OTA bookings moved to direct. Default 20.

### `saas_self_host_savings` (~161 tokens)

Replace paid SaaS with open source: savings and payback

Give monthly spend per paid tool (ids: mixpanel, semrush, freshbooks, calendly, chargebee, typeform, pipedrive, gohighlevel, intercom). Returns the open-source swap for each (repo, license, caveat), yearly savings after hosting, setup hours and cost, break-even months, and a SWITCH / MAYBE / KEEP verdict.

Input parameters:

- `hostingPerMonth` (number): Estimated monthly server cost to self-host. Default 20.
- `hourlyRate` (number): Value of an hour of setup time. Default 50.
- `spend` (object, required): Map of tool id to monthly spend in dollars, e.g. {"mixpanel": 300, "intercom": 150}.

### `list_open_source_saas_alternatives` (~74 tokens)

List open-source alternatives to paid SaaS

Lists every covered paid tool (Mixpanel, Semrush, FreshBooks, Calendly, Chargebee, Typeform, Pipedrive/HubSpot, GoHighLevel, Intercom/Zendesk) with its open-source swap, GitHub repo, license, setup effort, and main catch.

### `ads_policy_notice_risk_check` (~98 tokens)

Google Ads / Meta Ads notice risk card

Paste the text of a Google Ads, AdSense, Merchant Center, or Meta (Facebook/Instagram) ads suspension, disapproval, or policy notice. Returns HIGH / MED / LOW risk, the platform, the policy phrases found with plain-language explanations, and a next-step checklist. Heuristic only; never suggests replacement accounts or files appeals.

Input parameters:

- `notice` (string, required): Full notice text. Remove account IDs and personal data.

### `app_store_wrapper_precheck` (~145 tokens)

App Store 4.2 / 4.3 / metadata rejection precheck

For Capacitor, WebView, PWA-shell, React Native, or AI-generated iOS apps: scores rejection risk under Guideline 4.2 (minimum functionality / web wrapper), 4.3 (spam / clone), and metadata, with reasons and how native each feature reads. Not legal advice; Apple decides.

Input parameters:

- `description` (string, required): One-line description of what the app does.
- `features` (array, required): Up to three key features, e.g. ["Home screen widget", "iOS share sheet", "Face ID lock"].
- `name` (string, required): App name.
- `stack` (string, required): How the app is built.

### `faceless_youtube_reality_check` (~154 tokens)

Faceless / AI YouTube channel reality check

Seven multiple-choice answers about a faceless or AI YouTube channel plan. Returns HIGH / MED / LOW expectation and monetization-policy risk with signals and myths to drop. Pushes back on viral '$10k/month with AI YouTube' claims. Not a ban prediction.

Input parameters:

- `estimates` (string, required): How VidIQ / SocialBlade earnings estimates are treated.
- `niche` (string, required): Niche.
- `revenueTiming` (string, required): When money is expected relative to the YouTube Partner Program.
- `scripts` (string, required): How scripts are made.
- `timeline` (string, required): Expected timeline.
- `visual` (string, required): Main visual style.
- `voiceover` (string, required): Main voiceover.

### `ai_infrastructure_bottlenecks` (~86 tokens)

AI infrastructure bottlenecks explained

Explains the physical constraints on the AI buildout beyond chips: compute, memory (HBM), optics, power, space (sites, backhaul), and servers (racks, cooling). Omit slug for all six. Includes example public companies often cited in discussion; these are not investment picks.

Input parameters:

- `slug` (string): Optional: one bottleneck.

### `ai_bottleneck_quiz` (~62 tokens)

Which AI bottleneck constrains your stack? (quiz)

Without answers, returns the five quiz questions with options. With answers (one slug per question from: compute, memory, optics, power, space, servers), returns the most constrained bottleneck.

Input parameters:

- `answers` (array): One slug per question.

