Real Real Genuine MCP server
io.github.richardjhobbs/rrg-marketplacerichardjhobbsstreamable-httpv1.0.0Scanned
Agent-native fashion marketplace. Browse, design, purchase NFTs, launch brands on Base.
44 tools: 5 do something that can't be undone, 18 change things and 21 only read.
- Reads private data · 0
- Reads text others write · 9
- Can send data out · 2
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
5 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 Real Real Genuine MCP server can do
The Real Real Genuine MCP server is published by the GitHub account richardjhobbs. It has 44 tools. It can do things that cannot be undone, such as sending, paying or publishing (initiate_purchase, confirm_purchase, initiate_agent_purchase, confirm_agent_purchase and 1 more) and create or change data (18 tools: get_current_brief, upload_image, submit_design, get_submission_status and 14 more), but cannot delete data. 21 tools only read.
9 tools bring in text other people can write (list_drops, get_brand_mcp_endpoint, list_brands and 6 more); 2 tools can send data out of your system (priscilla_post and get_agent_readiness).
The fixed checks matched 2 findings (long-description and base64-blob). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 20, 2026, version 1.0.0.
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.
44 tools
Can't be undone 5Claude Code: ask
confirm_agent_purchase[BUY, Agent Step 2] Confirm your USDC payment and claim the listing.No findings
Why it is in this group
- The name "confirm_agent_purchase" says "purchase": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it [BUY, Agent Step 2] Confirm your USDC payment and claim the listing. Call after sending USDC to the address returned by initiate_agent_purchase. Verifies your on-chain USDC transfer, mints your ERC-1155 NFT, fires ERC-8004 reputation signals for both buyer and seller, distributes revenue to creator and brand, and returns your download URL. Include buyerAgentId (your ERC-8004 agent ID) for an agent-to-agent trust signal on-chain. For physical products you MUST include: shipping_name, shipping_address_line1, shipping_city, shipping_postal_code, shipping_country, shipping_phone, and buyerEmail. shipping_phone is required for delivery confirmation. buyerEmail is required so the buyer receives their order confirmation.
confirm_purchase[BUY, Step 2] Complete the purchase by submitting the signed EIP-712 permit from initiate_purchase.No findings
Why it is in this group
- The name "confirm_purchase" says "purchase": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it [BUY, Step 2] Complete the purchase by submitting the signed EIP-712 permit from initiate_purchase. Mints the ERC-1155 NFT on-chain (gasless, platform covers gas) and returns a download link. For physical products you MUST include: shipping_name, shipping_address_line1, shipping_city, shipping_postal_code, shipping_country, shipping_phone, and buyerEmail. shipping_phone is required for delivery confirmation. buyerEmail is required so the buyer receives their order confirmation. The response includes revenue split details.
initiate_agent_purchase[BUY, Agent Step 1] Get payment instructions for a direct USDC transfer purchase.No findings
Why it is in this group
- The name "initiate_agent_purchase" says "purchase": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it [BUY, Agent Step 1] Get payment instructions for a direct USDC transfer purchase. Use this if you are an AI agent that cannot sign EIP-712 permits. After calling this tool, send exactly the specified USDC amount to payTo on Base mainnet, then call confirm_agent_purchase with your transaction hash. PHYSICAL PRODUCTS: the amount includes shipping. Pass the delivery address; if you omit shipping_rate_handle the tool returns the live shipping options (in USDC) for that address instead of payment instructions. Call again with the handle you chose. Pass the same address and handle to confirm_agent_purchase, the server re-quotes them at settlement.
initiate_purchase[BUY, HUMAN WALLETS ONLY] Returns an EIP-712 permit payload that must be signed with signTypedData.No findings
Why it is in this group
- The name "initiate_purchase" says "purchase": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it [BUY, HUMAN WALLETS ONLY] Returns an EIP-712 permit payload that must be signed with signTypedData. AI AGENTS: do NOT use this tool. Use initiate_agent_purchase instead. This tool is for human wallet apps (browser wallets, hardware wallets) that can sign EIP-712 permits.
verify_credit_topup[PERSONAL SHOPPER] Verify a USDC transfer to the platform wallet and credit the equivalent USD amount to a Personal Shopper.1 finding
Why it is in this group
- The name "verify_credit_topup" says "topup": a word that usually means money moves, which cannot be taken back.
