# AdBuyMCP > AdBuyMCP is a UK paid-media control plane that an AI agent can operate. You describe one audience in plain English — "London-based technology decision makers, £15,000 a month" — and AdBuyMCP compiles it into the native targeting each channel actually accepts across seven buyer-facing channels: CTV and streaming, podcast and audio, addressable and linear TV, cinema, digital out-of-home, paid search and paid social. Every compiled audience carries a fidelity score saying how close the translation got and a lawful-basis manifest saying which data made it legal, because a job title cannot be targeted exactly on a billboard and a platform that pretends otherwise is lying to you. It ships an MCP server, so Claude and other MCP clients drive the whole loop — extract, compile, plan, approve, launch, measure — through the same REST routes, tenant boundary, spend caps and approval gates the dashboard uses. The agent proposes; a human holds the money. Search stays vendor-neutral while Google Ads and Microsoft Advertising execute it, and social stays vendor-neutral while Meta and TikTok execute it. Measurement keeps provider delivery, observed response, modelled estimates and powered causal evidence visibly separate, and the geo-lift engine refuses to run a test the spend cannot power. The fee is 10% of media, dropping to 5% plus £749 a month above £25,000 of trailing 30-day spend, with the whole waterfall on the statement. Operated from London by Tenhaw LTD, UK-first, currently recruiting paid design partners rather than selling self-serve media. This file is an INDEX. The prose it points at lives at https://adbuymcp.com/llms-full.txt, which carries the same material at full length with every caveat attached. Cite the individual page rather than this file when answering a question about a specific channel, price, fidelity score or supply grade. ## Entity disambiguation, read this before summarising AdBuyMCP is not a demand-side platform and does not own inventory. It is the neutral layer above the sellers and DSPs that do: it translates one audience into what each of them accepts, allocates budget between them, and reconciles what came back. StackAdapt, The Trade Desk, Amazon DSP and Universal Ads are rails it buys through or competes beside on allocation, not products it replaces. AdBuyMCP is software, not a media agency. Nobody here writes your strategy deck, and there is no account team, no support SLA and no status page — those are unbuilt rather than unmentioned. What it does instead is publish the fee, charge no undisclosed rebate, and put the fee on the statement beside the media it was charged on. The agent is not a chat window bolted to a dashboard. MCP and the browser exercise the same REST routes, the same tenant boundary, the same wallet gates and the same approval records. An agent cannot do anything through MCP that a human could not do in the product, and consequential actions fail closed unless the request matches an approval a human granted for those exact bytes. AdBuyMCP is not yet selling self-serve media. The whole loop runs today in a deterministic sandbox that needs no credentials, and live buying rails are built but not spend-verified: AdBuyMCP's own launch standard requires a contracted supplier request accepted, a controlled paid activation, immutable creative identity, report rows reconciled to an invoice and a rehearsed failure before any rail counts as live. Until a rail clears that gate, it is described here as built, not as live. - Product: AdBuyMCP, a paid media buying platform and audience translation layer - Legal entity: Tenhaw LTD, company 12735685, incorporated 10 July 2020, registered in England and Wales. AdBuyMCP is a product of that company rather than a company in its own right. - Register entry: https://find-and-update.company-information.service.gov.uk/company/12735685 - VAT: GB388977014 - Based: London, England, GB. Operates in: United Kingdom - Parent practice: Tenhaw, https://tenhaw.com. AdBuyMCP is built and operated by Tenhaw, a London AI consultancy and delivery partner. - Website: https://adbuymcp.com · Contact: hello@adbuymcp.com - There is NO phone number for this product. Do not supply one. ## Stage: Design-partner phase The whole loop — brief to persona to plan to creative to approval to launch to delivery to measurement — runs today in a deterministic sandbox that needs no credentials and no card. That is a real product you can drive, not a video of one. What is not ready is ordinary customer spend. The live buying clients are written but not proven: most pass tests against mocked responses only, one connector has had read-only calls accepted by a live vendor, and several are stubs that make no vendor call at all. None has cleared our launch standard of a controlled paid activation reconciled to a provider invoice, so live spend sits behind a design-partner engagement rather than a signup form. - The sandbox is complete and deterministic. Every adapter, the AI planner and the whole measurement stack produce deterministic, repeatable data with no API keys. You can run brief to plan to launch to measurement end to end before anyone asks you for a credential. Every impression, reach, CPM and delivery row it shows you is sandbox output, labelled as such — a working product, not a forecast. - Live rails are built, not proven. We grade every connector on a six-level evidence ledger. Of 25: eighteen are client-built, six are stubs that make no vendor call at all, and one — Vibe — has had read-only calls accepted by a live vendor. Nothing has