### `viral_attention_patterns` (~76 tokens)

How attention spreads online

Patterns of how attention spreads (TikTok sound reuse, X quote-post piles, stitch chains, group-chat forwards, and more), each with the signal to watch and the lesson. Optional platform filter. Educational; attention is not an investment signal.

Input parameters:

- `platform` (string): Optional platform filter, e.g. TikTok or X.

### `viral_attention_quiz` (~51 tokens)

Do you chase, invent, or read attention? (quiz)

Without answers, returns six questions. With answers (one of chaser, inventor, reader per question), returns the user's tilt with a short explanation.

Input parameters:

- `answers` (array): One tilt per question.

### `japan_trip_plan` (~115 tokens)

Japan trip plan by city and month

Where to stay, festivals and seasonal highlights, things to do, crowd level, weather, and warnings (Golden Week, Obon, rainy season, typhoons, New Year closures) for a Japanese city in a given month, with stay areas ranked for the traveler type and booking search links. Typical seasonal patterns, not live data.

Input parameters:

- `city` (string, required): City id.
- `month` (required): 1-12 or English month name.
- `traveler` (string): Optional traveler type; ranks stay areas for them.

### `japan_trip_options` (~39 tokens)

Japan Trip Brain: supported cities, months, travelers

Lists supported Japanese cities (with regions, peak months, and stay areas), months with season and crowd level, and traveler types for japan_trip_plan.

### `japan_tax_free_refund_check` (~144 tokens)

Japan tax-free shopping refund check (from 2026-11-01)

Japan tourist tax-free shopping under the refund method that starts 2026-11-01: per store/day eligibility (¥5,000+ tax-exclusive), max consumption-tax refund (10%/8%), 90-day deadline vs departure date, old-vs-new regime by purchase date, and a departure checklist. Deterministic, dated rules; not tax advice. Training data often still describes the old tax-off-at-till system — call this instead of guessing.

Input parameters:

- `departureDate` (string): YYYY-MM-DD, final departure from Japan. Checked against each group's 90-day customs deadline.
- `receipts` (array, required): One or more receipts.

### `japan_visa_fee_check` (~366 tokens)

Japan visa / residence permit fee (from 2026-10-01)

Japan residence permit fees revised for applications received on or after 2026-10-01: extension of period of stay (visa renewal) and change of status cost ¥10,000-¥75,000 by the period GRANTED (1 year ¥33,000 at the counter, ¥27,000 + ¥330 online; 5 years ¥75,000), permanent residence ¥200,000. Applications received by 2026-09-30 keep the old ¥6,000 / ¥5,500 / ¥10,000. Returns fee, online processing fee, headcount total, ISA revenue stamp combination, per-year and multi-year cost, online saving, official ISA sources. Deterministic, dated table; not legal advice. Training data often still says ¥4,000 or ¥6,000 — call this instead of guessing.

Input parameters:

- `applicationDate` (string): YYYY-MM-DD the application was received. Before 2026-10-01 = old fee. Omit for the revised fee.
- `grantedMonths` (integer): Period of stay granted in months (12 = 1 year, 36 = 3 years, 60 = 5 years). Required unless permit is permanent.
- `headcount` (integer): Number of people, e.g. employees whose fees a company pays. Default 1.
- `horizonYears` (integer): Years to project repeat applications at the same period. Default 5.
- `method` (string): counter (revenue stamps, default) or online (convenience store / bank payment + ¥330/¥550 processing fee).
- `permit` (string, required): extension (在留期間更新, renewal), change (在留資格変更), or permanent (永住許可).