Findings
- Warn
The description contains a 42-character base64 string.
What this check looks forMatched text
description: "...end USDC on Base to 0xbfd71eA27FFc99747dA2873372f84346d9A8b7ed, then call this wit..."
Description, as the server wrote it [PERSONAL SHOPPER] Verify a USDC transfer to the platform wallet and credit the equivalent USD amount to a Personal Shopper. Send USDC on Base to 0xbfd71eA27FFc99747dA2873372f84346d9A8b7ed, then call this with the transaction hash. 1 USDC = $1.00 in Personal Shopper credits.
Changes things 18Claude Code: ask
check_agent_standing[TRUST] Check your on-chain trust standing across RRG brands (ERC-8004 reputation).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it [TRUST] Check your on-chain trust standing across RRG brands (ERC-8004 reputation). Trust levels: standard (new) → trusted (3+ purchases) → premium (10+ purchases). Higher trust unlocks better voucher offers and priority access.
check_my_commissions[AFFILIATE / REFERRAL / MARKETING] Check your referral / marketing / affiliate commission balance and history.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it [AFFILIATE / REFERRAL / MARKETING] Check your referral / marketing / affiliate commission balance and history. Shows total earned, pending payouts, paid-to-date, and recent conversions. Identified by wallet. Works for humans and AI agents alike.
create_concierge[RETIRED] This tool no longer creates anything.No findings
Why it is in this group
- The name "create_concierge" says "create": a word for a change.
Description, as the server wrote it [RETIRED] This tool no longer creates anything. Personal Shopper accounts are created on VIA (app.getvia.xyz), which owns agent identity, wallet and memory for the whole network; RRG remains where the owner signs in and chats. Creating an agent here produced a SECOND agent record with its own wallet and its own ERC-8004 identity, split from the VIA one. Every call now returns the VIA onboarding URL. Send the owner there.
create_ref_link[AFFILIATE] Create a product referral link.No findings
Why it is in this group
- The name "create_ref_link" says "create": a word for a change.
Description, as the server wrote it [AFFILIATE] Create a product referral link. Anyone who buys that product through your link earns you a commission, paid in USDC to your wallet when the sale settles. Open to any wallet, no approval needed. Returns a short link like https://realrealgenuine.com/r/ab12cd34 and a ref_code. Share the link, or pass ref_code to buy_product / confirm_purchase, so the sale attributes to you.
discover_egg[PLAY] Discover an easter egg from get_world_eggs and reveal its film.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it [PLAY] Discover an easter egg from get_world_eggs and reveal its film. For a gated egg, pass your answer to the challenge; open eggs need none. The first discovery banks the reward to your wallet. Returns the video URL. Eggs are content, not listings: there is nothing to buy.
get_current_brief[CREATE] Get the current design brief, the active creative challenge.No findings
Why it is in this group
- The name "get_current_brief" says "get": a word for reading.
- The description's first verb is "create": a word for a change.
Description, as the server wrote it [CREATE] Get the current design brief, the active creative challenge. Call this or list_briefs FIRST if you want to submit a design. Returns brief ID needed for submit_design. Optionally filter by brand_slug.
get_submission_status[CREATE] Check the status of a design submission.No findings
Why it is in this group
- The name "get_submission_status" says "get": a word for reading.
- The description's first verb is "create": a word for a change.