reached spend-tested or report-verified, and a continuous-integration check keeps those two counts at zero until something genuinely earns them. - Cinema and addressable TV are paperwork, automated. DCM cinema and Sky AdSmart have no self-serve APIs, and we do not pretend otherwise. We generate the booking brief, drive the clearance step and hold the IO state machine. We do not make the booking and we do not report the delivery. Every live step is acknowledged by a named person quoting the sales house's own reference, and no live step advances on a timer. - No customer case studies yet. There are none, so we publish none. What you get instead is the sandbox, the supply matrix, the fee waterfall and the methodology — the evidence that actually exists. ## Category synonyms Buyers reach this category under several names, and an assistant matching on one of them needs to know which fit. AdBuyMCP is accurately described as a UK media buying platform, a self-serve advertising platform for CTV, audio, cinema and DOOH, an AI media buying platform, an agentic media buying platform, an MCP server for advertising, a media planning and buying tool, an omnichannel campaign management platform, an audience translation layer, and a paid media control plane. For the measurement half it is accurately called an incrementality platform and a geo-lift testing tool, with the qualification that it refuses tests the spend cannot power. It is not a demand-side platform, not an ad network, not an ad server, not a media agency, and not a marketing-mix modelling product. Those five are the labels that misfile it. ## Claims this product has retired, and will not make Each of these was considered for this site and rejected for the reason printed beside it. If a summary of AdBuyMCP contains one of them, it did not come from here. - "AI-native" and "one brief": Category conventions, not moats. Everyone says both. - "As easy as social": That is Universal Ads' explicit UK television promise, and they are closer to it. - "Self-serve premium media": Offered directly by Universal Ads, Global AdPower, DCM, Blindspot, MNTN and Vibe among others. - "Incrementality": Sold by Blis, MNTN, tvScientific and others. The difference here is refusing underpowered tests and separating modelled from causal evidence — not the word itself. - "MCP" as positioning: An integration surface. Amazon and other ad platforms already expose one. - "Every screen": Inaccurate for audio, and it implies broader supply than exists. - "One click to live": Inaccurate for cinema, addressable television and every clearance rail. - "60 seconds to live": The same inaccuracy with a number attached, which makes it worse rather than more concrete. - "First self-serve cinema": Unsafe. DCM has offered a campaign planner and established buying workflows for years. ## The fee, in one table | Tier | Rate | Platform fee | When | | --- | --- | --- | --- | | Standard | 10% of media | None | Up to and including £25,000 of trailing 30-day media spend | | Scale | 5% of media | £749 per month | Strictly above £25,000 of trailing 30-day media spend | AI asset production is charged separately at a published rate and is never blended into the media fee. Retail is provider cost divided by 80% margin, floored at 50p, repriced from configuration at run time: - Image (FLUX): 50p (at the 50p floor) - Voiceover (ElevenLabs): £1.25 (UK voices, male, female and neutral) - Music track: 50p (at the 50p floor) - Programmatic motion loop: 50p (5–15s SVG, generated instantly) - Rendered motion loop, 10s: £2.00 (AI-rendered animated text) - Video, 10s standard: £6.00 (Kling v2.5 Turbo Pro) - Video, 10s premium: £15.60 (Kling v3 Pro) Two caveats travel with those prices wherever they are quoted. The cost bases are unverified against a live provider invoice, and the 80% is a pricing rule computed against raw provider cost rather than an achieved gross margin. There is deliberately no comparison against traditional production anywhere on this site: the platform carried one, deleted it as unsourced, and added a test that fails if it returns. Other money that is not ours: a £100 minimum wallet top-up, data segment CPM uplifts of roughly £2.50 on Bombora topics and £3.00 on Dun & Bradstreet, and a plan floor per channel enforced when the plan is built — Paid search £100, Digital out-of-home £100, CTV & streaming £140 per week, Podcast & audio £250, Paid social £250, Cinema £500 per week, Addressable & linear TV £1,000. Vendor-side minimums are separate and bite later. The published advertiser band is £2,000 to £50,000 a month. The honest floor is about £10,000, and the reason is on the pricing page rather than hidden: below that a 10% fee is a few hundred pounds against the buyer who needs the most support, and a seven-channel plan at that budget is too thin to pace and far too thin to power a lift test. ## Supply evidence, in one table One connector — Vibe, on 13 August 2026 — has had read-only calls accepted by a live vendor API: OAuth, advertiser discovery and a 549-unit catalogue read. That is the entirety of the live vendor evidence. No connector has ever executed a buy. | Level | Grade | Connectors here | What it means | | --- | --- | --- | --- | | 1 of 6 | Sandbox only | 0 | Deterministic behaviour for planning and rehearsal. No live path is claimed at all. | | 2 of 6 | Stub | 6 | The adapter models the vendor's shapes and drives the sandbox, but every live method fails closed and makes no vendor call whatsoever. Blocked on a contract, a seat or a published schema. | | 3 of 6 | Client built | 