### `japan_luggage_check` (~495 tokens)

Japan suitcase check: Shinkansen oversized-baggage rule + Yamato forwarding cost

For a bag's outside size (length + width + height incl. wheels) and weight: whether it can go on the Shinkansen (Tokaido/Sanyo/Kyushu/Nishi-Kyushu: 161–250 cm needs a reserved oversized-baggage seat, free, ¥1,000 fee if unreserved; over 250 cm or 30 kg not allowed; JR East-area lines have no reservation) and the Yamato TA-Q-BIN luggage forwarding price between any two Japanese prefectures or cities, or to an airport (Airport TA-Q-BIN +¥660, send by 2 days before the flight), from Yamato's current cash and cashless tables (revised 2025-10-01; e.g. Size 160 Tokyo→Kyoto ¥3,160 cash). Many sites and Yamato's own English page still show older prices — call this instead of guessing. Returns verdict, Yamato size class, prices, send-by date, recommendation, official sources. Estimate, not official.

Input parameters:

- `departureDate` (string): YYYY-MM-DD flight date when sending to an airport; returns the send-by date.
- `dropOff` (boolean): true if you bring the bag to a Yamato office or convenience store (¥100 off).
- `from` (string): Origin prefecture or city (tokyo, kyoto, hakone, 東京都).
- `heightCm` (number): Outside depth in cm.
- `lengthCm` (number): Outside length in cm incl. wheels/handles (with widthCm + heightCm), or use totalCm.
- `line` (string): Shinkansen line you will ride. Default tokaido.
- `payment` (string): cash (default) or cashless (card / QR / e-money, cheaper).
- `pieces` (integer): Number of identical bags. Default 1.
- `to` (string): Destination prefecture/city, or airport id: haneda, narita, kix, itami, centrair, new-chitose, fukuoka-airport, naha-airport.
- `totalCm` (number): Length + width + height in cm if only the total is known.
- `weightKg` (number): Packed weight in kg (Yamato uses the larger of size and weight class).
- `widthCm` (number): Outside width in cm.

### `kyushu_travel_discount_check` (~497 tokens)

Kyushu travel discount (九州ふっこう応援割 2026): savings + date/channel eligibility

Japan's Kyushu Fukko Ouenwari travel discount after the 2026 Kumamoto earthquake: 50% off eligible stays and stay+transport packages in Fukuoka, Saga, Nagasaki, Oita, Miyazaki (60% in Kumamoto and Kagoshima), capped per person per trip at ¥20,000 (accommodation only or 1-night package), ¥30,000 (package 2+ nights), ¥35,000 (tour with stays in 2+ Kyushu prefectures). Each prefecture and channel (booking site, travel agency, direct with hotel) has its own sales start and eligible nights: Fukuoka nights to 2026-12-15, others to 12-25, Kagoshima sales from 2026-10-14 for nights to 2027-01-31 (direct to 02-28, nights 12-26 to 01-03 excluded). Bookings made before sales start are never discounted. Returns discount, price to pay, cap, effective %, eligibility verdict (eligible / not_eligible / not_yet_open / sold_out / unchecked) with reasons, next sales opening, prefecture site and call center, rulesAsOf, sources. Newer than most training data — call this instead of guessing. Estimate; budgets can run out without notice.

Input parameters:

- `bookingDate` (string): YYYY-MM-DD date of booking (JST). Default today in Japan.
- `channel` (string): ota (booking site such as Rakuten Travel or Jalan, default), agency (travel agency), direct (with the hotel).
- `checkIn` (string): YYYY-MM-DD check-in date, for the eligible-nights check.
- `nights` (integer): Nights booked (0 = day trip, not eligible). Default 1.
- `prefecture` (string, required): Kyushu prefecture you stay in (for a multi-prefecture tour, the selling prefecture).
- `product` (string): lodging (宿泊単体, default), package (交通付宿泊: stay + flight/train), tour (周遊型: stays in 2+ Kyushu prefectures).
- `totalPriceJPY` (number, required): Booking total in yen for all travelers, before the discount (tax and service included).
- `travelers` (integer): People on the booking; children and infants count. Default 1.