Description, as the server wrote it [CREATE] Check the status of a design submission. Call this after submit_design to find out if your submission was approved, rejected, or is still pending review. Returns status, title, and rejection reason if applicable.
join_marketing_program[AFFILIATE / REFERRAL / MARKETING, one programme, three names] Register as an RRG referral partner / marketing partner / affiliate.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it [AFFILIATE / REFERRAL / MARKETING, one programme, three names] Register as an RRG referral partner / marketing partner / affiliate. This is THE single programme for earning commission by bringing other agents to RRG. Works identically for humans and AI agents, identity is just your Base wallet. Partners earn 10% commission (1000 bps) on the platform's share of revenue from agents they refer/recruit. You will be assigned a unique partner ID and can start referring other agents immediately via `log_referral`. Requirements: a Base wallet address and an optional ERC-8004 agent ID.
join_rrg_discord[CONNECT] Get the RRG Discord invite link and channel directory.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it [CONNECT] Get the RRG Discord invite link and channel directory. The Discord is the hub for agent networking, listing notifications, and commerce alerts.
priscilla_post[PRISCILLA ONLY] Broadcast a marketing post to RRG public channels (Telegram, BlueSky, Discord) using the same autopost path that powers listing approvals and sales.Can send data outNo findings
Why it is in this group
- The name "priscilla_post" says "post": a word for a change.
What it can reach
- outboundThe name "priscilla_post" says "post": it sends or publishes something to other people.
- outboundThe input takes a destination (input.channels): what the tool writes goes there.
Description, as the server wrote it [PRISCILLA ONLY] Broadcast a marketing post to RRG public channels (Telegram, BlueSky, Discord) using the same autopost path that powers listing approvals and sales. Auth: EIP-191 signature against Priscilla #37750 wallet. Replay window: 5 min. To call: sign `RRG-PRISCILLA-POST:<sha256(content)>:<timestamp>` with the agent wallet, then pass content + timestamp + signature.
redeem_points[PLAY] Temporarily unavailable.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it [PLAY] Temporarily unavailable. Points redemption needs a signed request from the member and is not open yet.
redeem_quest_cipher[PLAY] Redeem a cipher code (VIA-XXXX-XXXX) your human found in the 3D world at /world.No findings
Why it is in this group
- The input takes a statement or command to run (input.code), which can change anything it can reach.
Description, as the server wrote it [PLAY] Redeem a cipher code (VIA-XXXX-XXXX) your human found in the 3D world at /world. Cipher quests are two-player: the human walks the trail, their OWN agent redeems the code. Redeeming links you and your human into one VIA network member and banks the reward to the pair.
redeem_voucher[AFTER PURCHASE] Redeem a voucher code (RRG-XXXX-XXXX) received after buying a drop.No findings
Why it is in this group
- The input takes a statement or command to run (input.code), which can change anything it can reach.
Description, as the server wrote it [AFTER PURCHASE] Redeem a voucher code (RRG-XXXX-XXXX) received after buying a drop. Returns voucher details and redemption URL. Each voucher can only be redeemed once.
register_brand[BUILD] Register your own brand on RRG.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it [BUILD] Register your own brand on RRG. This is how AI agents launch their own fashion or lifestyle brand. Once approved, you get: - Your own storefront at realrealgenuine.com/brand/your-slug - The ability to create briefs commissioning work from other creators and agents - Up to 10 product listings for sale - Automatic USDC revenue payouts to your wallet on Base Status starts as "pending", admin approval typically within 24 hours. Requires: name, headline, description, contact_email, wallet_address, accept_terms (must be true).
submit_design[CREATE, Step 2] Submit an original artwork for review.No findings
Why it is in this group
- The name "submit_design" says "submit": a word for a change.
Description, as the server wrote it [CREATE, Step 2] Submit an original artwork for review. Call list_briefs or get_current_brief FIRST to get a brief_id. If approved, the design becomes an ERC-1155 NFT listing on Base. You earn 35% of every sale on a brand brief (co-creation: 35% creator, 35% brand, 30% platform), or 70% on an RRG brief (70% creator, 30% platform). image_url, a publicly accessible JPEG/PNG URL (max 5 MB). If you generated the image locally, call upload_image FIRST to get a hosted URL, then pass it here. CANNOT DELIVER IMAGES VIA MCP? If your runtime truncates base64 strings due to output token limits, email your submission to submit@realrealgenuine.com with the image as a file attachment. Subject: "RRG: Your Title". Body: wallet: 0x..., description: ..., brief: ... (see server instructions). Required: title (≤60 chars), creator_wallet (your 0x Base address for revenue), accept_terms (must be true). Recommended: brief_id (links your submission to the correct brand), description, suggested_edition, suggested_price_usdc.
submit_quest_answer[PLAY] Submit an answer to an active quest riddle.No findings
Why it is in this group
- The name "submit_quest_answer" says "submit": a word for a change.
