
Get found MCP server
Which MCP servers are Get found'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 2026-11-02
- Registry nameio.spotby/registryverified in the MCP registry
The registry name sits under spotby.io. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-11-02
- Tools3
- Server calls itselfspotby-registry
- Server version0.1.0-beta
- Protocol version2025-03-26
On 2026-11-02 the server answered initialize and tools/list without a sign-in. First answer in 644 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 2 of the 7 days it takes to judge reliability.
Once connected
- Parameters are untyped or undescribed in 2 of 3 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
- Answeredmeasuring2 of the 7 daily checks it takes to print a share
- Median first answer702 ms
- Space in an agent's context≈ 577 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsC · 72 of 100
- Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 2 of 3
- Not saying whether it only reads or can destroy: 3 of 3
What an agent can do with it
- not sure · keep opening hours and prices current for AI assistants
- not sure · see which AI agents read the business profile and when
- cannot · get alerted when an assistant first reads the profile
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 (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 →
search_businessesSearch verified businesses in the Spotby registry by free text, city and/or category. Returns compact results; use get_business for full details.
get_businessFull profile of one business: identity, description, services with prices, weekly hours (all time ranges), contacts, photos with AI descriptions, FAQs, synced products, declared freshness.
get_changesBusinesses whose data changed since a given moment — the freshness feed. Use it to stay in sync without re-crawling.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"registry": {
"type": "http",
"url": "https://mcp.spotby.io/"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http spotby https://mcp.spotby.io/claude.ai, ChatGPT and other clients: add https://mcp.spotby.io/ 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.