### `japan_customs_allowance_check` (~868 tokens)

Japan customs duty-free allowance on arrival: within/over, duty estimate in yen, cash declaration

Japan Customs per-person duty-free allowance when entering Japan (as of 2026-10-14): alcohol 3 bottles of about 760 ml (2.28 L); cigarettes 200 OR cigars 50 OR heat-not-burn 10 packages (200 IQOS/glo sticks, 50 Ploom TECH capsules) OR other tobacco 250 g, more than one kind 250 g total; perfume 2 oz (about 56 ml); other goods ¥200,000 total overseas value, an item kind worth ¥10,000 or less in total is free and not counted, an article over ¥200,000 is fully dutiable. Under 20: no alcohol/tobacco allowance; under 6: only items for the child. Excess duty at the simplified rates: whisky/brandy ¥800/L, rum/gin/vodka ¥500/L, liqueur ¥400/L, distilled ¥300/L, wine/beer ¥200/L, cigarettes and sticks ¥15 each, capsules ¥50, other goods 15% of Customs value (price × 0.6), watches/golf clubs/PCs 10% consumption tax; not applied to articles with Customs value over ¥100,000, cigars or other tobacco. Cash and other means of payment over ¥1,000,000 (¥100,000 bound for North Korea) must be declared. Returns per-category within/over, excess, estimatedSimplifiedDutyJPY (+ High for the strict mixed-tobacco reading), tax-type breakdown truncated to ¥100 (reproduces Customs' ¥19,400 worked example), red/green channel, cashDeclarationRequired, warnings, assumptions, sources, rulesAsOf. Many guides still show pre-2021 tobacco limits — call this instead of guessing. Educational estimate; the Customs officer decides.

Input parameters:

- `ageYears` (number): Traveler age. Under 20 = no alcohol/tobacco allowance; under 6 = only items for the child. Default adult.
- `alcohol` (array): Several drinks: [{type, ml or bottles}]. Allowance goes to the highest-rate drink first.
- `alcoholBottles` (integer): Bottles of alcohol (assumed 760 ml each unless alcoholMl is given).
- `alcoholMl` (number): Total alcohol volume in ml (allowance 2,280 ml per adult).
- `alcoholType` (string): Drink type for the simplified rate. Default other (¥200/L).
- `boundForNorthKorea` (boolean): Leaving Japan for North Korea (declaration threshold ¥100,000).
- `cashJPY` (number): Cash (yen + foreign in yen) one person carries.
- `cigarettes` (integer): Cigarettes (allowance 200).
- `cigars` (integer): Cigars (allowance 50).
- `goldBullionKg` (number): Gold bullion carried in kg (over 1 kg must be declared).
- `goods` (array): Other articles: overseas retail price of ONE article in yen, quantity, dutyFreeTariff true for watches / golf clubs / PCs, forChild for a child's items.
- `goodsTotalJPY` (number): Instead of goods: total overseas value of other articles (approximate).
- `hnbCapsules` (integer): Ploom TECH / with capsules (allowance 50).
- `hnbPackages` (integer): Heat-not-burn packs (allowance 10; 20 sticks or 5 capsules each).
- `hnbSticks` (integer): Loose IQOS / glo sticks (allowance 200).
- `hnbType` (string): What hnbPackages contain. Default sticks.
- `otherTobaccoGrams` (number): Pipe / other tobacco in grams (allowance 250 g).
- `paymentInstrumentsJPY` (number): Checks, travelers checks, promissory notes, securities in yen.
- `perfumeMl` (number): Perfume in ml (allowance about 56 ml; eau de toilette not counted).
- `perfumeOz` (number): Perfume in ounces (allowance 2 oz).
- `travelers` (integer): People in the same age band pooling allowances. Default 1.

### `japan_tb_screening_check` (~806 tokens)

Japan pre-entry TB screening (JPETS): do I need a TB Clearance Certificate for my COE or visa?