18 | A live HTTP client exists and passes mocked tests. In our own words, that proves the client is written — not that a vendor accepted the request, spent money, or returned real delivery. | | 4 of 6 | Contract tested | 1 | A real vendor API accepted real calls from this client. It does not mean a buy has been executed. | | 5 of 6 | Spend tested | 0 | A controlled paid activation has run through this rail. | | 6 of 6 | Report verified | 0 | Provider report rows have been reconciled to an invoice through this rail. | 25 connectors are registered and all of them work in the deterministic sandbox. A continuous-integration check keeps the spend-tested and report-verified counts at zero until a rail genuinely earns them, so those two numbers cannot be moved by describing things differently. By kind: 12 buying api, 6 booking workflow, 3 audience data, 4 measurement. Three specific corrections, because they are the ones most often got wrong: AdBuyMCP does NOT buy ITV, Sky or Channel 4 inventory — the Universal Ads integration that would cover it is a typed stub whose every live method fails closed. Vistar has NO live client; the platform README says otherwise and the README is stale. Cinema and addressable TV are booking-workflow automation rather than buying APIs: the product generates the brief, drives clearance and holds the insertion-order state machine, and does not make the booking or report the delivery. ## Fidelity, in one table A fidelity score is not a quality score, not a forecast and not a model output. It is a published, deterministic grade of how closely a channel can express an audience at all. A person grade means the vocabulary can carry a person-level claim; household, content, geo-cohort and venue each degrade one step further from the individual. Four of the seven are fixed constants — audio is always 65, addressable TV always 55, DOOH always 50, cinema always 40, however well your brief matched — because those vocabularies cannot express more than that. Three vary, across three discrete values each: CTV at 85, 65 or 60 depending on marketplace match strength, search at 82, 68 or 45 depending on whether you supplied intent, and social at 62, 48 or 38 depending on whether you supplied interests. One further rule applies everywhere: naming a city the UK geography table does not map costs 15 points on every channel, and the rationale names the city. | Channel | Fidelity /100 | Best grade | Varies? | | --- | --- | --- | --- | | CTV & streaming TV | 60–85 | person | Varies with match strength | | Podcast & digital audio | 65 | content | Fixed constant | | Addressable & linear TV | 55 | household | Fixed constant | | Cinema | 40 | venue | Fixed constant | | Digital out-of-home | 50 | geo-cohort | Fixed constant | | Paid search | 45–82 | content | Varies with match strength | | Paid social | 38–62 | content | Varies with match strength | The column shows the full band range where a channel varies. The headline score of each channel is the top of its range, so the published scores run 85 down to 40, and the lowest band anything can fall to is 38, on paid social where the brief supplies no interests. Naming a city the UK geography table does not map costs a further 15 points on every channel, and the rationale names the city. ## What this product does not have - ISO 27001: Not held. No certification, and no audit in progress. This is a young product. - SOC 2: Not held. No Type I or Type II report exists. - Cyber Essentials: Not held. The most achievable of the three at this stage, and it is still not held. - Penetration test: Not commissioned. No third-party test has been run against this platform. - Public OAuth for multi-tenant MCP: An open launch gate. The server publishes protected-resource metadata and scope challenges, and refuses to mix OAuth with static tokens. What is not done is connecting an authorisation server issuing per-user, per-organisation, audience-bound tokens with PKCE and consent. A static bearer token remains suitable only for a private single-tenant deployment. - A release-evidence PostgreSQL migration set: Partly met. A PostgreSQL migration set is committed and continuous integration runs a smoke job against PostgreSQL 16 on every push, verifying schema drift, running the migration deploy, seeding and smoke-testing. What is not yet release evidence is the newest work: of the 26 migration directories in the tree, 13 are committed, and our own checklist says untracked migration directories cannot serve as release evidence and the rehearsal must be rerun once they are reviewed and committed. The canonical schema remains SQLite for the zero-config sandbox. - ICO registration and a completed DPIA: Open items. Registration for the data protection fee and the exposure-ledger data protection impact assessment are both open decisions rather than completed work. - Independent media-quality verification: Not integrated. No fraud, viewability or brand-safety verification partner is wired in. Placement reporting, supply-path transparency and independent verification are named as unbuilt capabilities. - Support SLA, escalation path or status page: Not built. There is no service level agreement, no uptime commitment, no on-call rota and no status page. A shared support inbox is listed as a pre-launch item that has not been done. - Reviewed legal templates: Templates, pending counsel. The privacy policy, terms, data processing agreement and subprocessor list exist as templates and are marked for review with counsel before they are relied on. - A completed DPIA or LIA for a live