
Dekadans MCP server
Which MCP servers are Dekadans's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-28
- Registry namenet.dekadans/asoverified in the MCP registry
The registry name sits under dekadans.net. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-28
- Tools13
- Server calls itselfaso-saas
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 539 ms.
- Its tools do every use case we checked: Track keyword rankings across many App Store storefronts daily; Find new keywords through suggestions and competitor rankings.
Once connected
- For "Track keyword rankings across many App Store storefronts daily", the likely first call is add_app.
- For "Find new keywords through suggestions and competitor rankings", the likely first call is get_keyword_suggestions.
- add_app, add_keywords change data without a sign-in: anyone with the address can call them.
- Parameters are untyped or undescribed in 9 of 13 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP score77 of 100answers 100 · does the job 100 · definitions 85 · context 100 · connects 100 · lowered by the warning signs below
- What an agent can do with it2 of 2 use cases
- Answered100% of days7 of 7 daily checks
- Median first answer511 ms
- Space in an agent's context≈ 1,740 tokensthe definitions of all its tools (13), which an agent carries on every turn
- Tool definitionsB · 85 of 100
- Typed results0 of 13 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 9 of 13
- Not saying whether it only reads or can destroy: 3 of 13
What an agent can do with it
- can do · Track keyword rankings across many App Store storefronts daily
- can do · Find new keywords through suggestions and competitor rankings
- not sure · Ask an AI assistant which tracked keywords dropped
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
- Tools that change data, on a server that answers without a sign-in: add_app, add_keywords
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
list_appsTracked apps of the user.
add_appTrack an app by App Store ID; its name is looked up automatically. Omit appStoreId (and pass name) for a temporary app. Free plan: 1 app.
add_keywordsTrack up to 100 keywords for an app in a store and measure rank, popularity and difficulty. Plan limit on total tracked keywords (free: 10); a batch over the limit is rejected entirely.
refresh_app_keywordsMeasure all tracked keywords of an app now and append to history.
get_app_keywordsTracked keywords of an app with latest metrics.
get_keyword_historyDaily rank, popularity and difficulty history of one tracked keyword (keywordId from get_app_keywords), oldest first; days without a measurement are omitted. Free plan: last 7 days.
get_usageCurrent plan, tracked apps, keywords and research calls in the current quota period (free: month, pro: day). A null limit means unlimited.
search_app_storeLive App Store search for a keyword. Returns ranked apps and difficulty; with appStoreId also that app's ranking (null = not in the returned results). Counts toward the research quota.
get_keyword_popularityPopularity scores for up to 100 keywords in a store, without tracking them. Counts toward the research quota.
get_keyword_suggestionsKeyword ideas for an App Store app with popularity and difficulty for the selected platform. Counts toward the research quota.
get_most_searched_keywordsOne page of the most searched keywords in a store, optionally for an App Store category id (e.g. 6013). Check `month`: data can be from an earlier month. Counts toward the research quota.
get_competitor_keywordsDerives 1–3 word candidates from the top 10 competitors ranking for a keyword and returns those with popularity > 5, highest first. Pass your appStoreId to exclude your own app. Counts toward the research quota.
get_app_detailsApp Store details (developer, rating, price, description, screenshots) for up to 50 App Store IDs. IDs not available in the store are omitted. Counts toward the research quota.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"aso": {
"type": "http",
"url": "https://dekadans.net/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http dekadans https://dekadans.net/mcpclaude.ai, ChatGPT and other clients: add https://dekadans.net/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.