AI Data Stream MCP server
Which servers in the official MCP registry are AI Data Stream's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-20
- Registry namestream.aidata/site-searchverified in the MCP registry
The registry name sits under aidata.stream. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-20
- Tools4
- Server calls itselfAI Data Stream Site Search
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 88 ms.
- Its tools do none of the product's use cases we checked: find top landing pages from GA4 data; check whether a Google update caused traffic drops.
- Checked on 2 of the 7 days it takes to judge reliability.
Once connected
- Parameters are untyped or undescribed in 1 of 4 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 scoreafter a weeka score needs 7 daily checks: 2 so far
- What an agent can do with it0 of 2 use cases
- Answeredmeasuring2 of the 7 daily checks it takes to print a share
- Median first answer2068 ms
- Space in an agent's context≈ 536 tokensthe definitions of all its tools (4), which an agent carries on every turn
- Tool definitionsA · 96 of 100
- Typed results4 of 4 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 1 of 4
What an agent can do with it
- not sure · ask why website traffic changed
- cannot · find top landing pages from GA4 data
- cannot · check whether a Google update caused traffic drops
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
None of the five warning signs in these definitions.
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 (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). 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 →
search_siteFull-text search across aidata.stream: documentation, blog posts, changelog, pricing, FAQ and the home page. Returns the best-matching sections with a snippet and a URL (with anchor where available). Use get_page to read a whole page…
get_pageFetch the full text of one aidata.stream page as Markdown. Accepts a path ("/pricing/", "/docs/getting-started/") or an absolute aidata.stream URL. Use list_pages or search_site to find URLs.
list_pagesList the pages on aidata.stream with title and description, optionally filtered by section (docs, blog, changelog, core) and language. Good first call to see what documentation exists.
get_pricingCurrent AI Data Stream plans as structured data: monthly and annual prices in USD, GBP and EUR, what each tier includes, trial terms, extra seat cost and sign-up links. AI usage is never billed by AI Data Stream: users bring their own AI…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"site-search": {
"type": "http",
"url": "https://aidata.stream/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http aidata https://aidata.stream/mcpclaude.ai, ChatGPT and other clients: add https://aidata.stream/mcp as a custom connector in the settings.
- stream.aidata/aidataanswers, requires sign-inverified in the MCP registry
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.
Cookies
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.