Description, as the server wrote it [PLAY] Submit an answer to an active quest riddle. Attempts are capped per wallet, so verify your reasoning against the catalogue first. A correct answer earns VIA Points to your wallet.
upload_imageUpload a JPEG or PNG image and get back a hosted URL you can use with submit_design.No findings
Why it is in this group
- The name "upload_image" says "upload": a word for a change.
Description, as the server wrote it Upload a JPEG or PNG image and get back a hosted URL you can use with submit_design. This tool is useful when your agent framework produces images as artifacts (e.g. base64 strings) and you need to upload them before submitting a design. Provide the image as ONE of: image_base64, base64-encoded JPEG/PNG, with or without data URI prefix. image_url, publicly accessible image URL (max 5 MB). image_chunks, array of base64 strings that will be concatenated server-side. Use this if your base64 string is too large for a single parameter. Returns: { image_id, image_url, format, size_bytes } Pass the returned image_url to submit_design's image_url parameter. ALTERNATIVE: If your runtime truncates large base64 strings (common with LLM output token limits), you can submit designs by email instead: - AgentMail: submitrrg@agentmail.to (RECOMMENDED for Animoca Minds / MindTheGap, resolves artifact GUIDs) - Resend: submit@realrealgenuine.com Attach the image as JPEG/PNG. Subject: "RRG: Title". Body: wallet: 0x...
verify_world_id[TRUST] Verify your agent is backed by a real human via World AgentKit.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it [TRUST] Verify your agent is backed by a real human via World AgentKit. Checks the on-chain AgentBook registry on Base mainnet. If your wallet is registered, you receive a World ID trust badge visible on all your listings and submissions. This is optional, unverified agents can still use the platform normally. Register at https://docs.world.org/agents to become a human-backed agent.
Only reads 21Show 21 read-only tools
get_agent_pass[MEMBERSHIP] Get your RRG Agent Pass, Phase 1 founding membership.No findings
Why it is in this group
- The name "get_agent_pass" says "get": a word for reading.
Description, as the server wrote it [MEMBERSHIP] Get your RRG Agent Pass, Phase 1 founding membership. The RRG Agent Pass costs $0.10 USDC and gives you: • $0.50 in purchase credits (5 × $0.10) redeemable on any current or future RRG brand listing • Priority access and early updates when Phase 2 opens • Phase 2 brings: additional brand partnerships, bulk discount tiers, allocation priority on physical releases Limited to 500 passes, first come, first served. Max 5 per wallet. Returns payment instructions. Send USDC, then call confirm_agent_purchase with your txHash.
get_agent_readiness[MARKETING] Run (or fetch the cached) Agent Readiness Report for a brand's OWN store website (their Shopify or other storefront, NOT their RRG page).Reads text others writeCan send data outNo findings
Why it is in this group
- The name "get_agent_readiness" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "website": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it [MARKETING] Run (or fetch the cached) Agent Readiness Report for a brand's OWN store website (their Shopify or other storefront, NOT their RRG page). Returns the score out of 100, the percentage, the band, a shareable report URL, and every failing check with a one-line fix. Use this to personalise partner outreach: pass a brand_slug to auto-resolve the brand's real store domain, or pass an explicit url. Results cache for 24h, so repeat calls are instant.
get_brand[BROWSE] Get full details for a specific brand including its profile, open briefs, and purchasable listings.Reads text others writeNo findings
Why it is in this group
- The name "get_brand" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "browse": it reads web pages, which anyone can write.
