Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Dynamis buscar doctrina sobre lanzamiento en frío"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Sistema portable de doctrina operativa para infoproductos, construido a partir de 66 fichas de expertos agrupadas en 8 clusters (A, C, D, E, F, G, H, I). Incluye síntesis cross-experto, skills para Cursor, un meta-índice, y un MCP server para usar la doctrina desde cualquier cliente MCP (Cursor, Claude Desktop, Windsurf, Continue, Cline, etc.).
La doctrina de los expertos vive separada del contexto del operador. Cada usuario completa su propio CEREBRO/OPERADOR.md (no se commitea).
El repo es también un paquete MCP ejecutable. Sin publicar a npmjs.com, cualquiera puede usarlo directo desde GitHub con npx.
.cursor/mcp.json{
"mcpServers": {
"dynamis": {
"command": "npx",
"args": ["-y", "github:Santiagociroc11/Dynamis-mcp"]
}
}
}Mismo comando npx -y github:Santiagociroc11/Dynamis-mcp sobre stdio. Al primer arranque, npx clona el repo, ejecuta npm install (que dispara postinstall → npm run build y genera dist/ + data/), y arranca el servidor.
npx falla en tu entorno)En algunos entornos Windows con Node muy nuevo, npx.cmd puede fallar al resolver npx-cli.js. Si npx -y github:... no arranca, usa el bin local directamente:
git clone https://github.com/Santiagociroc11/Dynamis-mcp.git
cd Dynamis-mcp
npm install # instala deps + genera dist/ y data/ via postinstallY en el mcp.json apunta al bin compilado con su path absoluto:
{
"mcpServers": {
"dynamis": {
"command": "node",
"args": ["C:/ruta/absoluta/al/Dynamis-mcp/dist/index.js"]
}
}
}Esta forma evita npx por completo y es 100% reproducible. Para actualizar la doctrina, git pull && npm run build.
URI | Qué devuelve |
| Índice maestro (66 fichas, 16 clusters) |
| Ficha individual de un experto |
| Síntesis cross-experto (A, C, D, E, F, G, H, I) |
| Skill operativo (8 disponibles) |
| 6 tensiones transversales |
buscar_doctrina(query, experto?, cluster?) — busca en fichas y síntesis (insensible a acentos).
validar_atribucion(experto, cluster) — anti-fantasma: verifica EXPERTOS FUENTE antes de citar.
que_skill_aplica(problema) — meta-índice problema → skill + cluster.
auditar_cluster(cluster) — separa ★ consenso de ◇ una voz.
get_benchmark(cluster?, metrica?) — benchmarks, preserva [¿?].
sesgo_cluster(cluster) — % Vinícius + lectura de confianza.
listar_huecos(cluster?) — huecos conocidos + fuente externa asignada.
La referencia completa de tools y resources está en el código (src/index.ts).
{
"mcpServers": {
"dynamis": {
"command": "npx",
"args": ["-y", "github:Santiagociroc11/Dynamis-mcp"],
"env": { "DYNAMIS_PATH": "/ruta/a/data" }
}
}
}DYNAMIS_PATH apunta a una carpeta con fichas/, sintesis/, skills/ e indice_maestro.md.
Related MCP server: DocSmith MCP Server
CEREBRO/
├── sintetizador.md Plantilla: ficha individual
├── sintetizadorTOTAL.md Plantilla: síntesis cross-experto
├── TRANSFERENCIA.md Cómo transferir / instalar
├── OPERADOR.template.md Plantilla de contexto personal (cada uno copia y completa)
├── empaquetar-dynamis.ps1 Script para regenerar zip one-shot
└── DYNAMIS/
├── indice_maestro.md Mapa de fichas y clusters
├── fichas/ Doctrina cruda por experto (66 fichas)
└── sintesis/ Modelos integrados por cluster (A, C, D, E, F, G, H, I)
.cursor/skills/
├── dynamis-index/ Meta-índice: qué skill invocar
├── estructura-lanzamiento-cierre/ Cluster A
├── whatsapp-grupos-cierre/ Cluster C
├── oferta-anclaje-backend/ Cluster F
├── equipo-comercial-closers/ Cluster E
├── ecosistema-escalera-valor/ Cluster G
├── agencia-equipos-contratacion/ Cluster H
└── operacion-agil-delegacion/ Cluster ID (tráfico/creativos) no tiene skill propio: es insumo para los skills de ads del operador.
Clonar o descargar este repo.
Copiar CEREBRO/ al nuevo workspace.
Copiar .cursor/skills/ (o las subcarpetas que apliquen).
Copiar CEREBRO/OPERADOR.template.md → CEREBRO/OPERADOR.md y completar el perfil (ticket, canal, mercado, defaults, doctrina propia).
