WATR Software Oracle — architecture standard by rule_id is an MCP server published by io.github.edbror, hosted at watr-software-oracle.onrender.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 5 tools, including get_rule, search_practices, review_code, judge_code, list_domains.
152 rules with a stance: enforce blocks the PR, prefer is justified. From Clean Code to agents.
632 connections through 4 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Return one full rule, smell or meta-heuristic by its rule_id. Example rule_ids: CC-FN-01, SOLID-DIP-01, SMELL-14, WATR-MH-02. — Devuelve una regla, smell o meta-heurística completa por su rule_id. Ejemplos de rule_id: CC-FN-01, SOLID-DIP-01, SMELL-14, WATR-MH-02.
| Parameter | Type | Description |
|---|---|---|
| rule_id * | string |
{
"name": "get_rule",
"description": "Return one full rule, smell or meta-heuristic by its rule_id.\n\nExample rule_ids: CC-FN-01, SOLID-DIP-01, SMELL-14, WATR-MH-02.\n\n— Devuelve una regla, smell o meta-heurística completa por su rule_id.\nEjemplos de rule_id: CC-FN-01, SOLID-DIP-01, SMELL-14, WATR-MH-02.\n",
"inputSchema": {
"type": "object",
"title": "get_ruleArguments",
"required": [
"rule_id"
],
"properties": {
"rule_id": {
"type": "string",
"title": "Rule Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "get_ruleOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Find the WATR rules that apply to a question or a snippet. The query must be **in English**: the corpus is in English and the search is lexical, so a query in any other language returns little or nothing. Translate the intent before calling ("catch vacío" -> "empty catch swallowing error"). Returns the top k with rule_id and stance; use get_rule for the full text. — Busca las reglas del estándar WATR que aplican a una consulta o a un fragmento. La consulta debe ir EN INGLÉS: el corpus está en inglés y la búsqueda es léxica, así que una consulta en español devuelve poco o nada. Devuelve top-k con rule_id y stance; usa get_rule para el texto completo.
| Parameter | Type | Description |
|---|---|---|
| k | integer | |
| query * | string |
{
"name": "search_practices",
"description": "Find the WATR rules that apply to a question or a snippet.\n\nThe query must be **in English**: the corpus is in English and the search is\nlexical, so a query in any other language returns little or nothing.\nTranslate the intent before calling (\"catch vacío\" -> \"empty catch\nswallowing error\").\n\nReturns the top k with rule_id and stance; use get_rule for the full text.\n\n— Busca las reglas del estándar WATR que aplican a una consulta o a un\nfragmento. La consulta debe ir EN INGLÉS: el corpus está en inglés y la\nbúsqueda es léxica, así que una consulta en español devuelve poco o nada.\nDevuelve top-k con rule_id y stance; usa get_rule para el texto completo.\n",
"inputSchema": {
"type": "object",
"title": "search_practicesArguments",
"required": [
"query"
],
"properties": {
"k": {
"type": "integer",
"title": "K",
"default": 5
},
"query": {
"type": "string",
"title": "Query"
}
}
},
"outputSchema": {
"type": "object",
"title": "search_practicesOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
}
}Return the WATR standard that applies to a snippet, so that YOU judge it. This server does not judge code: it hands back the structural signals it observes, the applicable rules with their stance, the meta-heuristics that govern the call, and the mandatory output format. The reasoning and the verdict are yours; the corpus supplies the consistency. Nothing leaves this server. Prefer this over judge_code when the code cannot go to a third party. — Devuelve el estándar WATR que aplica a un fragmento, para que TÚ emitas el veredicto. Este servidor no juzga el código: entrega las señales estructurales, las reglas aplicables con su stance y el formato de salida obligatorio. No sale nada de este servidor.