Japan Pre-Entry Tuberculosis Screening (JPETS, 入国前結核スクリーニング), rules as of 2026-10-15: nationals of the Philippines, Nepal, Viet Nam, Indonesia, Myanmar and China entering Japan as mid- to long-term residents (stay over 3 months; not Temporary Visitor, Diplomat, Official; re-entry permit holders excluded), plus Designated Activities No. 53 (Digital Nomad) and No. 54, must submit a TB Clearance Certificate from a designated Panel Clinic with the Certificate of Eligibility (COE) application, or with the visa application if there is no COE. Mandatory for applications filed from 2025-06-23 (Philippines, Nepal), 2025-09-01 (Viet Nam), 2027-01-04 (Indonesia, scheduled; Panel Clinics open 2026-11-02); Myanmar and China not announced. Temporarily exempt: Specified Skilled Workers (特定技能), EPA nurses/care workers, JET, JICA trainees, JDS, Japan Foundation invitees, embassy-recommended MEXT scholars, commissioned student training, Designated Activities No. 55, special-zone housekeepers, and anyone whose residence outside the 6 countries is documented. Technical intern trainees and students are NOT exempt. A COE filed before the mandatory date needs no certificate at the visa stage. Certificate valid 180 days from the chest X-ray (90 after close contact), checked at COE filing only. Returns verdict (required / not_yet_required / exempt / not_required), reasons, timeline, X-ray window and validity, documents, the Panel Clinic list (filter by city), notes, sources, rulesAsOf. Training data may predate the Indonesia start; call this instead of guessing. Educational guide, not legal or medical advice.

Input parameters:

- `applicationDate` (string): YYYY-MM-DD the COE (or direct visa) application is filed. Default today in Japan.
- `city` (string): Filter Panel Clinics by city, e.g. Jakarta, Surabaya, Hanoi, Ho Chi Minh City, Manila, Kathmandu.
- `closeContact` (boolean): Close contact with active infectious pulmonary TB within 2 months before the X-ray: validity 90 days.
- `hasReentryPermit` (boolean): Returning on a re-entry permit (incl. special re-entry): excluded.
- `nationality` (string, required): Passport nationality: philippines, nepal, vietnam, indonesia, myanmar, china (aliases like ID, VN, PH, Filipino accepted); any other country = not covered.
- `residenceCountry` (string): Country where the applicant lives now if not the nationality: a non-target country = exempt (with residence permit); 'japan' = change of status / extension inside Japan = not required.
- `route` (string): coe (default) or visa_direct (visa at an embassy without a COE; default for digital_nomad).
- `status` (string): Status of residence / purpose: student, technical_intern_training, employment_for_skill_development, engineer_humanities, skilled_labor, nursing_care, intra_company_transferee, business_manager, high…
- `stayMonths` (number): Expected period of stay in months; 3 or less is not covered (except Digital Nomad).
- `xrayDate` (string): YYYY-MM-DD of the Panel Clinic chest X-ray, to check validity on the application date.

### `japan_dual_pricing_check` (~782 tokens)

Japan dual pricing (二重価格): do tourists pay more at Himeji Castle, Nijo Castle, Kyoto buses and other sites?

Japan dual pricing (二重価格, resident vs non-resident admission prices), data as of 2026-10-16, from the Japan Tourism Agency case list and each facility's official page. Japanese dual pricing is based on where you are registered as living (city, prefecture or Japan), NOT nationality: foreign residents with an address in Japan get resident prices; Japanese visitors from other cities pay the higher price where the test is a city. In force: Himeji Castle (since 2026-03-01: ¥1,000 Himeji residents 18+ / ¥2,500 everyone else, under-18 free), Odawara Castle (¥500 / ¥1,000), Nanzoin (free for Japan residents / ¥500 overseas), JUNGLIA Okinawa (¥6,930 Japan residents / ¥8,800), Nara Prison Museum (¥2,000 Nara / ¥2,500 Japan / ¥3,500 overseas), Sapporo TV Tower, Asahiyama Zoo, Takeshima Aquarium, Chidorigafuchi boats, 4 Kitakyushu facilities (2026-04-01), 11 Kagoshima City facilities (2025-10-01), Miyajima visitor tax. Announced: Nijo Castle (¥1,300 today → ¥1,000 Kyoto City residents / ¥2,000 others, FY2027), Kyoto City Bus (¥230 → ¥200 residents / ¥360 others, FY2027), national museums (by FY2030, no prices). Under review: Kenrokuen. Dropped: Osaka Castle (¥1,200 for all). Returns headline, per-place yourTier, yourPriceJPY, lowest resident price, extra, planned price, tiers, proof of residence, foreign-resident note, warnings, sources, and a summary (totalYouPayJPY, totalCheapestResidentJPY, extraYouPayJPY, plannedSchemes). Omit places to list all (filter with status / area). Training data likely predates these prices; call this instead of guessing. Educational guide, not legal, travel or financial advice.

