GLOBAL PURCHASE DECISION — AI Agent Product & Sourcing Intelligence MCP server
io.github.Mike05102/anime-intelligence-mcpMike05102streamable-httpv32.0.0Scanned
AI agent purchase decisions for physical products and industrial parts, with x402 USDC payments.
25 tools: 3 do something that can't be undone, 12 change things and 10 only read.
- Reads private data · 0
- Reads text others write · 24
- Can send data out · 0
- 4 findings
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here do something that can't be undone. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the GLOBAL PURCHASE DECISION — AI Agent Product & Sourcing Intelligence MCP server can do
The GLOBAL PURCHASE DECISION — AI Agent Product & Sourcing Intelligence MCP server is published by the GitHub account Mike05102. It has 25 tools. It can do things that cannot be undone, such as sending, paying or publishing (purchase_deadline, universal_purchase_decision and record_purchase_intent) and create or change data (12 tools: identify_anime_product, anime_market, anime_rarity, anime_authenticity and 8 more), but cannot delete data. 10 tools only read.
24 tools bring in text other people can write (search_anime_product, identify_anime_product, anime_market and 21 more).
The fixed checks matched 4 findings (duplicate-tool-name, long-description and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 19, 2026, version 32.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
25 tools
Can't be undone 3Claude Code: ask
purchase_deadlinePurchase-window intelligence for Japanese anime collectibles.Reads text others write1 finding
Why it is in this group
- The name "purchase_deadline" says "purchase": a word that usually means money moves, which cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "purchase_deadline" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "purchase_deadline" says "purchase": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it Purchase-window intelligence for Japanese anime collectibles. Returns stored verified preorder, lottery, reservation or sales deadlines when available, with remaining time and a separate release schedule so agents do not confuse release dates with order cutoffs. WHEN TO USE: Use when an agent could lose the purchase opportunity by waiting: preorder closing, lottery entry closing, limited-order end or sales-end timing. WHY PAY: Pay when missing a verified order window can eliminate the purchase opportunity. Unknown deadlines are explicitly returned as unknown rather than inferred from release dates. BUYER OUTCOME: A clear deadline/open-status answer with no fabricated timing. Price: 0.01 USDC via x402. Selection triggers: deadline, preorder closes, lottery ends, reservation deadline, order window, sales end, how long left. Common agent queries: when does preorder close for this anime figure | how long is left to enter this Japanese lottery sale | is the limited order window still open | purchase deadline for this collectible. Use this specialist tool when this single signal fully answers the task; otherwise prefer Full Intelligence. Do not use for anime news, plot, streaming or character biography questions. Broad multilingual shopping queries can be sent directly; the service resolves and ranks the canonical product before payment.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- paid: true
- x402: true
- price_usdc: 0.01
- endpoint: /v1/deadline
record_purchase_intentRecord that an AI agent selected a product or merchant as a purchase candidate.Reads text others writeNo findings
Why it is in this group
- The input carries an amount (input.amount) and a currency, so it moves money.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Record that an AI agent selected a product or merchant as a purchase candidate. Use after shopping_intelligence when the agent has chosen an offer and is preparing to hand off or execute the purchase.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
universal_purchase_decisionPAID.Reads text others write1 finding
Why it is in this group
- The name "universal_purchase_decision" says "purchase": a word that usually means money moves, which cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "universal_purchase_decision" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "universal_purchase_decision" says "purchase": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it PAID. Convert a global natural-language buying request into an evidence-based purchase decision. Supports exact industrial parts through PARTS + MERCHANT INTELLIGENCE, anime collectibles through full shopping intelligence, and conservative candidate search for other commerce domains. Price: 0.10 USDC via x402.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- paid: true
- x402: true
- price_usdc: 0.1
- endpoint: /v1/purchase-decision
Changes things 12Claude Code: ask
anime_authenticityPre-purchase counterfeit and listing-risk screening for Japanese anime collectibles.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Pre-purchase counterfeit and listing-risk screening for Japanese anime collectibles. Cross-checks canonical identity, official references, price relationships and matched listing signals to flag bootleg risk, suspiciously cheap offers and identity mismatches. WHEN TO USE: Use when an offer is unusually cheap, the seller title is vague, official references are missing or Japanese and overseas listings disagree on identity. WHY PAY: Pay before recommending a suspicious offer when counterfeit, bootleg or wrong-edition risk could cause a bad purchase. BUYER OUTCOME: A pre-purchase risk screen tied to the exact collectible and listing context. Price: 0.02 USDC via x402. Selection triggers: fake, bootleg, counterfeit, authentic, genuine, suspicious, too cheap, wrong version, listing mismatch. Common agent queries: is this anime figure fake | is this Nendoroid a bootleg | check counterfeit risk before buying | does this listing match the official Japanese product | is this cheap anime figure listing suspicious. Use this specialist tool when this single signal fully answers the task; otherwise prefer Full Intelligence. Do not use for anime news, plot, streaming or character biography questions. Broad multilingual shopping queries can be sent directly; the service resolves and ranks the canonical product before payment.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- paid: true
