Skip to content
MCP server

Product Hunt

By product

Explore over a decade of Product Hunt launches, compare tools using community reviews, and discover startups worth researching. Create and manage your own launches in Claude.

First seen 14 Nov 2026. One server, whatever directories list it: each directory listing keeps its own page and history.

2
Directories
Collected by InvokeRank
29
Tools
From an anonymous probe
-
ToolBench grade
Not graded by Arcade
-
GitHub stars
No repository data

Tools

ToolDescriptionBehaviour
ads_create_accountSet up a self-serve Product Hunt ad account for the signed-in user, when ads_get_context lists none. Give what they promote: post_id of a Product Hunt launch they make or are on the team of, or website_url. budget_band is their approximate total budget. Set agency (and client_name) when booking for a client. The account's confirmed Product Hunt email becomes the contact and can sign in to Ads Manager. Product Hunt's ads team sees the request. A returning self-serve buyer gets their existing account back. This creates no campaign, draft, or payment. Next, call ads_start_draft with the returned advertiser_id.Destructive
ads_get_campaignRead an authorized campaign, a page of its permitted budgets, and its self-serve portal creative state (slots, associated launch selection, and variant controls) when your membership reaches the campaign's asset request. live means an active, unpaused budget with live placements; daily limits, targeting, and auctions still affect delivery, and draft budgets never serve. creative is null when no current portal asset request is reachable. Give the user preview_url to see the ad on the real Product Hunt homepage. Commercial terms and billing details are not exposed; delivery results are in ads_get_performance.Read-only
ads_get_contextList ad accounts accessible through your current portal membership. Follow next_after_id even when a page is empty. Every account can manage drafts and campaigns; access is always advertiser. With none, offer ads_create_account.Read-only
ads_get_draftRead your current unfinished ad composer draft, available placement options, and text and image field limits. Requires account-wide portal access. A null draft means no saved work. Budgets and minimums are in whole USD; these are draft choices, not a price quote or reservation. A managed account's draft (mode request) is a campaign request with no budgets or checkout, so its min_budget is 0. Billing stays in the browser and is omitted here. draft.variants lists additional creative variants, whose creative_changes carry their variant_key; draft.launch is the linked Product Hunt launch, set with ads_update_draft post_id from a list_my_launches launch_id. An attached image shows its image_id, or null when it was uploaded in the browser. Open portal_url, select the advertiser, and open its composer to continue. Give the user preview_url to see the ad on the real Product Hunt homepage.Read-only
ads_get_performanceRead delivery results for an ad account you can access: impressions, clicks, CTR, CPM and spend in USD as totals and per campaign, ad type and creative, plus a daily series. Pass campaign_id for one campaign. Figures come from the advertiser portal's report, refreshed about hourly, over the same history as ads_list_campaigns (usually campaigns active in about the last 12 months). Spend is delivered value (impressions at the booked CPM) capped at each booking's budget; it is not an invoice. Totals, campaigns, ad types and creatives always cover the whole report; days, start_date, end_date and breakdown shape only the daily series. A series over 500 rows, counting each day and each breakdown row, is refused: narrow the dates or pass campaign_id.Read-only
ads_list_campaignsList campaigns reachable through your current membership in an ad account. Like the advertiser portal, it leaves out campaigns that ended before the account's visible history begins (usually about 12 months ago). Use ads_get_campaign for authorized budget schedules, delivery status, and editable creative slots.Read-only
ads_prepare_checkoutCheck whether your self-serve ad draft is ready to pay for and quote what checkout will book. Requires account-wide portal access. Pass write_revision as expected_revision. Managed request drafts are rejected. This never charges, holds a card, accepts terms, or submits anything: fix blocking_errors with ads_update_draft (uploading images via ads_prepare_image first), then give the buyer checkout_url to review the terms and pay in the browser. Totals over the card limit use payment_method ach, paid by bank or invoice in the browser. Amounts are whole USD.Read-only
ads_prepare_imagePrepare an image for an ad draft field (draft_id, kind and asset_kind) or for an existing campaign image slot (campaign_id and slot_id), checked against the returned constraints. Preparing does not change the draft or campaign: once status is ready, attach it with ads_update_draft creative_changes image_id (with a variant_key for a variant) or ads_update_campaign slot_changes image_id. Send the bytes one of three ways: 1. source_url, when the image is already at a public URL. 2. For a local file, prefer the upload: call without source_url or content, then POST the file as multipart field file to upload.url on www.producthunt.com with upload.headers before upload.expires_at, for example: curl -X POST -H "Authorization: Bearer <upload ticket>" -F [email protected] <upload.url> The ticket covers only this image; never send this connection's own token there. 3. content, only when you cannot reach www.producthunt.com.Changes data