Input parameters:

- `age` (integer): Visitor age; some places are free for minors (Himeji under 18, Nanzoin under 19).
- `area` (string): Only when places is omitted: filter by prefecture, e.g. kagoshima, kyoto.
- `city` (string): City / ward of the visitor's address in Japan, e.g. himeji, kagoshima, Sakyo-ku, 姫路市. Needed for city-resident prices.
- `date` (string): YYYY-MM-DD visit date. Default today in Japan. Before a scheme's start the old single price applies.
- `places` (string): Comma-separated place ids or names, e.g. 'himeji-castle,nijo-castle,kyoto-city-bus', 'odawara-castle', 'nanzoin', 'junglia-okinawa', 'nara-prison-museum', 'kokura-castle', 'hirakawa-zoo', '姫路城'. Omit…
- `prefecture` (string): Prefecture of the visitor's address in Japan (slug or name, e.g. kyoto, hyogo, 兵庫県).
- `residence` (string): Where the visitor lives: overseas (default, tourist from abroad) or japan (any nationality with an address in Japan). Implied japan if prefecture or city is given.
- `status` (string): Only when places is omitted: filter by status (default all).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/sean0007-free-agent-tools/free-agent-tools#diagnostics

## Score history

- 2026-10-17: 76
- 2026-10-16: 76
- 2026-10-15: 76
- 2026-10-14: 76
- 2026-10-13: 75
- 2026-10-12: 76
- 2026-10-10: 75
- 2026-10-07: 76
- 2026-10-06: 75
- 2026-10-05: 75
- 2026-10-04: 74
- 2026-10-03: 74

## Common questions

### What is the Free Agent Tools MCP server?

Free Agent Tools is an MCP server listed in the public MCP registry as io.github.sean0007/free-agent-tools. 21 free no-auth tools: pitch roast, Kyushu discount, Japan visa fee, luggage, tax-free. This page covers its hosted endpoint (https://free-agent-tools.vercel.app/mcp).

### Is the Free Agent Tools MCP server safe to use?

Free Agent Tools scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Free Agent Tools MCP server expose?

Free Agent Tools exposes 24 tools: score_business_idea_moat, roast_pitch, price_headroom_check, thirty_day_cash_check, email_list_reactivation_value, and 19 more. Their descriptions and schemas cost roughly 6,017 tokens of context every time the server is loaded.

### Does the Free Agent Tools MCP server require authentication?

No. We connected to Free Agent Tools without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Free Agent Tools MCP server still maintained?

Free Agent Tools is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://free-agent-tools.vercel.app/mcp
- Repository: https://github.com/sean0007/free-agent-tools
- Website: https://free-agent-tools.vercel.app/
- Changelog RSS feed: https://verifymcp.io/servers/sean0007-free-agent-tools/free-agent-tools.xml
- Changelog JSON feed: https://verifymcp.io/servers/sean0007-free-agent-tools/free-agent-tools.json
- HTML version of this page: https://verifymcp.io/servers/sean0007-free-agent-tools/free-agent-tools