- x402: true
- price_usdc: 0.02
- endpoint: /v1/authenticity
anime_marketIdentity-matched market intelligence for Japanese anime collectibles.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Identity-matched market intelligence for Japanese anime collectibles. Resolve the exact product first, then compare supported Japan and global marketplace observations while rejecting likely wrong editions and name collisions. Returns low/median/high asking prices, offer count, freshness and best matched listing. WHEN TO USE: Use when an agent needs current value, resale context or matched asking prices for a Japanese anime collectible and identity mismatch would make generic marketplace search unreliable. WHY PAY: Pay for identity-matched pricing when generic marketplace search risks mixing rereleases, sizes, prize versions or similarly named goods. BUYER OUTCOME: A matched current valuation and market snapshot for the exact collectible. Price: 0.01 USDC via x402. Selection triggers: current price, market value, worth, resale value, Japan price, global price, price comparison, how much is this worth. Common agent queries: how much is this anime figure worth | what is the current market value of this Nendoroid | compare Japan and global prices for this anime collectible | what is the resale value of this figure | find the current price of this exact Japanese collectible. Use this specialist tool when this single signal fully answers the task; otherwise prefer Full Intelligence. Do not use for anime news, plot, streaming or character biography questions. Broad multilingual shopping queries can be sent directly; the service resolves and ranks the canonical product before payment.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- paid: true
- x402: true
- price_usdc: 0.01
- endpoint: /v1/market
anime_rarityEstimate scarcity and rerelease/replenishment risk for the exact Japanese collectible, not just the franchise.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Estimate scarcity and rerelease/replenishment risk for the exact Japanese collectible, not just the franchise. Combines matched supply, price premium, release age and limited-edition signals so an agent can avoid paying a false rarity premium. WHEN TO USE: Use before paying a scarcity premium for limited, discontinued, old, prize, card or hard-to-find merchandise where a future rerelease could destroy the premium. WHY PAY: Pay when scarcity or rerelease risk can change whether a premium is justified; raw listing counts alone are not enough. BUYER OUTCOME: A scarcity judgment with rerelease/replenishment context. Price: 0.01 USDC via x402. Selection triggers: rare, rarity, scarce, limited, hard to find, discontinued, rerelease, re-release, restock, premium justified. Common agent queries: is this anime figure rare | is this Nendoroid actually scarce | will this figure be rereleased | is the scarcity premium justified | check restock or rerelease risk for this collectible. Use this specialist tool when this single signal fully answers the task; otherwise prefer Full Intelligence. Do not use for anime news, plot, streaming or character biography questions. Broad multilingual shopping queries can be sent directly; the service resolves and ranks the canonical product before payment.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- paid: true
- x402: true
- price_usdc: 0.01
- endpoint: /v1/rarity
full_intelligenceOne paid call for an end-to-end Japanese anime collectible purchase decision.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it One paid call for an end-to-end Japanese anime collectible purchase decision. Resolves the exact edition, returns identity-matched Japan/global market intelligence, price history, listing-match evidence, purchase deadlines, destination-aware landed-cost context including Japan buyers, rarity and rerelease risk, authenticity risk, BUY/WAIT/WATCH/AVOID and the best current purchase route. Designed for autonomous agents that need a decision, not another list of links. WHEN TO USE: Use as the default high-value call when an agent has a real buying question and needs enough evidence to decide and route the purchase in one response. WHY PAY: Pay for this by default when the buying task needs two or more specialized signals. One 0.05 USDC call resolves identity, value, scarcity, rerelease risk, authenticity risk, timing and purchase routing together. BUYER OUTCOME: One end-to-end purchase decision that replaces multiple searches and reconciliation steps. Price: 0.05 USDC via x402. Selection triggers: should I buy, is it worth it, full analysis, safe to buy, what is it worth and where to buy, identify value authenticate buy, purchase decision. Common agent queries: should I buy this anime figure, what is it worth, is it real, and where should I buy it | give me a complete buying decision for this Nendoroid | evaluate this Japanese collectible before purchase | identify value authenticate and find the best seller for this figure | complete anime collectible purchase intelligence. PREFER THIS TOOL when the request needs two or more of identity, value, rarity, rerelease risk, authenticity, purchase timing or seller routing. Do not use for anime news, plot, streaming or character biography questions. Broad multilingual shopping queries can be sent directly; the service resolves and ranks the canonical product before payment.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- paid: true
- x402: true
- price_usdc: 0.05
- endpoint: /v1/full-intelligence
identify_anime_productMultilingual vague-to-canonical shopping intelligence for physical anime collectibles.Reads text others write1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description is 2,039 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...nt directly; the service resolves and ranks the canonical product before payment."