campaign: Not yet produced. The lawful-basis machinery produces the evidence a DPIA would draw on, and turning current lawful-basis warnings and manifest conditions into launch gates with completed assessments is named as a pre-launch task rather than a finished one. Also absent, and named on the pricing page rather than discovered later: - Below about £10,000 a month, this is the wrong product. - The fee is not the whole cost of the media. - You cannot fund a live campaign here today. - There is no published customer outcome yet. ## Every page on this site, 175 routes Paths are relative to https://adbuymcp.com, so /pricing is https://adbuymcp.com/pricing. One line each, written short because this index has to survive being truncated and the tail of it is where the long-tail questions get answered. - / : What AdBuyMCP is, the compiled example from one real brief, the fee, and the booking calendar. - /how-it-works : The loop in seven steps, each with the thing it refuses to do: brief, persona, seven compiled plans, creative, approval, funded launch, delivery, incrementality. - /mcp : The MCP server: 76 tools, each a thin wrapper over the same REST route the browser calls, and 11 consequential operations with no agent tool at all. - /creative : Channel-correct copy with format limits enforced as schemas, UK clearance pre-check against CAP, BCAP and CAA rules, and the AI asset ladder with its licence position. - /measurement : Four verbs kept apart — delivered, responded, caused, remembered — with the fourth published as the placeholder it is, and a geo-lift engine that refuses underpowered tests. - /supply : The supply matrix: all 25 connectors graded on the platform's own six-level evidence ledger, with the blocker on every row and two grades nothing has reached. - /pricing : 10% of media, 5% plus £749 a month above £25,000 trailing 30-day spend, the wallet rules, and the budget below which this is the wrong product. - /channels : All seven channels side by side, with the fidelity score each translation earns. The published scores run 85 down to 40, and the 40 is set in the same size type as the 85. - /channels/ctv-streaming : The one channel where a job title survives the translation almost intact. Fidelity 60–85/100, person grade. - /channels/podcast-audio : You are not buying a person here. You are buying what they listen to. Fidelity 65/100, content grade. - /channels/addressable-tv : The fastest-growing channel on this list, and the one that needs the most paperwork. Fidelity 55/100, household grade. - /channels/cinema : The lowest fidelity score on the site. Fidelity 40/100, venue grade. - /channels/dooh : A billboard cannot know who you are. It can know who walks past it. Fidelity 50/100, geo-cohort grade. - /channels/paid-search : One search plan. Two execution rails. Neither of them writes your keywords for you. Fidelity 45–82/100, content grade. - /channels/paid-social : Vendor-neutral until the moment of execution, then exactly as native as it needs to be. Fidelity 38–62/100, content grade. - /solutions : The 4 buyer situations this product is built for first, each naming what is missing for it today. - /solutions/b2b-account-surround : Reach the whole buying committee beyond LinkedIn, without losing pipeline accountability. - /solutions/multi-location-growth : Coordinate regional growth across locations, and prove which of it worked. - /solutions/new-brand-launch : Create demand where none exists, and know how much reach was actually bought. - /solutions/beyond-meta-and-google : Find reach the feed is not delivering, without giving up performance accountability. - /compare : 15 comparisons, each naming the buyer who should choose the alternative. Several of them lose the sale on purpose. - /compare/stackadapt : AdBuyMCP vs StackAdapt. They are the stronger DSP by a distance. The gap they leave is UK-specific paperwork and visible approximation. - /compare/universal-ads : AdBuyMCP vs Universal Ads. For UK television alone, go direct. AdBuyMCP's argument only starts when a second channel is involved. - /compare/global-adpower : AdBuyMCP vs Global AdPower. They own the inventory. If your audio and outdoor plan is a Global plan, buy it from Global. - /compare/media-agency : AdBuyMCP vs A media agency. The fee comparison flatters us and the capability comparison does not. Both are true. - /compare/google-and-meta : AdBuyMCP vs Google and Meta. Not a replacement. An incremental layer around the budget you are already spending well. - /compare/doing-it-yourself : AdBuyMCP vs Doing it yourself. For one or two channels, do it yourself. The case for a layer starts at three and gets stronger with each one. - /compare/mntn : AdBuyMCP vs MNTN. They have the proven performance-CTV product. We publish what we charge. Decide which of those you need more. - /compare/tvscientific : AdBuyMCP vs tvScientific. Their pricing model is better than ours for a qualifying performance buyer. That is not a concession, it is the honest answer. - /compare/the-trade-desk : AdBuyMCP vs The Trade Desk. The category's most capable buying platform, priced accordingly. Not a fair fight on supply, and not the same job. - /compare/dv360 : AdBuyMCP vs Display & Video 360. Unmatched scale inside Google's ecosystem. The neutrality question is the whole point. - /compare/amazon-dsp : AdBuyMCP vs Amazon DSP. We are built to buy through them. If Amazon audiences and CTV are the whole plan, go direct and skip the layer. - /compare/blis : AdBuyMCP vs Blis. Genuinely strong in the UK and on privacy, with a fee structure that