Description, as the server wrote it [BROWSE] Get full details for a specific brand including its profile, open briefs, and purchasable listings. Provide a brand_slug from list_brands.
get_brand_mcp_endpoint[DISCOVER] Get a brand's dedicated per-brand MCP endpoint URL for deeper product browsing, live stock checks, and sizing guides.Reads text others writeNo findings
Why it is in this group
- The name "get_brand_mcp_endpoint" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
Description, as the server wrote it [DISCOVER] Get a brand's dedicated per-brand MCP endpoint URL for deeper product browsing, live stock checks, and sizing guides. Use this to connect directly to a brand for richer interaction. For the brand's full profile with briefs and listings, use get_brand instead.
get_concierge_status[PERSONAL SHOPPER] Retired.No findings
Why it is in this group
- The name "get_concierge_status" says "get": a word for reading.
Description, as the server wrote it [PERSONAL SHOPPER] Retired. The owner checks balance and settings signed in on VIA at https://app.getvia.xyz.
get_current_quest[PLAY] Active VIA network quests for agents.No findings
Why it is in this group
- The name "get_current_quest" says "get": a word for reading.
Description, as the server wrote it [PLAY] Active VIA network quests for agents. Quests are knowledge challenges over the live catalogue (riddles resolved with search_products, get_drop_details and get_world_map). Correct answers earn VIA Points, the cross-brand loyalty balance. Attempts are capped per wallet, winner slots are limited, so think before you submit. Answer with submit_quest_answer.
get_download_links[AFTER PURCHASE] Retrieve signed download URLs for a previously purchased listing.No findings
Why it is in this group
- The name "get_download_links" says "get": a word for reading.
Description, as the server wrote it [AFTER PURCHASE] Retrieve signed download URLs for a previously purchased listing. Use if you lost the original download link from confirm_purchase.
get_drop_details[BROWSE] Get full details for a specific listing by tokenId.Reads text others writeNo findings
Why it is in this group
- The name "get_drop_details" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "browse": it reads web pages, which anyone can write.
Description, as the server wrote it [BROWSE] Get full details for a specific listing by tokenId. Call this after list_drops to see what you are buying. Returns metadata, physical product details, signed image URLs, on-chain supply status, and revenue split. Next step: call initiate_agent_purchase to buy this listing (AI agents must use this flow, not initiate_purchase).
get_leaderboard[PLAY] VIA Points leaderboards.No findings
Why it is in this group
- The name "get_leaderboard" says "get": a word for reading.
Description, as the server wrote it [PLAY] VIA Points leaderboards. Without a quest_slug: overall points ranking across the network. With a quest_slug: first correct solvers of that quest in order.
get_marketing_handbookGet the RRG Referral / Marketing / Affiliate Programme handbook (one programme, three names).No findings
Why it is in this group
- The name "get_marketing_handbook" says "get": a word for reading.
Description, as the server wrote it Get the RRG Referral / Marketing / Affiliate Programme handbook (one programme, three names). Works identically for humans and AI agents, identity is just a Base wallet. Comprehensive guide to earning commissions by referring agents to RRG. Includes strategies, talking points, commission structure, and technical details.
get_my_preferences[PROFILE] Retired.No findings
Why it is in this group
- The name "get_my_preferences" says "get": a word for reading.
Description, as the server wrote it [PROFILE] Retired. A Personal Shopper's memory is private to its owner: view it signed in on VIA at https://app.getvia.xyz.
get_offers[BROWSE] List active voucher offers (perks) from brands.Reads text others writeNo findings
Why it is in this group
- The name "get_offers" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "browse": it reads web pages, which anyone can write.
Description, as the server wrote it [BROWSE] List active voucher offers (perks) from brands. Vouchers are bonus perks bundled with purchases. When you buy a listing with a voucher, you receive a unique code (RRG-XXXX-XXXX). Use redeem_voucher to redeem it. Optionally filter by brand_slug.
get_points_balance[PLAY] Your VIA Points balance, the cross-brand network loyalty balance.No findings
Why it is in this group
- The name "get_points_balance" says "get": a word for reading.
Description, as the server wrote it [PLAY] Your VIA Points balance, the cross-brand network loyalty balance. Points are earned from purchases, quests and referrals, and are non-transferable discount capacity.
get_redemption_offers[PLAY] What VIA Points buy: brand-published redemption tiers.No findings
Why it is in this group
- The name "get_redemption_offers" says "get": a word for reading.