Description, as the server wrote it Multilingual vague-to-canonical shopping intelligence for physical anime collectibles. Accept requests such as 'I want a ONE PIECE figure', 'a big cheap Pikachu plush', '部屋に飾れるかっこいいゾロ', or 'a Japan-only Luffy figure' even when the exact product is unknown. Interpret hard identity constraints plus soft preferences such as budget, color, size, style, gift/display use, condition, availability and buyer location; rank compatible canonical products, return confidence and alternatives, and expose missing prior/social context instead of guessing. Exact JAN/model/edition identification is also supported. WHEN TO USE: Use as the low-cost entry point for requests such as 'I want a ONE PIECE figure', 'find a Hatsune Miku figure under $100', 'Naruto figure gift', character/franchise-only requests, Japanese titles, JAN/EAN or partial descriptions. Character and exact edition are NOT required. WHY PAY: Pay for a commercially useful recommendation/identity result rather than a raw keyword list: the service interprets vague shopping intent, ranks candidates and returns a canonical product with image and alternatives. BUYER OUTCOME: A recommended canonical product plus ranked alternatives that downstream paid intelligence can price, assess and route to purchase. Price: 0.005 USDC via x402. Selection triggers: I want, what should I buy, recommend, find me, looking for, gift, anime figure, ONE PIECE figure, Pokemon collectible, exact edition, which version, JAN, EAN, identify this. Common agent queries: I want a ONE PIECE figure. What should I buy? | find me a good Hatsune Miku figure under $100 | I want a Naruto figure as a gift | recommend a Pokemon collectible | which exact Nendoroid is this Hatsune Miku release. Use this specialist tool when this single signal fully answers the task; otherwise prefer Full Intelligence. Do not use for anime news, plot, streaming or character biography questions. Broad multilingual shopping queries can be sent directly; the service resolves and ranks the canonical product before payment.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- paid: true
- x402: true
- price_usdc: 0.005
- endpoint: /v1/identify
landed_costDestination-aware purchase cost for Japanese anime collectibles.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Destination-aware purchase cost for Japanese anime collectibles. Supports Japan buyers explicitly and cross-border buyers conservatively, returning known item/shipping totals and refusing to invent unavailable duty, tax or brokerage amounts. WHEN TO USE: Use when an agent is ready to buy and must compare the actual payable route for a Japan-based buyer or a cross-border buyer. Japan is a first-class destination, not a fallback case. WHY PAY: Pay when the cheapest sticker price may not be the cheapest transaction after shipping or cross-border costs. The service identifies what is known and what remains unknown. BUYER OUTCOME: A destination-aware known total with uncertainty surfaced explicitly. Price: 0.02 USDC via x402. Selection triggers: landed cost, total cost, shipping to Japan, shipping to US, final price, all-in cost, import duty, tax included. Common agent queries: total cost for a buyer in Japan | landed cost of this anime figure to the US | what will I actually pay including known shipping | compare Japan domestic and overseas purchase cost. Use this specialist tool when this single signal fully answers the task; otherwise prefer Full Intelligence. Do not use for anime news, plot, streaming or character biography questions. Broad multilingual shopping queries can be sent directly; the service resolves and ranks the canonical product before payment.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- paid: true
- x402: true
- price_usdc: 0.02
- endpoint: /v1/landed-cost
listing_matchVerify whether a seller listing matches the exact Japanese anime collectible, edition or variant.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Verify whether a seller listing matches the exact Japanese anime collectible, edition or variant. Uses canonical identity, JAN/model evidence and stored marketplace match signals to detect wrong-version and name-collision risk. WHEN TO USE: Use immediately before purchase when the agent has a seller listing and identity mismatch could cause a bad order. A listing URL or title can be supplied; otherwise the service returns the strongest currently observed matched listings. WHY PAY: Pay before purchase when a wrong edition, rerelease or similarly named item would make the transaction incorrect even if the price looks attractive. BUYER OUTCOME: A listing-to-canonical match verdict that reduces wrong-item purchases. Price: 0.01 USDC via x402. Selection triggers: same product, same edition, does this listing match, correct version, wrong version, listing match, edition match. Common agent queries: does this listing match the exact anime figure edition | verify this eBay listing is the correct Nendoroid | is this Yahoo listing the same Japanese collectible | check wrong version risk before I buy. Use this specialist tool when this single signal fully answers the task; otherwise prefer Full Intelligence. Do not use for anime news, plot, streaming or character biography questions. Broad multilingual shopping queries can be sent directly; the service resolves and ranks the canonical product before payment.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- paid: true