ads_start_draftStart an empty ad composer draft or return your current unfinished draft without changing it. Requires account-wide portal access. Other members' drafts are never returned. This saves no campaign, payment, submission, or live creative. Use ads_update_draft to fill it in. Repeating this call resumes your current open draft. Add images with ads_prepare_image. Finish checkout in the browser; a managed account's draft (mode request) has no checkout and is sent to the ads team from the browser. Give the user preview_url to see the ad on the real Product Hunt homepage.Changes data
ads_submit_campaignSubmit an existing campaign's staged creative slot and associated launch changes for review. Requires editable portal access for the campaign. It always takes two calls, and only the second one submits. 1. Call without confirmation_token. Nothing is submitted; the result is outcome needs_confirmation with preview (the slot_changes and launch_change to send), side_effects, warnings for empty required slots, and a confirmation_token valid for 15 minutes. 2. Show the user the preview and side_effects and get their explicit confirmation. Then call again with confirmation_token and without preview. A token proves a preview was returned, not user approval: never pass one the user did not confirm. If the campaign changed since the preview, nothing is submitted (confirmation_invalid). On managed campaigns with live ads, eligible slot changes may go live immediately; self-serve campaigns, launch changes and newsletter sponsor copy wait for review.Destructive
ads_update_campaignEdit an existing campaign's self-serve creative slots, associated Product Hunt launch, or creative variants. Requires editable portal access for the campaign. Commercial terms (name, budgets, dates, placements, pause state) are not editable here. - Edits apply directly (outcome applied) and stay staged until ads_submit_campaign submits them; call it when the user is ready to submit. - Removing a live or submitted variant, or passing preview true, changes nothing and returns outcome needs_confirmation with preview, side_effects and a confirmation_token valid for 15 minutes. Show the user and resend the identical request with confirmation_token after they confirm. - Feed and billboard placements with a change in review on an approved campaign have locked true: they cannot edit slots or add variants until review finishes. Sponsor copy stays editable.Destructive
ads_update_draftSave only the changes the user requested to their unfinished ad composer draft. Requires account-wide portal access. Omitted fields and content added in the browser stay saved. This never submits, publishes, charges, or changes a live campaign. Checkout happens in the browser, where a request-mode draft is sent to the ads team instead. Give the user preview_url to see the ad on the real Product Hunt homepage.Destructive
find_alternativesFind alternatives to a product the user names. When to use: "alternatives to [product]", "apps like [product]", "[product] competitors", "what can I use instead of [product]?". Leave every filter at its default ("any", "all_time", []) unless the user stated the matching constraint. Do not infer a filter from the named product itself: Notion is freemium and productivity-tagged, but "alternatives to Notion" does not mean pricing "free_options" or tags ["productivity"]. For example: "alternatives to notion" → { "product_name": "notion" } "free notion alternatives" → { "product_name": "notion", "pricing": "free" } "self-hosted alternatives to slack" → { "product_name": "slack", "tags": ["self-hosted"] } Returns similar products with ratings, categories and relevance scores in an interactive carousel.Read-only
find_investable_startupsFind launches from a date window that Product Hunt's proprietary model ranks as likely to raise a Series A within two years of launch. Use it to surface promising startups; it is not investment advice. When to use: "promising startups that launched last month", "which recent launches look fundable", or any request to shortlist new startups by potential. For "new YC startups" or plain "recent launches", use search_launches instead. Only launches in the model's Top 10% are returned, strongest first. series_a_band ranks the launch against all Product Hunt launches, from "Top 0.1%" to "Top 10%". Quote it as given ("Product Hunt's model ranks this launch in the Top 1%"); it is a ranking, not a probability. For example: "which recent launches look fundable?" → {} "AI agent startups from Q3 2026 likely to raise" → { "category_slug": "ai-agents", "launched_after": "2026-07-01", "launched_before": "2026-09-30" }Read-only
get_categoriesList all available Product Hunt categories with their slugs. - When to use: When you need to find the right category_slug for get_products or search_launches, or when the user asks what categories Product Hunt has, or wants to browse available topics. - Returns: All searchable categories organised by parent/child hierarchy with slugs. Use the slug values directly in get_products(category_slug) or search_launches(category_slug).Read-only