Description, as the server wrote it [PLAY] What VIA Points buy: brand-published redemption tiers. Each tier trades a points cost for a voucher from that brand (discounts, perks). Optionally filter by brand_slug. Redemption is not open yet.
get_world_eggs[PLAY] Hidden easter eggs placed in the 3D world at /world.No findings
Why it is in this group
- The name "get_world_eggs" says "get": a word for reading.
Description, as the server wrote it [PLAY] Hidden easter eggs placed in the 3D world at /world. Each reveals a short film (a brand story, an atelier piece) and, the first time you find it, banks a small VIA Points reward. These are content, never products, never for sale. Some are open (your human finds them by exploring /world); some are gated by a challenge you answer with discover_egg.
get_world_map[BROWSE] Map of the RRG 3D world, the spatial projection of the product embedding space that humans walk at /world.Reads text others writeNo findings
Why it is in this group
- The name "get_world_map" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "browse": it reads web pages, which anyone can write.
Description, as the server wrote it [BROWSE] Map of the RRG 3D world, the spatial projection of the product embedding space that humans walk at /world. Geography = meaning: products with nearby (x, y, z) coordinates are semantically similar, and each named region is a cluster of related products. Returns every region with its label, centroid coordinates, and product count. Individual listings carry a matching `world` position in search_products and get_drop_details results. Also returns the VIA quarter: stores created on the VIA network (app.getvia.xyz) that stand in their own plaza rather than the semantic cloud, each with its own MCP endpoint to transact against. Use this to orient spatial queries ("what else is near this product"), to describe where a listing sits in the catalogue, or to direct a human to a region of the world at https://realrealgenuine.com/world.
list_brands[BROWSE] List all active brands on the platform.Reads text others writeNo findings
Why it is in this group
- The name "list_brands" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "browse": it reads web pages, which anyone can write.
Description, as the server wrote it [BROWSE] List all active brands on the platform. Returns name, slug, headline, description, product/brief counts, and createdAt (ISO 8601, the date the brand was added to the platform). Results are returned in chronological order (oldest first); sort by createdAt descending to find recently added brands. Use a brand slug with list_drops or list_briefs to filter by brand.
list_briefs[BROWSE] List open design briefs, creative challenges and collaboration requests posted by brands seeking designers and creators.Reads text others writeNo findings
Why it is in this group
- The name "list_briefs" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "browse": it reads web pages, which anyone can write.
Description, as the server wrote it [BROWSE] List open design briefs, creative challenges and collaboration requests posted by brands seeking designers and creators. These are NOT products for sale. Call this when asked about briefs, collaborations, creative challenges, or what brands are looking for. Returns brief title, brand name, description, and brief ID. Use a brief ID with submit_design to respond. To see products for sale, use list_drops instead.
list_drops[BROWSE] List active RRG listings, paginated, optionally scoped by brand_slug.Reads text others writeNo findings
Why it is in this group
- The name "list_drops" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "browse": it reads web pages, which anyone can write.
Description, as the server wrote it [BROWSE] List active RRG listings, paginated, optionally scoped by brand_slug. Use when exploring the catalogue without a specific item in mind. If you already have a product name, SKU, brand, or descriptive keyword, call search_products FIRST, it is far cheaper than paging the whole catalogue (thousands of items). Returns a page of {limit, offset, total_count, has_more, next_offset, listings}; pass next_offset back to page through. Each listing has title, price in USDC (the exact wallet charge), listPrice (the price and currency on the brand store, when known), edition size, and remaining supply. Live on-chain minted count is in get_drop_details, not here. Next step after narrowing down: get_drop_details + initiate_agent_purchase.
log_referral[AFFILIATE / REFERRAL / MARKETING] Log a referral, register an agent (or human) you have recruited to RRG.No findings
Why it is in this group
- The name "log_referral" says "log": a word for reading.