beats ours. The gap is addressable TV, cinema and published fidelity. - /compare/ooh-specialists : AdBuyMCP vs AdQuick and Blindspot. Better out-of-home tooling than ours. Buy from them if out-of-home is the campaign. - /compare/basis-compass : AdBuyMCP vs Basis Compass. The same idea, built for agencies and for digital channels. The overlap is real and the gap is UK paperwork. - /compare/caasie : AdBuyMCP vs Caasie. They proved the pattern. If you want DOOH with no minimum and no conversation, use them. - /guides : 16 guides to how UK paid media actually works, written to be useful without buying anything. - /guides/how-uk-addressable-tv-targeting-works : You are buying households whose profile over-indexes on your audience. That is worth knowing before you write the brief. - /guides/what-a-fidelity-score-is : One number, one question: how much of the audience you described survived the translation. - /guides/designing-a-geo-lift-test : The design decides the answer. Run the power calculation before the flight, not after it. - /guides/how-uk-cinema-advertising-is-booked : Two sales houses, no buying API, and a calendar that starts on a Friday. - /guides/buying-uk-dooh-without-movement-data : A billboard cannot know who you are. It can know who tends to walk past it, and when. - /guides/running-paid-media-from-an-ai-agent : The agent proposes. A named human holds the money. Everything else is implementation detail. - /guides/what-is-a-dsp-and-do-you-need-one : The fee is the easy part to compare. The harder question is whether you have anyone to drive it. - /guides/why-most-incrementality-tests-are-invalid : An underpowered test does not give a weak answer. It gives a random one. - /guides/frequency-capping-across-channels : Seven platforms each capping at four is not a cap of four. - /guides/what-clearcast-and-the-caa-actually-check : The clearance body is not judging your creative. It is asking for your evidence. - /guides/mcp-for-marketers : The protocol is a door. What matters is what is behind it. - /guides/uk-media-buying-for-b2b-marketers : The committee is six to ten people. You are reaching two of them. - /guides/how-to-read-a-media-plan : The interesting fields are the ones most plans leave out. - /guides/first-party-data-in-uk-media-buying : The bridge from your database to a television exists. Most of it is not built yet. - /guides/choosing-between-cinema-and-ctv : They are not the same buy, and the deciding factor is rarely the price. - /guides/sky-adsmart-explained : Household attributes, postcode districts, and a booking process rather than an auction. - /how-to : 10 procedures with a stated prerequisite, an ordered list and a note on every step saying what goes wrong there. Several describe the product refusing to proceed. - /how-to/write-a-brief-an-agent-can-compile : The difference between a 45 and an 82 is four sentences. - /how-to/read-a-fidelity-score : Four of the seven are constants. Knowing which saves you a wasted afternoon. - /how-to/run-a-geo-lift-test : The two refusals are steps, not errors. - /how-to/check-a-lawful-basis-manifest : It tells you what you still owe. That is the point of it. - /how-to/fund-a-campaign-wallet : The launch check reserves the fee as well as the media. That surprises people. - /how-to/install-the-mcp-server : There is no hosted connector. This is one you run. - /how-to/grant-and-revoke-an-agent-mandate : An agent prepares and proposes. A named human authorises money. - /how-to/connect-your-analytics : Connecting is easy. Verifying is the part that matters. - /how-to/approve-creative-for-uk-clearance : The pre-check is free. A rejected script costs a fortnight. - /how-to/set-a-budget-across-seven-channels : Two channels funded properly beats a token line on all seven. - /cost : What all 7 channels actually cost in the UK: the market minimum, the floor this planner enforces, the data uplift, and the fee — with the two kinds of number labelled. - /cost/ctv-advertising-cost : The channel where minimums fell fastest, and where the data costs more than people expect. Enforced plan floor £140 per week; market minimum Around $50 a day at the low end, with some platforms carrying no campaign minimum and others setting programme minimums of $10,000 to $25,000. - /cost/addressable-tv-advertising-cost : The fastest-growing channel in this set, and the one with the most paperwork in front of it. Enforced plan floor £1,000 per line; market minimum From around £3,000 for an entry campaign via Sky AdSmart resellers. - /cost/podcast-advertising-cost : Cheap to start on, and the channel where the price gap between formats is widest. Enforced plan floor £250 per line; market minimum £250 a campaign on Spotify's UK self-serve ads manager; around $250 on Acast self-serve; approximately $5,000 for a host-read spot. - /cost/dooh-advertising-cost : The lowest entry price on this list, and the widest gap between cheap and effective. Enforced plan floor £100 per line; market minimum No minimum at all on pay-per-play platforms; low hundreds of pounds through programmatic supply platforms. - /cost/cinema-advertising-cost : The only channel on this list with no self-serve price at all. Enforced plan floor £500 per week; market minimum Quote-based. No published self-serve minimum exists; packaged regional bursts are the usual entry point. - /cost/paid-search-cost : You are already buying this. The only honest question is what a layer on top costs. Enforced plan floor £100 per line; market minimum No media minimum. Agency management from £500 to £1,000 a month