Model Context Protocol For teams with AI assistants
Your Rivly data straight into Claude, ChatGPT or your own agent.
One key per project, everything logged. Ask your assistant about the week, about the buying questions you lost, or add a new one. The server stands in Germany.
Summarise the Rivly week for alpenkiste.de in five sentences.
Which buying questions did we lose to Bergwerk Outdoor this week?
Add a buying question about down jackets and put it in the measurement plan.
Week 37, alpenkiste.de: Index 41 out of 100, +4 since week 36. Gemini recommends you, ChatGPT rarely (2 of 12 buying questions). New blind spot “down jacket under 300 euros”. Bergwerk Outdoor is running 30 active ads, two of them winning ads. Three recommendations open, 14 points.
Demo example alpenkiste.de, fictional brands
The tools
Writing tools work only with a key set to “read and write”. Plan limits apply to agents as well.
-
get_overviewread Rivly Index, channel values and the “In short” of the current week -
get_ai_answersread AI answers word for word per buying question and system, with sources -
get_rankingsread Google positions, Google AI Overview and search volume per term -
get_competitorsread Competitors with values from all four channels -
get_recommendationsread Open recommendations with steps, points and status -
get_coreread Profile, offer, search queries with volume, buying questions and competitors with the reason they were added, from the core of the project -
get_mapread Market map of the plan: fields with status, demand, leader and own page, plus the measures with their id -
get_site_auditread Website check: technology, sitemap, llms.txt, access for AI providers and page potential -
get_page_briefread Page brief for a measure or a field: heading, sections, customer questions, schema and llms.txt line -
get_llms_txtread Draft of the llms.txt with the pages of the core, plus the lines for pages that are not online yet -
get_structureread Structure of the website against demand: demand without a page, pages not on place 1 and topics without demand -
get_live_check_historyread History of the AI Live Check: questions with the answers of ChatGPT and Gemini, source app or MCP, rest of the weekly quota -
get_adsread Ads channel: active ads of the brand and its competitors from Meta and Google, with themes and winners -
get_pressread Press channel: editorial articles of the last 30 days, share of coverage and media that name only competitors -
get_backlinksread Backlinks in the Website Check: linking domains against the competitors, strong links, gaps and missing directories, collected monthly -
get_business_profileread Google Business in the Website Check: own listings checked against the website, place in Google Maps and reviews -
get_historyread History per calendar week: Rivly Index and the channels GEO, SEO, ads and press, plus events such as a new measurement basis -
get_measure_planread Measurement plan: which buying questions and search queries Rivly measures every week, with the last result and free slots in the tariff -
update_recommendationwrite Tick off a step, schedule it or report it as done -
add_promptwrite Add a buying question or a search query to the measurement plan -
check_pagewrite Check one page of the website right away: reachable, sitemap, linking, search query, schema and llms.txt -
mark_action_donewrite Report an active measure as done, the next measurement checks the effect -
ask_live_checkwrite Ask ChatGPT and Gemini one question live, with the same weekly quota as the chat in the app -
promote_live_checkwrite Take a question from the Live Check into the measurement plan as a buying question so it is measured every week -
create_page_briefwrite Have a new page brief written for a measure or a field, with the same monthly quota as the button in the Fahrplan
Connect in three steps
- Create a key in the app and choose the rights (read only, or read and write).
- Paste the snippet into Claude, ChatGPT, Cursor or your own agent.
- Restart the assistant. Done.
{
"mcpServers": {
"rivly": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.rivly.de", "--header", "Authorization: Bearer <YOUR-KEY>"]
}
}
} Settings → Connectors → add “Rivly”
Server URL: https://mcp.rivly.de
Authentication: Bearer <YOUR-KEY> {
"mcpServers": {
"rivly": {
"url": "https://mcp.rivly.de",
"headers": { "Authorization": "Bearer <YOUR-KEY>" }
}
}
} curl -X POST https://mcp.rivly.de \
-H "Authorization: Bearer <YOUR-KEY>" \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' Server URL https://mcp.rivly.de, you create the key in the app. MCP is included in every plan.
Security
Every key belongs to one project and one rights level. Every request is logged with client, tool and time. Revoking a key disconnects all clients immediately. Server and data in Germany.
The tools deliver the data from AI visibility, search visibility, advertising and press. The plans are listed under Pricing, the setup step by step in the documentation.