The Profound Agency is a remote MCP server that gives an AI agent 24 tools, among them ask, can_i_advertise, check_order_status. It answers at https://theprofound.agency/api/mcp/ over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 2 October 2026; the last check, on 17 November 2026, succeeded.
Search, price and order press placements across 1,600+ publications. Free AI-visibility audits too.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
ask | A question in plain words, answered from theprofound.agency with source URLs: publication prices, whether a category can advertise on a channel, the fee, refund terms, definitions, channel requirements, and anything the FAQs, glossary, chan Inputs: question |
can_i_advertise | Whether a restricted category — alcohol, cannabis/CBD, tobacco, casinos, firearms, supplements, political, housing, loans, crypto and the rest — can run on a channel, and with what limits (age gates, restricted targeting, pre-approval). Giv Inputs: category, channel, state |
check_order_status | Payment and fulfilment state for an order you created. Requires the billing email the order was placed with, which is what stops anyone reading anyone else's order. Returns paid: false plus the payment link while it is still awaiting paymen Inputs: orderId, email |
compare_placements | Two to four publications side by side: price, Domain Authority and Rating, monthly traffic, link type, turnaround, region, disclosure, indexing, categories, genres, accepted niches and their prices, and labels, with which is cheapest, faste Inputs: ids |
create_booking_link | The agency's booking URL for a 30-minute meeting, returned with the human's name and email as separate fields. Give the human the URL and ask them to enter the name and email on the booking page — the meeting does not exist until they confi Inputs: name, email |
create_order | Open a pending order for a client and return a payment link. IMPORTANT: this does not pay for anything. The order stays unpaid until a human opens the returned payUrl and pays on the store's checkout. Give the link to the client or to someo Inputs: items, contact, placedBy, clientReference, notes |
create_text_link | A text message to the agency's number, (908) 448-4001, prepared for the human to send from their own phone: returns the message and an sms: link that opens their messaging app with it filled in. Nothing is sent until the human taps send, so Inputs: name, message, company |
get_availability | Real open slots from the agency's appointment calendar: 30-minute meetings on weekdays, booked in the agency's timezone. Returns each slot's start, end and a readable label. A slot is not a booking — hand the human a link from create_bookin Inputs: daysAhead, durationMinutes |
get_catalog_changes | What each weekly catalogue sync changed: publications added and removed, and price changes, newest first. Filter by a date (only newer syncs), a maximum price, one or more categories, a minimum Domain Authority, additions only, or price dro Inputs: since, maxPrice, category, categories, minDomainAuthority, newOnly |
get_channel | The full detail for one paid media product: what it is, where the ads run, the creative formats, the targeting that can be layered on, and caveats — the limits and prerequisites a buyer should know before submitting a brief. Also lists the Inputs: slug |
get_client_order | For a paid order: each publication on it, with its own stage, what we need next, the content the client sent, the latest outline or draft we wrote, and a sample of the publication's writing. Each publication is worked through separately. Ne Inputs: orderLink |
get_placement | Full detail for one publication by its id (the slug from search_placements), including price, price with the 3.5% checkout processing fee, authority scores, estimated monthly traffic (monthlyTraffic), turnaround, disclosure policy, link typ Inputs: id |
list_capabilities | The outcomes we can deliver — geo-fencing, website retargeting, visit tracking, identity resolution and so on — each in plain language with the products that provide it. Use this to translate what a client wants into what to ask for. |
list_categories | Every category, genre and restricted niche in the network, each with how many publications carry it. Use them to pick valid values for search_placements' categories, genres and niche filters. |
list_channels | Every paid media product we run — Meta, Connected TV, geo-targeted mobile, search, audio, out-of-home and the rest — each with a one or two sentence description. The slugs are what submit_campaign_brief takes as channels. Use get_channel fo |
plan_placements | Recommend a set of publications for a goal, audience and budget — already quoted, total inside budget including the 3.5% processing fee. Use this when a buyer says what they want to achieve and what they can spend, rather than naming public Inputs: goal, audience, budget, count, minDomainAuthority, minMonthlyTraffic |