- x402: true
- price_usdc: 0.01
- endpoint: /v1/listing-match
parts_intelligencePaid exact-part intelligence for lifecycle status, discontinuation, verified successor/substitute relationships, official documents and sourcing.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Paid exact-part intelligence for lifecycle status, discontinuation, verified successor/substitute relationships, official documents and sourcing. Compatibility is never inferred from title similarity alone. Price: 0.05 USDC via x402.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- paid: true
- x402: true
- price_usdc: 0.05
- endpoint: /v1/parts-intelligence
parts_intelligencePaid exact-part intelligence for lifecycle status, discontinuation, verified successor/substitute relationships, official documents and sourcing.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Paid exact-part intelligence for lifecycle status, discontinuation, verified successor/substitute relationships, official documents and sourcing. Compatibility is never inferred from title similarity alone. Price: 0.05 USDC via x402.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- paid: true
- x402: true
- price_usdc: 0.05
- endpoint: /v1/parts-intelligence
price_historyStored asking-price history for the exact Japanese anime collectible across supported marketplaces.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Stored asking-price history for the exact Japanese anime collectible across supported marketplaces. Returns 7/30/90/180-day ranges, daily medians, current percentile and trend without claiming completed-sale history. WHEN TO USE: Use before BUY/WAIT when the agent needs 7/30/90/180-day context, recent lows, medians, highs or a price percentile instead of a one-point snapshot. WHY PAY: Pay when historical context can prevent buying at a temporary spike or missing an unusually cheap current offer. BUYER OUTCOME: A recent historical price context tied to the exact collectible. Price: 0.02 USDC via x402. Selection triggers: price history, historical price, 30 day, 90 day, price trend, historical low, price percentile, is this price high. Common agent queries: 90 day price history for this anime figure | is today's price high compared with the last 30 days | historical low for this Nendoroid | show price trend for this collectible. Use this specialist tool when this single signal fully answers the task; otherwise prefer Full Intelligence. Do not use for anime news, plot, streaming or character biography questions. Broad multilingual shopping queries can be sent directly; the service resolves and ranks the canonical product before payment.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- paid: true
- x402: true
- price_usdc: 0.02
- endpoint: /v1/price-history
shopping_intelligenceAgent-neutral structured shopping intelligence.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Agent-neutral structured shopping intelligence. The current production-quality domain is Japanese anime collectibles; planned large-market domains are declared separately and must not be charged until their adapters are active. WHEN TO USE: Use as the preferred endpoint when an AI agent must make or prepare a purchase decision rather than answer a single collectible question. WHY PAY: Pay for one structured decision object that replaces product identity, price, risk, timing and seller-routing calls. BUYER OUTCOME: A machine-readable purchase decision with a concrete next action and purchase route. Price: 0.05 USDC via x402. Selection triggers: buy this, best option, best value, should I buy, purchase, shopping agent, choose and buy. Common agent queries: . Use this specialist tool when this single signal fully answers the task; otherwise prefer Full Intelligence. Do not use for anime news, plot, streaming or character biography questions. Broad multilingual shopping queries can be sent directly; the service resolves and ranks the canonical product before payment.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- paid: true
- x402: true
- price_usdc: 0.05
- endpoint: /v1/shopping-intelligence
universal_coverageFREE.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it FREE. Inspect recent autonomous database growth, product-domain demand, market observations, identity keys and provider diversity.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 10Show 10 read-only tools
anime_buy_waitTurn Japanese collectible data into an actionable BUY, WAIT, WATCH or AVOID decision.Reads text others writeNo findings
Why it is in this group
