
Break3 MCP server
Which MCP servers are Break3'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 2026-11-13
- Addresshttps://break3.app/mcp/opennot in the official registry: answered when asked
No entry in the official MCP registry names this server. It answered on break3.app when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.
- Stateanswerschecked 2026-11-13
- Tools2
- Server calls itselfbreak3-open
- Server version1.1.0
- Protocol version2025-06-18
On 2026-11-13 the server answered initialize and tools/list without a sign-in. First answer in 65 ms.
Should an agent connect it
- On Nov 21, 2026 we called its read-only tools following a fixed scenario, and 1 of 1 steps returned what the check expects.
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.
Measured daily
- INITE MCP score100 of 100answers 100 · definitions 100 · context 100 · connects 100
- Checked by calling it1 of 1 steps passedlatest run Nov 21, 2026, read-only calls only
- Answered100% of days9 of 9 daily checks
- Median first answer81 ms
- Space in an agent's context≈ 168 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.
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 →
about_break3described by the serverHow Break3 works: streaks, daily check-ins, steps, portraits, leagues, languages, and how to connect a person's account. Examples: "как работает Break3?", "como funciona o Break3?".
list_habit_typesverified Nov 21, 2026The kinds of habit Break3 tracks, quit or build, with their names in English, Russian and Portuguese: the values create_habit takes on the signed-in server. Examples: "какие привычки можно отслеживать?", "quais hábitos posso acompanhar?".
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"open": {
"type": "http",
"url": "https://break3.app/mcp/open"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http break3 https://break3.app/mcp/openclaude.ai, ChatGPT and other clients: add https://break3.app/mcp/open 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.