quick_visibility_check | Five basics of whether AI systems can read a website, checked instantly from its public pages: AI crawlers allowed in robots.txt, an llms.txt, Organization and FAQ structured data, and a title and description. Free, no score, nothing stored Inputs: website |
quote_placements | Price a set of placements exactly as the store's checkout would, including the 3.5% processing fee. Use this to give a client a total before creating an order. Quoting does not reserve anything. Placements that are not available are refused Inputs: items |
request_audit | Request a free audit of whether AI systems — ChatGPT, Perplexity, Google's AI Overviews and crawling agents — can reach, read and quote a website. Scored out of 100 across crawler access, structured data, answer readiness, agent files, off- Inputs: contact, website, track, concerns, notes, referredBy |
review_content | The client's decision on one publication's latest outline or draft from get_client_order. Approving an outline starts the draft; approving the draft sends it to our editors for a final read, and cannot be undone. Show the client the full te Inputs: orderLink, publication, piece, action, feedback |
search_placements | Search the publisher network for editorial placements. Filter by price, Domain Authority, Domain Rating, monthly traffic, category, genre, region, turnaround, link type (dofollow or nofollow), whether the outlet is Google-indexed or LLM-rea Inputs: query, categories, genres, niche, minPrice, maxPrice |
submit_article_draft | File the client's article draft against a paid order. The order id plus the billing email on the order prove ownership — a wrong pairing reads exactly like a missing order. The order must be paid: an unpaid order has bought nothing yet. The Inputs: orderId, email, draft, title, authorName, referredBy |
submit_campaign_brief | Submit a paid media brief for a client and have the team come back with a quote — impressions, placements and a recommendation. Use this for advertising campaigns (display, video, Connected TV, social, search, audio, out-of-home), which are Inputs: contact, capabilities, channels, goal, geography, budget |
submit_content | What one publication's article should be built from, the same as the form on the client's order page. Each publication on an order needs its own. Needs at least who they are and what the article should say, or a draft of their own. Only whi Inputs: orderLink, publication, about, angle, facts, links |
Every block below points at https://theprofound.agency/api/mcp/. Pick your client and copy.
claude mcp add --transport http the-profound-agency https://theprofound.agency/api/mcp/
{
"mcpServers": {
"the-profound-agency": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://theprofound.agency/api/mcp/"]
}
}
}{
"mcpServers": {
"the-profound-agency": {
"url": "https://theprofound.agency/api/mcp/"
}
}
}{
"servers": {
"the-profound-agency": {
"type": "http",
"url": "https://theprofound.agency/api/mcp/"
}
}
}{
"context_servers": {
"the-profound-agency": {
"url": "https://theprofound.agency/api/mcp/"
}
}
}{
"mcpServers": {
"the-profound-agency": {
"serverUrl": "https://theprofound.agency/api/mcp/"
}
}
}{
"mcpServers": {
"the-profound-agency": {
"url": "https://theprofound.agency/api/mcp/"
}
}
}name: The Profound Agency
version: 0.0.1
schema: v1
mcpServers:
- name: The Profound Agency
type: streamable-http
url: https://theprofound.agency/api/mcp/{
"mcpServers": {
"the-profound-agency": {
"httpUrl": "https://theprofound.agency/api/mcp/"
}
}
}{
"mcpServers": {
"the-profound-agency": {
"type": "http",
"url": "https://theprofound.agency/api/mcp/"
}
}
}{
"mcpServers": {
"the-profound-agency": {
"url": "https://theprofound.agency/api/mcp/"
}
}
}goose://extension?url=https%3A%2F%2Ftheprofound.agency%2Fapi%2Fmcp%2F&type=streamable_http&id=the-profound-agency&name=The%20Profound%20Agency
It answered our last check on 17 November 2026 in 1190 ms. Over 4 checks since 2 October 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
24, as returned by the server's own tools/list on 20 November 2026: ask, can_i_advertise, check_order_status, compare_placements, create_booking_link, create_order, create_text_link, get_availability, and 16 more.
It answered our last check on 17 November 2026 in 1190 ms. Over 4 checks since 2 October 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://theprofound.agency/api/mcp/. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.jfromtheroc. Endpoint host: theprofound.agency. ARD identifier: urn:air:io.github.jfromtheroc:mcp:the-profound-agency.
First indexed 2 October 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.