WATR Software Oracle MCP
A remote MCP server providing 152 engineering rules for code quality, Clean Code, SOLID principles, and agent architecture. It allows agents to review code, search practices, and get verdicts with traceable stances (enforce, prefer, context-dependent) to ensure consistent senior-level coding criteria.
Endpoint and access
No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.
https://watr-software-oracle.onrender.com/mcpWhat its tools do
5 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.
Not annotated (5)
Checks and signals
Each line is separate evidence, not a trust score.
- Passed Endpoint answered the live check ·
- Warning Does not report a server version
- Availability 1 of 1 checks passed in 30 days
What you can do with it
- Review code fragments for structural signals and applicable rules
- Search natural language queries to find applicable rules with stances
- Get detailed rule information including principles and refactoring advice
- Judge code with probability per rule (requires token)
Source and maintenance
Protocol and capabilities
- Server
- WATR Software Oracle unreported
- MCP protocol negotiated in check
- 2025-11-25
- Tools
- 5 advertised
- Resources
- 0 advertised
- Resource templates
- 0 advertised
- Prompts
- 0 advertised
{
"tools": {
"listChanged": false
},
"prompts": {
"listChanged": false
},
"resources": {
"subscribe": false,
"listChanged": false
}
}Server-provided instructions
Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.
Tools
5 advertised
get_rule
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.
{
"type": "object",
"title": "get_ruleArguments",
"required": [
"rule_id"
],
"properties": {
"rule_id": {
"type": "string",
"title": "Rule Id"
}
}
}{
"type": "object",
"title": "get_ruleOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
}search_practices
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. Traduce la intención antes de llamar ("catch vacío" -> "empty catch swallowing error"). Devuelve top-k con rule_id y stance; usa get_rule para el texto completo.
{
"type": "object",
"title": "search_practicesArguments",
"required": [
"query"
],
"properties": {
"k": {
"type": "integer",
"title": "K",
"default": 5
},
"query": {
"type": "string",
"title": "Query"
}
}
}{
"type": "object",
"title": "search_practicesOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
}review_code
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 que observa, las reglas aplicables con su stance, las meta-heurísticas que gobiernan el juicio, y el formato de salida obligatorio. El razonamiento y el veredicto son tuyos — la consistencia la pone el corpus.
{
"type": "object",
"title": "review_codeArguments",
"required": [
"code"
],
"properties": {
"code": {
"type": "string",
"title": "Code"
},
"language": {
"type": "string",
"title": "Language",
"default": ""
}
}
}{
"type": "object",
"title": "review_codeOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
}judge_code
Opinión del corpus sobre un fragmento, con una probabilidad por regla. Diferencia con `review_code`: ahí recibes las reglas y juzgas tú, así que dos clientes sobre el mismo diff pueden discrepar. Aquí el corpus se moja: una pregunta por regla en alcance, y el stance decide qué umbral aplica. ⚠️ NO es una compuerta, y no lo cuelgues de un CI. Medido sobre 13 pares reales (26 mediciones, 6 autores, 2018–2026): deja pasar el 38% de las violaciones, y el barrido completo de umbrales no encuentra nada mejor porque el límite es la resolución del instrumento, no dónde se corta. Para lo que sí sirve: ordenar qué mirar primero y decirte con qué regla, que son 11 aciertos de 13 al comparar un antes contra un después. ⚠️ Manda el fragmento a api.typesafe.ai, un tercero. `review_code` no sale de esta máquina: si el código no puede salir, usa ése. ⚠️ PIDE TOKEN en el servidor remoto, porque es el único tool que cuesta dinero y lo paga quien lo hospeda. Va en la cabecera `Authorization: Bearer <token>` de la conexión MCP. Sin él, este tool contesta diciéndolo y te manda a `review_code`, que hace el mismo trabajo gratis. Esto se dice aquí a propósito: un cliente MCP lee esta descripción antes de llamar, así que es donde se entera sin tener que fallar primero.
{
"type": "object",
"title": "judge_codeArguments",
"required": [
"code"
],
"properties": {
"code": {
"type": "string",
"title": "Code"
},
"language": {
"type": "string",
"title": "Language",
"default": ""
}
}
}{
"type": "object",
"title": "judge_codeOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
}list_domains
Mapa del corpus: dominios, temas y los rule_id de cada uno, con su stance.
{
"type": "object",
"title": "list_domainsArguments",
"properties": {}
}{
"type": "object",
"title": "list_domainsOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
}Prompts
0 advertised
Resources
0 advertised
90-day uptime
A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.
- 2026-11-07: 1 of 1 checks answered
30-day availability
Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.
- Successful checks
- 1 of 1 (100%)
- Average latency
- 1064 ms
- 95th percentile latency
- 1064 ms
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · probe · passed · 1064 ms · metadata changed · 5 tool(s), 0 resource(s), 0 resource template(s), 0 prompt(s); warnings: Does not report a server version
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
claude mcp add --transport http watr-software-oracle-mcp https://watr-software-oracle.onrender.com/mcpCodex
codex mcp add watr-software-oracle-mcp --url https://watr-software-oracle.onrender.com/mcpCursor
{
"mcpServers": {
"watr-software-oracle-mcp": {
"url": "https://watr-software-oracle.onrender.com/mcp"
}
}
}Cline
{
"mcpServers": {
"watr-software-oracle-mcp": {
"type": "streamableHttp",
"url": "https://watr-software-oracle.onrender.com/mcp",
"disabled": false
}
}
}VS Code
{
"servers": {
"watr-software-oracle-mcp": {
"type": "http",
"url": "https://watr-software-oracle.onrender.com/mcp"
}
}
}Gemini CLI
gemini mcp add --transport http watr-software-oracle-mcp https://watr-software-oracle.onrender.com/mcpClaude Desktop
https://watr-software-oracle.onrender.com/mcpWindsurf
{
"mcpServers": {
"watr-software-oracle-mcp": {
"serverUrl": "https://watr-software-oracle.onrender.com/mcp"
}
}
}Let your agent find its tools
Find servers like WATR Software Oracle MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.