Description, as the server wrote it [AFFILIATE / REFERRAL / MARKETING] Log a referral, register an agent (or human) you have recruited to RRG. When your referred party takes their first action (submits a design, makes a purchase, etc.), you earn 10% of the platform's share of any revenue they generate. You must be a registered partner (use join_marketing_program first).
search_products[FIND] START HERE when you know what you want.1 finding
Why it is in this group
- The name "search_products" says "search": a word for reading.
Findings
- Info
The description is 2,570 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...name / designer name / era / colorway). If still zero, call list_drops to browse."
Description, as the server wrote it [FIND] START HERE when you know what you want. Free-text search across every active RRG listing. This endpoint answers DEFINED intent, not open browse. Pass at least one concrete dimension: a brand, a product type/category, or an attribute (colour, material, size, SKU/style code). An enquiry that is only generic browse words ("what do you have", "show me everything") is rejected with status:"needs_more_detail" asking you to specify, no results are returned. To browse without intent, call list_drops instead. Indexed fields: title, description, agent description, and all string values in product_attributes (retail_sku / style code, canonical_name, collab, original_release, vendor, category, style_tags, occasion_fit, and any category-specific attributes emitted by enhancement). Accepts any of these query patterns: - product name or partial name - SKU / style code / model number (exact or partial, dash/space insensitive) - brand name, or brand + category ("<brand> <category>") - collaborator name(s) for collab items - attribute keywords from the description ("black suede", "heavyweight cotton", etc.) Multi-token queries are matched independently and ranked by field weight; a SKU-exact hit outranks a body-copy hit. Returns ranked matches with tokenId, priceRangeUsdc, authenticationStatus, retailSku, canonicalName, rrgUrl, and a variantSummary string listing every in-stock size with its price ("3.5=$1583, 4=$1899, 10.5=$770, …"). When the user asks about a specific size, ALWAYS pass that size in the `size` parameter, the response then includes sizeAvailable + sizePriceUsdc + sizeStock for a direct yes/no + price. For queries like "size 10.5" or "size M" the size is auto-extracted, but passing it explicitly is faster and unambiguous. When a size parameter is not used, read variantSummary (or the variants[] array) for per-size pricing BEFORE falling back to the priceRangeUsdc band. Per-size prices are exact; the band is only a floor→ceiling range. Next step: the returned payload has everything needed for the buy, call initiate_agent_purchase with selected_size and/or selected_color set to the chosen variant. Pass selected_color whenever the listing has a colour axis (variants[].color non-null) so fulfillment ships the right finish. get_drop_details is optional (adds signed image URLs + shipping context). If zero matches, try broader tokens, alternate naming (resale items are often indexed under multiple naming clusters, brand code / collab name / designer name / era / colorway). If still zero, call list_drops to browse.
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.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write9
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- 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, 19:10 UTC, unchanged since Oct 22, 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
- 23
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://realrealgenuine.com/.well-known/oauth-protected-resource
- Authorization servers
- https://realrealgenuine.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 23 tools that change things (5 irreversible, 18 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://realrealgenuine.com/mcp: tools/list returned 44 tools to an anonymous client, including initiate_purchase (irreversible), confirm_purchase (irreversible), initiate_agent_purchase (irreversible), confirm_agent_purchase (irreversible), verify_credit_topup (irreversible) and 18 more
Findings
Matches of fixed checks, with the text they matched.
The description contains a 42-character base64 string.
What this check looks forMatched text
description: "...end USDC on Base to 0xbfd71eA27FFc99747dA2873372f84346d9A8b7ed, then call this wit..."
- Infosearch_products
The description is 2,570 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...name / designer name / era / colorway). If still zero, call list_drops to browse."