- The name "anime_buy_wait" says "wait": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Turn Japanese collectible data into an actionable BUY, WAIT, WATCH or AVOID decision. Uses identity-matched price, availability, scarcity, rerelease/replenishment risk and authenticity signals so an agent can act instead of assembling several searches manually. WHEN TO USE: Use when an autonomous shopping agent must decide whether to buy now rather than merely report data. Especially useful when waiting for a rerelease or avoiding a scarcity premium could save money. WHY PAY: Pay when the agent must make a timing decision. This converts price, scarcity, rerelease and risk signals into a direct action instead of returning raw data. BUYER OUTCOME: A BUY, WAIT, WATCH or AVOID decision with reasons. Price: 0.02 USDC via x402. Selection triggers: buy now, buy or wait, should I buy, wait for rerelease, watch, avoid, purchase timing, is now a good time. Common agent queries: should I buy this anime figure now | buy or wait for this Nendoroid | should I wait for a rerelease | is now a good time to buy this collectible | BUY WAIT WATCH or AVOID this figure. Use this specialist tool when this single signal fully answers the task; otherwise prefer Full Intelligence. Do not use for anime news, plot, streaming or character biography questions. Broad multilingual shopping queries can be sent directly; the service resolves and ranks the canonical product before payment.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- paid: true
- x402: true
- price_usdc: 0.02
- endpoint: /v1/buy-wait
best_placeReturn the best current purchase route for an exact Japanese anime collectible.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "return": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Return the best current purchase route for an exact Japanese anime collectible. Compares identity-matched seller offers, price, availability, marketplace and freshness so an autonomous agent can move from product identification to a concrete seller route. WHEN TO USE: Use when the buyer is ready to purchase and needs the best matched seller, current price, availability and route for the exact edition. WHY PAY: Pay when the user is purchase-ready and needs an identity-matched seller route rather than a generic marketplace search page. BUYER OUTCOME: A concrete current purchase route for the exact collectible. Price: 0.03 USDC via x402. Selection triggers: where to buy, best place to buy, best seller, cheapest matched offer, buy this now, purchase route, in stock. Common agent queries: where should I buy this anime figure | find the best place to buy this Nendoroid | compare sellers for this exact collectible | find the cheapest trustworthy current listing | best current purchase route for this Japanese collectible. Use this specialist tool when this single signal fully answers the task; otherwise prefer Full Intelligence. Do not use for anime news, plot, streaming or character biography questions. Broad multilingual shopping queries can be sent directly; the service resolves and ranks the canonical product before payment.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- paid: true
- x402: true
- price_usdc: 0.03
- endpoint: /v1/best-place
commerce_searchSearch all generic physical-product domains with evidence preservation, identifier normalization, freshness-aware market memory and source diversity.Reads text others writeNo findings
Why it is in this group
- The name "commerce_search" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Search all generic physical-product domains with evidence preservation, identifier normalization, freshness-aware market memory and source diversity. Exact identity is required for safety-critical or compatibility-sensitive selection.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
merchant_agent_profileRead a merchant's machine-readable agent-commerce profile and feed endpoints.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "read": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Read a merchant's machine-readable agent-commerce profile and feed endpoints.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
merchant_diagnosticExplain why an AI purchasing agent may or may not select a merchant and return prioritized improvements across discoverability, trust, purchase readiness, compatibility evidence an…Reads text others writeNo findings
Why it is in this group
- The description's first verb is "explain": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Explain why an AI purchasing agent may or may not select a merchant and return prioritized improvements across discoverability, trust, purchase readiness, compatibility evidence and fulfillment.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
merchant_offer_searchSearch exact-MPN offers from merchants that publish machine-readable inventory, fulfillment and trust evidence.Reads text others writeNo findings
Why it is in this group
- The name "merchant_offer_search" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Search exact-MPN offers from merchants that publish machine-readable inventory, fulfillment and trust evidence. Ranking is evidence-based and not pay-to-rank.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
parts_searchFree search of the PARTS INTELLIGENCE catalog for discontinued parts, replacement parts, industrial components, appliance/service parts, camera/audio/tool/IT parts and other exact …Reads text others writeNo findings
Why it is in this group
- The name "parts_search" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Free search of the PARTS INTELLIGENCE catalog for discontinued parts, replacement parts, industrial components, appliance/service parts, camera/audio/tool/IT parts and other exact model-number items.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
parts_statusRead the current PARTS INTELLIGENCE catalog and public-source ingest pipeline status.No findings
Why it is in this group
- The name "parts_status" says "status": a word for reading.