get_launchRead one launch you own or manage as its hunter, maker or product team member: its content, what still needs work, and what can still change. In the result: - status is draft, unscheduled, scheduled or live. Until its launch day starts only you and its makers can see it; once live, every change is public. - assessment lists what still needs a change or a decision, the programs (contests, Hypership) open on its launch day, and investor questions with their prompt IDs. Resolution options are alternatives; suggestions are optional. - editable_fields names the fields that can still change. You are a maker when makers lists you. - hunter is who hunts a submitted launch; pending_hunter_invite is an invite to a new hunter, changed with update_launch hunterInvite. - editable_section_urls opens a website panel (media, company_info, investor_questions) when the user wants to edit there; otherwise link url. When discussing the launch, briefly mention relevant assessment suggestions without waiting to be asked, and keep blockers apart from optional improvements. Suggest a next step, but ask before changing anything.Read-only
get_launch_contextRead composer limits, account eligibility, midnight-Pacific date availability, the existing product a link belongs to, your matching draft, and bounded topic/category/maker/funding backer/shoutout product suggestions. With no product, the launch is a new product and needs no product question. Availability is a snapshot, not a reservation.Read-only
get_leaderboardGet the ranked Product Hunt leaderboard for a specific day, week, month, or year. - When to use: The user asks "what won on [date]?", "top launches in [week/month/year]", "#1 product on [date]", "Product Hunt winners for [period]", or wants the official ranking for a past or recent day, week, month, or year. - Args: date (required; YYYY-MM-DD for a day, YYYY-Www for an ISO week, YYYY-MM for a month, or YYYY for a year), limit (default 5, max 8). - Returns: Top-ranked products for that period with their rank, votes, makers, ratings and links in an interactive carousel.Read-only
get_my_accountReturn the authenticated Product Hunt account identity.Read-only
get_product_profileGet detailed information about a product including description, makers, categories, social links, pricing, ratings, review highlights, a company object (YC batch, founded date, team size, operating status), a funding object (total raised, latest round, notable investors), and series_a_band when the latest launch ranks in the top bands of Product Hunt's Series A forecast. - When to use: "tell me about [product]", "what is [product]?", "who made [product]?", "give me info on [product]", or wants a comprehensive overview of a specific product. - Args: product_name (name or slug). - Returns: Full profile with reviews, rating, sentiment, company, and funding details.Read-only
get_productsGet top-rated or recently launched products in a Product Hunt category. When to use: "best [topic] tools", "top [topic] apps", "find me a [topic] app", "top open source [topic] tools". Leave pricing and open_source at "any" unless the user said the matching constraint. For example: "best note-taking apps" → { "category_slug": "notes-documents" } "best free note-taking apps" → { "category_slug": "notes-documents", "pricing": "free" } "newest graphic design apps" → { "category_slug": "graphic-design-tools", "order": "recent_launches" } Returns products with names, ratings, taglines, categories and links in an interactive carousel.Read-only
list_my_launchesList launches you own or manage as hunter, maker, or active product team member, most recently changed first. status is draft (not submitted), unscheduled, scheduled, or live. Read one with get_launch and its launch_id. permitted_actions lists the tools and website editing that apply to each item; the write tools appear only when this connection can edit launches.Read-only
prepare_launch_assetStage a thumbnail or gallery image for a launch you own or manage. Staging changes neither the displayed images nor the launch revision: once the asset is ready, attach it with update_launch thumbnailAssetId or ordered galleryAssetIds for the same launch_id. Images are PNG, JPEG, WebP or GIF, up to 10 MB, 10000 pixels per side and 40 megapixels. Send the bytes one of three ways: 1. source_url, when the image is already at a public URL. 2. For a local file, prefer the upload: call without source_url or content, then POST the file as multipart field file to upload.url on www.producthunt.com with upload.headers before upload.expires_at, for example: curl -X POST -H "Authorization: Bearer <upload ticket>" -F [email protected] <upload.url> The ticket covers only this asset; never send this connection's own token there. 3. content, only when you cannot reach www.producthunt.com.Changes data