En el chat de Cursor, invocar @dynamis-index cuando no sepas qué skill usar.
Opcional — agregar a las reglas del proyecto: "Si existe CEREBRO/OPERADOR.md, leelo antes de aplicar skills DYNAMIS."
¿No sé por dónde empezar? → @dynamis-index
Armar un launch → @estructura-lanzamiento-cierre
Cerrar por WhatsApp → @whatsapp-grupos-cierre
Diseñar oferta / anclaje → @oferta-anclaje-backend
Montar closers / HT → @equipo-comercial-closers
Pasar de picos a recurrencia → @ecosistema-escalera-valor
Estructurar agencia → @agencia-equipos-contratacion
Delegar / procesos → @operacion-agil-delegacion★ = consenso real (2+ voces independientes) → doctrina confiable.
◇ = una voz → hipótesis fuerte, no ley.
[¿?] nunca se elimina de benchmarks (verificar antes de proyectar caja).
Anti-fantasma: no citar expertos fuera de EXPERTOS FUENTE de cada síntesis.
Sesgo Vinícius calculado por cluster (ver dynamis-index).
Tensiones cierran con CONDICIÓN DE DECISIÓN; el default personal va en OPERADOR.md.
Tras cada launch (15 min), agregar en OPERADOR.md o en el skill usado:
- [fecha] Decisión aplicada: ...
Benchmark DYNAMIS: ...
Número real: ...
Veredicto: confirma / contradice / matiza. Ajuste: ...A los 3-4 launches, los números del operador pesan más que los de la mentoría.
Fichas — por cada transcripción, correr sintetizador.md → CEREBRO/DYNAMIS/fichas/moduloN/.
Índice maestro — agrupar fichas en clusters → indice_maestro.md.
Síntesis — por cluster, correr sintetizadorTOTAL.md → sintesis/.
Skills — convertir cada síntesis: ARSENAL OPERATIVO + MAPA DE TENSIONES → cuerpo del skill; CONDICIÓN DE DECISIÓN → lógica.
Meta-skill — dynamis-index/SKILL.md mapea skills, tensiones transversales y huecos.
Operador — cada usuario completa OPERADOR.md y agrega RESULTADOS PROPIOS tras cada launch.
npm install # instala deps + corre postinstall (build: copy-data + tsc)
npm run build # regenera dist/ y data/ manualmente
npm start # arranca el servidor stdioEstructura del paquete:
package.json bin: dynamis-mcp -> dist/index.js
src/index.ts código fuente del MCP server
scripts/copy-data.mjs copia CEREBRO/DYNAMIS + .cursor/skills -> data/
tsconfig.json
dist/ compilado (generado por build, en .gitignore)
data/ doctrina copiada (generada por build, en .gitignore)Si mejorás la doctrina base (nuevas fichas, síntesis, correcciones de sesgo):
Rama nueva.
Commit con descripción del cambio y la fuente (qué ficha/experto).
PR — respetá las reglas de calidad (★/◇, [¿?], anti-fantasma, sin contexto personal).
No commitear CEREBRO/OPERADOR.md ni datos de launches reales (están en .gitignore).
Devuelve el checklist de auditoria de un cluster separado en consensos reales (★) y voces unicas (◇). Regla DYNAMIS: ante recursos limitados, primero cerrar todos los ★, despues los ◇. Usalo para auditar un lanzamiento/cierre en curso.