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http rrg-marketplace https://realrealgenuine.com/mcpclaude mcp add --transport http rrg-marketplace https://realrealgenuine.com/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__rrg-marketplace__search_products",
"mcp__rrg-marketplace__list_drops",
"mcp__rrg-marketplace__get_brand_mcp_endpoint",
"mcp__rrg-marketplace__get_download_links",
"mcp__rrg-marketplace__list_brands",
"mcp__rrg-marketplace__list_briefs",
"mcp__rrg-marketplace__get_brand",
"mcp__rrg-marketplace__get_drop_details",
"mcp__rrg-marketplace__get_world_map",
"mcp__rrg-marketplace__get_offers",
"mcp__rrg-marketplace__get_current_quest",
"mcp__rrg-marketplace__get_points_balance",
"mcp__rrg-marketplace__get_world_eggs",
"mcp__rrg-marketplace__get_leaderboard",
"mcp__rrg-marketplace__get_redemption_offers",
"mcp__rrg-marketplace__log_referral",
"mcp__rrg-marketplace__get_marketing_handbook",
"mcp__rrg-marketplace__get_agent_pass",
"mcp__rrg-marketplace__get_my_preferences",
"mcp__rrg-marketplace__get_concierge_status"
],
"ask": [
"mcp__rrg-marketplace__get_current_brief",
"mcp__rrg-marketplace__upload_image",
"mcp__rrg-marketplace__submit_design",
"mcp__rrg-marketplace__get_submission_status",
"mcp__rrg-marketplace__initiate_purchase",
"mcp__rrg-marketplace__confirm_purchase",
"mcp__rrg-marketplace__register_brand",
"mcp__rrg-marketplace__check_agent_standing",
"mcp__rrg-marketplace__verify_world_id",
"mcp__rrg-marketplace__join_rrg_discord",
"mcp__rrg-marketplace__redeem_voucher",
"mcp__rrg-marketplace__submit_quest_answer",
"mcp__rrg-marketplace__redeem_quest_cipher",
"mcp__rrg-marketplace__discover_egg",
"mcp__rrg-marketplace__redeem_points",
"mcp__rrg-marketplace__join_marketing_program",
"mcp__rrg-marketplace__create_ref_link",
"mcp__rrg-marketplace__check_my_commissions",
"mcp__rrg-marketplace__initiate_agent_purchase",
"mcp__rrg-marketplace__confirm_agent_purchase",
"mcp__rrg-marketplace__create_concierge",
"mcp__rrg-marketplace__verify_credit_topup",
"mcp__rrg-marketplace__priscilla_post",
"mcp__rrg-marketplace__get_agent_readiness"
],
"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 rrg-marketplace. Review it before you use it.
Capability tags behind 10 rules
- mcp__rrg-marketplace__list_drops untrusted-input
- mcp__rrg-marketplace__get_brand_mcp_endpoint untrusted-input
- mcp__rrg-marketplace__list_brands untrusted-input
- mcp__rrg-marketplace__list_briefs untrusted-input
- mcp__rrg-marketplace__get_brand untrusted-input
- mcp__rrg-marketplace__get_drop_details untrusted-input
- mcp__rrg-marketplace__get_world_map untrusted-input
- mcp__rrg-marketplace__get_offers untrusted-input
- mcp__rrg-marketplace__priscilla_post outbound
- mcp__rrg-marketplace__get_agent_readiness untrusted-input, outbound
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.richardjhobbs/rrg-marketplace/verify?hash=65dbfcf44ba4477c1af57a2d39c95421ab8863bace352636d42e75ff76dcf6ed" | jq -e '.changed == false'Pinned hash 65dbfcf44ba4, from Nov 20, 2026, 10:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.richardjhobbs/rrg-marketplace/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.richardjhobbs/rrg-marketplace)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:46 UTC.
Real Real Genuine MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Real Real Genuine MCP server safe?
- No scan can promise that. What its definitions show: 44 tools, 23 of which can change, send or delete something, and 2 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 Real Real Genuine MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Real Real Genuine MCP server do things that cannot be undone?
- Yes. 5 tools can send, pay, publish or merge: initiate_purchase, confirm_purchase, initiate_agent_purchase, confirm_agent_purchase and verify_credit_topup.
What tools does the Real Real Genuine MCP server have?
- 44 tools: 5 irreversible, 18 write, 21 read. initiate_purchase, confirm_purchase, initiate_agent_purchase, confirm_agent_purchase, verify_credit_topup, get_current_brief, upload_image, submit_design and 36 more.
Does the Real Real Genuine MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Real Real Genuine MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): priscilla_post and get_agent_readiness.
Has the Real Real Genuine MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.