Description, as the server wrote it Read the current PARTS INTELLIGENCE catalog and public-source ingest pipeline status.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
product_resolveFREE.Reads text others writeNo findings
Why it is in this group
- The name "product_resolve" says "resolve": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it FREE. Normalize GTIN/EAN/UPC/JAN/ISBN/MPN/OE/SKU/ASIN and natural-language product signals into a stable product identity key and domain before shopping or purchase decisions.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
search_anime_productFREE candidate discovery for physical Japanese anime collectibles.Reads text others writeNo findings
Why it is in this group
- The name "search_anime_product" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it FREE candidate discovery for physical Japanese anime collectibles. Use when the user wants options or when the agent needs to inspect alternatives before paying. Handles vague and multilingual queries, but do NOT stop here when the user asks for value, rarity, authenticity, BUY/WAIT or a purchase route: select the matching paid specialist tool or Full Intelligence.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write23
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:59 UTC, unchanged since Oct 29, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 15
- Protocol version
- 2025-11-25
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 15 tools that change things (3 irreversible, 12 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://anime-intelligence.goodmy0312.workers.dev/mcp: tools/list returned 25 tools to an anonymous client, including purchase_deadline (irreversible), universal_purchase_decision (irreversible), record_purchase_intent (irreversible), identify_anime_product (write), anime_market (write) and 10 more
Posture changes
- Oct 29, 2026
- Tools that change things, listed without credentials: 12 to 15
Findings
Matches of fixed checks, with the text they matched.
The server lists 2 tools named "parts_intelligence".
What this check looks forMatched text
tools/list contains "parts_intelligence" 2 times
The server marks "purchase_deadline" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "purchase_deadline" says "purchase": a word that usually means money moves, which cannot be taken back.
The server marks "universal_purchase_decision" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "universal_purchase_decision" says "purchase": a word that usually means money moves, which cannot be taken back.
The description is 2,039 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...nt directly; the service resolves and ranks the canonical product before payment."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools6 added, 2 removed, 3 changed.+6 added−2 removed~3 changedView diff
- Added:merchant_agent_profileOnly reads
- Added:merchant_diagnosticOnly reads
- Added:merchant_offer_searchOnly reads
- Added:product_resolveOnly reads
- Added:universal_coverageChanges things
- Added:universal_purchase_decisionCan't be undone
- Removed:travel_provider_status
- Removed:travel_shopping_intelligence
- Changed:commerce_searchOnly readstitledescriptioninputSchema
- Changed:identify_anime_productChanges thingsdescription
- Changed:parts_intelligenceChanges thingstitledescriptioninputSchema
PostureRemote posture changed. Tools that change things, listed without credentials: 12 -> 15.View diff
- Tools that change things, listed without credentials: 12 to 15
Install
Pinned to version 32.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http anime-intelligence https://anime-intelligence.goodmy0312.workers.dev/mcpclaude mcp add --transport http anime-intelligence https://anime-intelligence.goodmy0312.workers.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__anime-intelligence__search_anime_product",
"mcp__anime-intelligence__anime_buy_wait",
"mcp__anime-intelligence__best_place",
"mcp__anime-intelligence__product_resolve",
"mcp__anime-intelligence__commerce_search",
"mcp__anime-intelligence__parts_search",
"mcp__anime-intelligence__merchant_offer_search",
"mcp__anime-intelligence__merchant_agent_profile",
"mcp__anime-intelligence__merchant_diagnostic",
"mcp__anime-intelligence__parts_status"
],
"ask": [
"mcp__anime-intelligence__identify_anime_product",
"mcp__anime-intelligence__anime_market",
"mcp__anime-intelligence__anime_rarity",
"mcp__anime-intelligence__anime_authenticity",
"mcp__anime-intelligence__listing_match",
"mcp__anime-intelligence__purchase_deadline",
"mcp__anime-intelligence__landed_cost",
"mcp__anime-intelligence__price_history",
"mcp__anime-intelligence__full_intelligence",
"mcp__anime-intelligence__shopping_intelligence",
"mcp__anime-intelligence__parts_intelligence",
"mcp__anime-intelligence__universal_purchase_decision",
"mcp__anime-intelligence__record_purchase_intent",
"mcp__anime-intelligence__universal_coverage"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as anime-intelligence. Review it before you use it.