| Parameter | Type | Description |
|---|---|---|
| code * | string | |
| language | string |
{
"name": "review_code",
"description": "Return the WATR standard that applies to a snippet, so that YOU judge it.\n\nThis server does not judge code: it hands back the structural signals it\nobserves, the applicable rules with their stance, the meta-heuristics that\ngovern the call, and the mandatory output format. The reasoning and the\nverdict are yours; the corpus supplies the consistency.\n\nNothing leaves this server. Prefer this over judge_code when the code\ncannot go to a third party.\n\n— Devuelve el estándar WATR que aplica a un fragmento, para que TÚ emitas\nel veredicto. Este servidor no juzga el código: entrega las señales\nestructurales, las reglas aplicables con su stance y el formato de salida\nobligatorio. No sale nada de este servidor.\n",
"inputSchema": {
"type": "object",
"title": "review_codeArguments",
"required": [
"code"
],
"properties": {
"code": {
"type": "string",
"title": "Code"
},
"language": {
"type": "string",
"title": "Language",
"default": ""
}
}
},
"outputSchema": {
"type": "object",
"title": "review_codeOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
}
}The corpus's own opinion on a snippet, with a probability per rule. Difference from `review_code`: there you get the rules and judge yourself, so two clients can disagree on the same diff. Here the corpus commits: one question per rule in scope, and the stance decides which threshold applies. ⚠️ NOT a gate, and do not hang it off a CI. Measured over 13 real pairs (26 measurements, 6 authors, 2018–2026): it lets 38% of violations through, and a full threshold sweep finds nothing better, because the limit is the instrument's resolution and not where you cut. What it is good for: ranking what to look at first and telling you which rule — 11 of 13 right when comparing a before against an after. ⚠️ Sends the snippet to api.typesafe.ai, a third party. `review_code` never leaves this server: if the code cannot leave, use that one. ⚠️ REQUIRES A TOKEN on the remote server, because it is the only tool that costs money and whoever hosts it pays. It goes in the MCP connection's `Authorization: Bearer <token>` header. Without it this tool says so and points you at `review_code`, which does the same work for free. This is stated here on purpose: an MCP client reads this description before calling, so it is where you find out without having to fail first. — Opinión del corpus sobre un fragmento, con una probabilidad por regla. NO es compuerta: deja pasar el 38% de las violaciones, medido sobre 13 pares reales. Manda el fragmento a api.typesafe.ai, un tercero, y PIDE TOKEN en la cabecera `Authorization: Bearer`. Si el código no puede salir de la máquina, o no tienes token, usa `review_code`.
| Parameter | Type | Description |
|---|---|---|
| code * | string | |
| language | string |
{
"name": "judge_code",
"description": "The corpus's own opinion on a snippet, with a probability per rule.\n\nDifference from `review_code`: there you get the rules and judge yourself,\nso two clients can disagree on the same diff. Here the corpus commits: one\nquestion per rule in scope, and the stance decides which threshold applies.\n\n⚠️ NOT a gate, and do not hang it off a CI. Measured over 13 real pairs\n(26 measurements, 6 authors, 2018–2026): it lets 38% of violations through,\nand a full threshold sweep finds nothing better, because the limit is the\ninstrument's resolution and not where you cut. What it is good for: ranking\nwhat to look at first and telling you which rule — 11 of 13 right when\ncomparing a before against an after.\n\n⚠️ Sends the snippet to api.typesafe.ai, a third party. `review_code` never\nleaves this server: if the code cannot leave, use that one.\n\n⚠️ REQUIRES A TOKEN on the remote server, because it is the only tool that\ncosts money and whoever hosts it pays. It goes in the MCP connection's\n`Authorization: Bearer <token>` header. Without it this tool says so and\npoints you at `review_code`, which does the same work for free. This is\nstated here on purpose: an MCP client reads this description before\ncalling, so it is where you find out without having to fail first.\n\n— Opinión del corpus sobre un fragmento, con una probabilidad por regla.\nNO es compuerta: deja pasar el 38% de las violaciones, medido sobre 13\npares reales. Manda el fragmento a api.typesafe.ai, un tercero, y PIDE\nTOKEN en la cabecera `Authorization: Bearer`. Si el código no puede salir\nde la máquina, o no tienes token, usa `review_code`.\n",
"inputSchema": {
"type": "object",
"title": "judge_codeArguments",
"required": [
"code"
],
"properties": {
"code": {
"type": "string",
"title": "Code"
},
"language": {
"type": "string",
"title": "Language",
"default": ""
}
}
},
"outputSchema": {
"type": "object",
"title": "judge_codeOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
}
}Map of the corpus: domains, topics and each one's rule_ids, with stance. — Mapa del corpus: dominios, temas y los rule_id de cada uno, con su stance.
No parameters.
{
"name": "list_domains",
"description": "Map of the corpus: domains, topics and each one's rule_ids, with stance.\n\n— Mapa del corpus: dominios, temas y los rule_id de cada uno, con su stance.\n",
"inputSchema": {
"type": "object",
"title": "list_domainsArguments",
"properties": {}
},
"outputSchema": {
"type": "object",
"title": "list_domainsOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
}
}WATR's architecture standard. Always cite the rule_id in every verdict. The stance decides: enforce blocks the PR, prefer is the default and a deviation must be justified, context-dependent requires naming the trade-off. WATR-MH-* meta-heuristics outrank topic rules when they collide. — Estándar de arquitectura de WATR. Cita siempre el rule_id en cada juicio. El stance manda: enforce bloquea el PR, prefer es el default y la desviación se justifica, context-dependent exige nombrar el trade-off. Las meta-heurísticas WATR-MH-* superan a la regla de tema cuando chocan.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.