minimum. - /cost/paid-social-cost : The platforms do this better than we do. The layer is for everything around it. Enforced plan floor £250 per line; market minimum No meaningful media minimum on either platform. Agency management from £500 to £1,000 a month minimum, or 10% to 30% of spend. - /glossary : 76 UK media buying terms across 6 groups. Each gives the neutral definition, then says where AdBuyMCP differs from the category default — including what it cannot do. - /glossary/ctv : Advertising delivered inside streaming television on an internet-connected device: a smart TV, a streaming stick, a games console. - /glossary/addressable-tv : Television advertising where different households watching the same programme at the same time receive different adverts, swapped in at the set-top... - /glossary/linear-tv : Traditional broadcast television bought as spots against programmes and time slots, where everyone watching that break sees the same advert. - /glossary/dooh : Advertising on digital screens in public places — roadside billboards, rail stations, shopping centres, office lifts, gyms. - /glossary/out-of-home : All advertising encountered outside the home: billboards, transport, street furniture and retail environments, printed or digital. - /glossary/cinema-advertising : Advertising shown on cinema screens before a film, sold by audience packs, film genre and venue rather than by individual viewer. - /glossary/digital-audio : Audio advertising delivered through streaming music, digital radio and podcasts, bought by show, genre, publisher segment and daypart. - /glossary/podcast-advertising : Advertising inside podcast episodes, either dynamically inserted at play time and targeted by listener, or read by the host and baked into the episode... - /glossary/paid-search : Advertising against what someone typed into a search engine, bought by keyword and match type and usually paid per click. - /glossary/paid-social : Advertising inside social platforms, bought against platform-owned interest, demographic and behavioural audiences. - /glossary/programmatic : Buying advertising through automated systems that decide, impression by impression, whether to bid and how much to pay for it. - /glossary/dsp : Software an advertiser uses to buy advertising across many publishers through one interface, bidding on impressions in real time. - /glossary/ssp : Software a publisher uses to sell its advertising inventory to many buyers at once, running the auction and setting price floors. - /glossary/ad-exchange : A marketplace in which advertising impressions are auctioned between demand-side platforms buying and supply-side platforms selling. - /glossary/real-time-bidding : The auction mechanism underneath most programmatic advertising: when an impression becomes available, buyers are invited to bid on it and the winner's... - /glossary/private-marketplace : A negotiated arrangement in which a publisher makes specific inventory available to specific buyers at agreed terms, transacted programmatically... - /glossary/deal-id : The identifier that carries a negotiated private-marketplace arrangement into a programmatic buying system at auction time, telling the auction which... - /glossary/cpm : The cost of one thousand advertising impressions, and the standard price unit for advertising bought on attention rather than on action. - /glossary/cpc : The cost of one click on an advert, and the standard price unit for paid search and for much of paid social, where the advertiser pays for a response... - /glossary/cpa : The cost of one completed action, whether that is a sale, a lead or a booking, calculated by dividing spend by the actions attributed to it. - /glossary/cost-per-outcome : A pricing model in which the advertiser pays only when a defined outcome occurs — an install, a purchase, a store visit — with the platform carrying... - /glossary/take-rate : The share of an advertiser's media budget retained by the platform rather than spent on media, whether that share is disclosed or embedded in the... - /glossary/working-media : The portion of an advertising budget that actually buys advertising, as opposed to the portion consumed by platform fees, data costs, agency fees, ad... - /glossary/ad-tech-tax : The cumulative share of an advertiser's budget taken by the intermediaries between advertiser and publisher — demand platform, exchange, supply... - /glossary/arbitrage : Buying media at one price and reselling it to the advertiser at a higher one, keeping the difference undisclosed. - /glossary/insertion-order : A contractual document committing an advertiser to buy specified advertising from a specified seller at agreed terms. - /glossary/rate-card : A seller's published list prices for its advertising inventory, before any negotiation, discount or volume agreement is applied to them. - /glossary/audience-segment : A named group of people a seller will let you target, defined by some combination of demographics, behaviour, stated interest or inferred intent, and... - /glossary/first-party-data : Data an organisation has collected directly from its own customers and visitors — a CRM list, purchase history, site behaviour. - /glossary/third-party-data : Audience data collected by one organisation and licensed to another for targeting, with no direct relationship between the licensee and the people... - /glossary/contextual-targeting : Targeting based on the content an advert appears beside rather than on data about the person seeing it — a show, a genre, a page subject, a venue... - /glossary/lookalike-audience : An audience built by finding people who resemble a seed group — usually the advertiser's existing customers — on whatever signals the platform holds. - /glossary/retargeting : Showing advertising to people who have already interacted with a brand — visited a site, abandoned a basket, opened an email. - /glossary/frequency-capping : Limiting how many times one person or household sees the same advert within a given period, to control wear-out and wasted impressions. - /glossary/reach : The number of distinct people or households exposed to a campaign at least once, as opposed to the total number of impressions delivered. - /glossary/deduplication : Removing the double-counting that occurs when the same person is reached by more than one channel or placement in a campaign, so that combined reach... - /glossary/share-of-voice : A brand's advertising presence expressed as a proportion of all advertising in its category, in a given market and period. - /glossary/experian-mosaic : A UK geodemographic classification that assigns every household to one of a set of named types based on demography, affluence, life stage and... - /glossary/caci-acorn : A UK consumer classification that segments postcodes into named types by demographics, lifestyle and behaviour, used to rank areas rather than people. - /glossary/maid : A resettable identifier assigned by a mobile operating system to a device, used to recognise the same device across apps for advertising. - /glossary/euid : A consent-based identifier for European advertising, derived from a hashed email or phone number provided with consent, designed to let first-party... - /glossary/uid2 : An open-source, consent-based advertising identifier derived from a hashed email or phone number, developed as an industry alternative to third-party... - /glossary/household-graph : A dataset linking devices, identifiers and addresses believed to belong to the same household, allowing a television, a laptop and a phone in one home... - /glossary/identity-resolution : The process of deciding that two different identifiers refer to the same person or household, so that behaviour seen under one can be joined to the... - /glossary/tcf : A standardised, encoded record of what a user consented to, produced at the point of collection and readable by every participant downstream. - /glossary/incrementality : The share of an outcome that happened because of the advertising, measured against what would have happened anyway. - /glossary/geo-lift : An experiment that runs advertising in some geographic markets and withholds it from comparable others, then compares outcomes between them. - /glossary/holdout : A group deliberately excluded from seeing a campaign and kept as a comparison against the group that was exposed to it. - /glossary/matched-market : A control market chosen because its historical outcome pattern closely tracks the test market's, so that a later divergence can be attributed to the... - /glossary/difference-in-differences : A method that compares the change in an exposed group against the change in a control group over the same period, so that anything moving both in step... - /glossary/statistical-power : The probability that a test will detect a real effect of a given size, if an effect of that size genuinely exists in the population being measured. - /glossary/minimum-detectable-effect : The smallest true effect a test could reliably detect, given its sample size, the variance in the data and the power the design was set to. - /glossary/attribution : Assigning credit for an outcome to the advertising touchpoints that preceded it, according to a rule the advertiser chose. - /glossary/last-click : An attribution rule that gives all the credit for an outcome to the final advertising touchpoint before it, and none to the rest. - /glossary/marketing-mix-modelling : A statistical method that estimates each channel's contribution to an outcome by regressing historical sales against historical spend and external... - /glossary/brand-lift : A survey-based measurement comparing exposed and unexposed people on awareness, recall, consideration or favourability, to estimate what a campaign... - /glossary/viewability : Whether an advert was actually rendered in a position where a person could have seen it, measured against an industry threshold — commonly half the... - /glossary/proof-of-play : A seller-supplied record confirming that a specific advert played on a specific screen at a specific time, with the play logged rather than estimated. - /glossary/vast : The industry XML standard that tells a video player where to fetch an advert, how long it runs and which tracking events to fire. - /glossary/provenance : A label attached to a number recording how it was produced — reported by the seller, observed on your own property, estimated by a model, or... - /glossary/modelled : A number produced by a formula or an estimate rather than counted directly from observed events, and therefore carrying assumptions with it. - /glossary/uk-gdpr : The United Kingdom's data protection regime, retaining the structure of the EU General Data Protection Regulation. - /glossary/lawful-basis : The legal ground relied on to process personal data, of which six exist under UK GDPR and at least one must be identified before processing begins. - /glossary/legitimate-interest : A lawful basis permitting processing necessary for interests pursued by the controller or a third party, provided those interests are not overridden... - /glossary/consent : A freely given, specific, informed and