search_launchesSearch product launches on Product Hunt from the last 1 to 365 days (default 30). When to use: "what's new?", "latest AI launches", "trending products this week", "new YC startups", "open source products launched this week". query matches launch names and taglines literally. To find products by what they do ("tools that summarize meetings"), use semantic_product_search instead. Leave pricing, open_source and yc at "any" unless the user said the matching constraint, and pass days_ago when they named a time window. For example: "what's new on product hunt this week" → { "days_ago": 7 } "latest AI agent launches" → { "category_slug": "ai-agents", "days_ago": 7 } "new YC startups" → { "yc": "yc_only" } Returns recent launches with date, makers, ratings, YC status and links in an interactive carousel.Read-only
semantic_product_searchSearch Product Hunt products by a natural-language topic or use case, using vector similarity. When to use: the user describes what they want without naming a category or product. Prefer get_products when the user asks for a category and find_alternatives when they name a specific product. Leave pricing, open_source and recency at "any" / "all_time" unless the user stated the matching constraint; do not infer a filter from the query topic. When a filter exists for a constraint, use the filter instead of putting the constraint in query. For example: "tools for managing claude code sessions" → { "query": "manage claude code sessions" } "free AI screen recorders" → { "query": "ai screen recorder", "pricing": "free" } "AI agents launched this month" → { "query": "ai agent", "recency": "this_month" } Returns semantically similar products with ratings, categories and relevance scores in an interactive carousel.Read-only
start_launchStart a launch for a product link, or resume your existing unsubmitted launch for the same link and product choice without changing it (created: false). Omit product_choice for a new product; nothing needs confirming. Only when get_launch_context finds an existing product for the link, ask the user whether this launch belongs to it, then send product_choice "existing" with its product_id; a link that belongs to an existing product is refused as new. values uses the same fields as update_launch changes, except images, which are prepared for the returned launch_id. The launch starts as a private draft: starting it never submits, schedules or enrolls it. The result is the launch as get_launch reads it. If the outcome is unknown, retry the identical request with the same idempotency_key; a retry returns the original launch.Changes data
submit_feedbackSend feedback about the Product Hunt MCP to the Product Hunt team. Call only when the user explicitly asks you or approves requests to do so. Encourage the user to leave feedback when a tool or upload fails, results are wrong or confusing, a capability is missing, or a step needs a workaround, unless they've previously declined. Never include secrets or personal details about anyone.Destructive
submit_launchSubmit a draft launch so it is scheduled for its launch day, or created unscheduled and not public when it has no launchDate. It always takes two calls, and only the second one submits. 1. Call without confirmation_token. Nothing is submitted; the result is outcome needs_confirmation with preview.submit (the complete submission as Product Hunt would carry it out), side_effects (what it does and what becomes public), warnings and a confirmation_token valid for 15 minutes. validation_failed means something blocks submission; fix it with update_launch first. 2. Show the user the preview and side_effects and get their explicit confirmation. Then call again with confirmation_token: the launch is created and every side effect happens, such as adding makers, posting the first comment, publishing shoutouts, entering programs and notifying followers. The token proves a preview was returned, not that the user approved it. If the launch, its launch day, permissions or assets changed since, nothing is submitted (confirmation_invalid). A submitted launch's launch_id becomes its numeric ID.Destructive
update_launchChange a launch you own or manage, at any status. Change only fields in get_launch editable_fields. - Draft: a draft is private, so every change, including added makers, applies directly (outcome applied), even when incomplete. It never submits, schedules or enrolls the launch. - Submitted or live: public changes, moving the launch's day, and notifying added makers return outcome needs_confirmation and change nothing. Which edits are public cannot be predicted, since even a launch that is not live yet can change a public product page, so send changes without preview and let the server decide. On needs_confirmation, show the preview, reasons and side_effects, get explicit user approval, then resend with confirmation_token and without preview. A token proves a preview was returned, not user approval: never send one the user did not approve. Use preview true only when the user wants to inspect an edit before deciding whether to make it, never to check whether it needs confirmation. If they already requested draft edits and want to see the submission first or say not to submit yet, save the edits, then call submit_launch without a token to preview the complete submission. On revision_conflict nothing changed: reread the launch, keep the user's requested changes, ask about competing edits, and send only those changes.Destructive

Directory listings

DirectoryListingTierFirst seen
ChatGPTProduct Huntcommunity14 Nov 2026
ClaudeProduct Huntpartner14 Nov 2026