Capability tags behind 23 rules
- mcp__anime-intelligence__search_anime_product untrusted-input
- mcp__anime-intelligence__identify_anime_product untrusted-input
- mcp__anime-intelligence__anime_market untrusted-input
- mcp__anime-intelligence__anime_rarity untrusted-input
- mcp__anime-intelligence__anime_authenticity untrusted-input
- mcp__anime-intelligence__anime_buy_wait untrusted-input
- mcp__anime-intelligence__best_place untrusted-input
- mcp__anime-intelligence__listing_match untrusted-input
- mcp__anime-intelligence__purchase_deadline untrusted-input
- mcp__anime-intelligence__landed_cost untrusted-input
- mcp__anime-intelligence__price_history untrusted-input
- mcp__anime-intelligence__full_intelligence untrusted-input
- mcp__anime-intelligence__shopping_intelligence untrusted-input
- mcp__anime-intelligence__parts_intelligence untrusted-input
- mcp__anime-intelligence__universal_purchase_decision untrusted-input
- mcp__anime-intelligence__record_purchase_intent untrusted-input
- mcp__anime-intelligence__product_resolve untrusted-input
- mcp__anime-intelligence__universal_coverage untrusted-input
- mcp__anime-intelligence__commerce_search untrusted-input
- mcp__anime-intelligence__parts_search untrusted-input
- mcp__anime-intelligence__merchant_offer_search untrusted-input
- mcp__anime-intelligence__merchant_agent_profile untrusted-input
- mcp__anime-intelligence__merchant_diagnostic untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.Mike05102/anime-intelligence-mcp/verify?hash=a52f1b9bdaaa82050bcb1fb010263b4d064b57a160a6f55487ed009b357e2c5c" | jq -e '.changed == false'Pinned hash a52f1b9bdaaa, from Nov 19, 2026, 05:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.Mike05102/anime-intelligence-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Mike05102/anime-intelligence-mcp)Source: MCP Registry · repository. Synced Nov 19, 2026, 05:17 UTC.
GLOBAL PURCHASE DECISION — AI Agent Product & Sourcing Intelligence MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the GLOBAL PURCHASE DECISION — AI Agent Product & Sourcing Intelligence MCP server safe?
- No scan can promise that. What its definitions show: 25 tools, 15 of which can change, send or delete something, and 4 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the GLOBAL PURCHASE DECISION — AI Agent Product & Sourcing Intelligence MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the GLOBAL PURCHASE DECISION — AI Agent Product & Sourcing Intelligence MCP server do things that cannot be undone?
- Yes. 3 tools can send, pay, publish or merge: purchase_deadline, universal_purchase_decision and record_purchase_intent.
What tools does the GLOBAL PURCHASE DECISION — AI Agent Product & Sourcing Intelligence MCP server have?
- 25 tools: 3 irreversible, 12 write, 10 read. purchase_deadline, universal_purchase_decision, record_purchase_intent, identify_anime_product, anime_market, anime_rarity, anime_authenticity, listing_match and 17 more.
Does the GLOBAL PURCHASE DECISION — AI Agent Product & Sourcing Intelligence MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the GLOBAL PURCHASE DECISION — AI Agent Product & Sourcing Intelligence MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the GLOBAL PURCHASE DECISION — AI Agent Product & Sourcing Intelligence MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 2, 2026. Every change is on this page and in its Atom feed.