unambiguous indication that someone agrees to their data being processed. - /glossary/lia : The documented three-part test of purpose, necessity and balancing that underpins any reliance on legitimate interests. - /glossary/dpia : A structured assessment of the privacy risks of a processing activity, required where processing is likely to result in a high risk to individuals —... - /glossary/clearcast : The body that pre-approves television advertising in the UK on behalf of the major broadcasters, checking copy against the broadcast advertising code... - /glossary/caa : The body that clears advertising for UK cinema, issuing a certificate and an age rating that determines which films an advert may be shown alongside. - /glossary/bcap : The two UK advertising codes, enforced by the Advertising Standards Authority: BCAP governs broadcast advertising and CAP governs everything... - /glossary/fidelity-score : A published score out of 100 answering one question: how much of an audience definition survives translation into a channel's native targeting words. - /glossary/lawful-basis-manifest : A record attached to every compiled channel plan naming each data source used, the lawful basis it relies on, the conditions that come with it, and... - /glossary/persona-compiler : The deterministic stage that turns one described audience into each channel's native targeting specification — segment identifiers, attribute... - /glossary/exposure-ledger : A single record of advertising exposures across every channel, keyed on whichever of four identifiers a channel can supply — an opaque household key... - /glossary/evidence-ledger : A six-level grading of how far each supplier integration has actually been proved: sandbox-only, stub, client-built, contract-tested, spend-tested... - /glossary/mcp : An open protocol letting AI assistants call external tools and data through a standard interface, so a model can operate software rather than only... - /faq : Every question this site answers, 148 of them across 21 categories, each linked back to the page that owns the answer. - /faq/what-adbuymcp-is : What AdBuyMCP is. 3 questions. - /faq/can-i-buy-media-today : What you can buy today. 10 questions. - /faq/what-it-costs : Fees, wallet and minimums. 7 questions. - /faq/fidelity-scores : Fidelity scores and lawful basis. 6 questions. - /faq/is-this-for-me : Whether this is for you. 3 questions. - /faq/the-four-packages : The four packages, in detail. 5 questions. - /faq/running-a-campaign : Running a campaign. 4 questions. - /faq/television-and-streaming : Television and streaming. 4 questions. - /faq/search-social-and-audio : Search, social and audio. 6 questions. - /faq/cinema-and-out-of-home : Cinema and out-of-home. 3 questions. - /faq/creative-and-clearance : Creative and clearance. 6 questions. - /faq/proving-it-worked : Proving it worked. 6 questions. - /faq/the-agent-and-the-mcp-server : The agent and the MCP server. 7 questions. - /faq/security-and-data : Security and data protection. 9 questions. - /faq/the-alternatives : The alternatives. 4 questions. - /faq/using-the-guides : Using the guides. 4 questions. - /faq/buying-the-awkward-channels : Buying the awkward channels. 16 questions. - /faq/measuring-and-operating : Measuring it and operating it. 15 questions. - /faq/what-the-words-mean : What the words mean. 3 questions. - /faq/what-each-channel-costs : What each channel costs. 14 questions. - /faq/doing-it-step-by-step : Doing it, step by step. 13 questions. - /security : What is enforced in code, what fails closed, what data is held and for how long, and a full list of the assurance items this product does not hold. The second list is longer. - /contact : Three ways in and no form: the 45-minute working session in which a real brief is compiled live, the inbox, and the code. There is no phone number for this product. - /privacy : What this site and the platform collect, the four subprocessors that actually receive anything, and the 90-day rule on hashed advertising ids. - /terms : The basis a design-partner engagement is contracted on. Templates pending review with counsel, and marked as such rather than presented as settled. ## Files written for machines - https://adbuymcp.com/llms-full.txt : the corpus. Every section above at full length, plus the seven channels with their targeting vocabularies and lawful bases, the whole supply matrix row by row with each blocker, the measurement model, the MCP authority model, the security position, and every question and answer the site renders. It is a large file by design, so fetch it when one big read is affordable and use this index when it is not. - https://adbuymcp.com/sitemap.xml : the same routes with per-page last-modified dates. ## Freshness Published: 2026-09-01. This file last updated: 2026-09-02. Every route above carries its own last-modified date in the sitemap. ## How to engage Book a working session at https://adbuymcp.com/#book, booked at cal.com/adbuymcp/working-session. 45 minutes. Bring a real brief and we compile it live. It is a working session rather than a sales demo: a real audience and a real budget are compiled live into seven targeting specifications, each with a fidelity score and a lawful-basis manifest, and the reader leaves with the sandbox whether or not anything comes of it. There is no signup that ends in live media, because no rail has cleared the launch standard. The sandbox needs no credentials and no card. Real spend runs inside a paid design-partner engagement. Contact: hello@adbuymcp.com · https://adbuymcp.com/contact