
CheckedCare MCP server
Which MCP servers are CheckedCare'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 2026-11-03
- Registry namecom.checkedcare/recordsverified in the MCP registry
The registry name sits under checkedcare.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-11-03
- Tools2
- Server calls itselfcheckedcare
- Server version1.0.0
- Protocol version2025-06-18
On 2026-11-03 the server answered initialize and tools/list without a sign-in. First answer in 163 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 1 of the 7 days it takes to judge reliability.
Once connected
- For "look up whether a daycare holds a current license", the likely first call is find_facility.
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: 1 so far
- Answeredmeasuring1 of the 7 daily checks it takes to print a share
- Median first answer402 ms
- Space in an agent's context≈ 524 tokensthe definitions of all its tools (2), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 2 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- can do · look up whether a daycare holds a current license
- not sure · review a daycare's past inspection findings and cited violations
- not sure · confirm a record with the state licensing agency
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 →
find_facilityUse this when the user names a child care center, preschool or family child care home (by name, license number, or name and city) in a covered US state and wants its official state licensing or inspection record. Returns up to 10 matching…
get_facility_recordUse this when one specific facility is identified (a record_key slug from find_facility, or a license number the user gave) and the user wants its license status, published inspection counts or the agency's inspection findings. Returns…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"records": {
"type": "http",
"url": "https://checkedcare.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http checkedcare https://checkedcare.com/mcpclaude.ai, ChatGPT and other clients: add https://checkedcare.com/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.