| Name | Required | Description | Default |
|---|---|---|---|
| cluster | Yes | Letra de cluster: A, C, D, E, F, G, H, I |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavioral context by stating the DYNAMIS rule for resource prioritization (close ★ first, then ◇) and indicates the tool is used for ongoing processes. However, it does not explicitly state whether the tool is read-only or has side effects, and there are no annotations to compensate. Given the lack of annotations, the description should more clearly disclose safety characteristics.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at three sentences, front-loading the key output (checklist) and rule, then ending with the use case. Every sentence adds value without redundancy, making it efficient and easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-parameter tool with no output schema, the description covers the purpose, an important behavioral rule, and the use case. It does not describe the exact return format beyond the symbols, but the separation into ★ and ◇ gives sufficient insight. Some examples of usage or error conditions could improve completeness, but it is mostly adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers 100% of the parameter (cluster) with a description listing valid letters. The tool description does not add additional semantic meaning beyond what the schema already provides, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns an audit checklist of a cluster, separated into real consensuses (★) and unique voices (◇). This specific verb and resource, combined with the unique output format, effectively distinguishes it from sibling tools like get_benchmark or listar_huecos.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states the tool is for auditing a launch/closure in progress ("Usalo para auditar un lanzamiento/cierre en curso"). While it does not exclude alternatives, this provides clear context for when to use it, which is adequate given the explicit use case.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Busca en las 66 fichas y 8 sintesis de DYNAMIS por palabra clave. Filtra opcionalmente por experto o cluster (letra A-I). Devuelve pasajes relevantes con atribucion.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Palabra o frase a buscar | |
| cluster | No | Letra de cluster: A, C, D, E, F, G, H, I | |
| experto | No | Filtrar por nombre de experto |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It discloses the search scope and return type, but lacks details on permissions, rate limits, or behavior when no results are found. For a read-oriented search tool, it is adequate but minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no wasted words. The first sentence states the core action and scope, the second adds filtering and return type. Front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description says it returns pasajes relevantes con atribucion, but does not specify structure, max results, pagination, or error handling. Given no output schema, this is minimally sufficient for a search tool but lacks depth for complete agent decision-making.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with all three parameters described. The description adds that cluster filtering uses letters A-I, but the schema explicitly lists letters excluding B, so the description is slightly inaccurate. This introduces potential confusion for agents.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches in 66 fichas and 8 sintesis of DYNAMIS by keyword, with optional filters for expert or cluster. It mentions returning relevant passages with attribution, effectively distinguishing it from sibling tools which focus on auditing, benchmarking, gaps, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for keyword searching with optional filters, but does not explicitly state when to use this tool over alternatives or when not to use it. No exclusions or context for when to prefer siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Devuelve los benchmarks de un cluster (o de todos si no se especifica). Preserva los marcadores [¿?] que indican numeros heredados de transcripciones sucias: verificar antes de proyectar caja. Filtra opcionalmente por metrica.
| Name | Required | Description | Default |
|---|---|---|---|
| cluster | No | Letra de cluster: A, C, D, E, F, G, H, I | |
| metrica | No | Palabra clave de metrica (ej. conversion, cpl, roas, show-up) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses that the tool preserves markers indicating dirty transcriptions and advises verification, which is a behavioral trait. However, it does not mention authorization, rate limits, or return format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise: two sentences, 30 words, no redundancy. Front-loaded with the main action and includes a critical warning efficiently.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description hints at return contents (benchmarks with possible markers) but does not explain structure or values. Adequate for a simple retrieval tool but could be more comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with parameter descriptions. The description adds value by clarifying default behavior for cluster ('o de todos si no se especifica'), but the filtering by metric is already in the schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it returns benchmarks of a cluster or all clusters if unspecified, with optional metric filtering. It specifies the resource and action but does not explicitly differentiate from siblings, though the action is distinct.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Describes when to use (getting benchmarks, specifying cluster or all) and optional filtering, but no explicit guidance on when not to use or alternatives. The warning about dirty markers provides some usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Lista los huecos conocidos de un cluster (o de todos): lo que DYNAMIS NO cubre y la fuente externa asignada. Usalo antes de buscar doctrina fuera del corpus y para saber qué documentar en OPERADOR.md.
| Name | Required | Description | Default |
|---|---|---|---|
| cluster | No | Letra de cluster: A, C, D, E, F, G, H, I |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It implies a read operation (listing gaps) but does not confirm side effects or permissions. The description does not contradict any annotations (none exist).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences with no redundancy. Every part earns its place: purpose and usage guidance are front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple parameter (one optional string) and no output schema, the description is complete: it explains what the tool does, when to use it, and the parameter behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 100% coverage for the single 'cluster' parameter with a description. The tool description adds value by clarifying that omitting the parameter lists all clusters ('o de todos'), which is not in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it lists known gaps of a cluster (or all), specifying 'lo que DYNAMIS NO cubre y la fuente externa asignada'. This is a specific verb and resource, and it distinguishes from siblings like buscar_doctrina (search doctrine).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says 'Usalo antes de buscar doctrina fuera del corpus y para saber qué documentar en OPERADOR.md', providing clear context for when to use it. It does not mention when not to use or alternatives, but the guidance is useful.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Meta-indice: dado un problema, devuelve que skill DYNAMIS invocar y el cluster fuente. Usalo PRIMERO cuando no sepas que skill aplica.
| Name | Required | Description | Default |
|---|---|---|---|
| problema | Yes | Descripcion del problema u objetivo |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears the full burden. It discloses that the tool returns a skill and cluster, but does not mention whether it has side effects, modifies state, or requires specific permissions. It implies a read-only operation but lacks explicit behavioral details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description consists of two concise sentences. The first states the core purpose, and the second provides usage guidance with emphasis ('PRIMERO'). No superfluous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (single parameter, no output schema), the description is complete enough. It explains what the tool does and when to use it. It could mention the output format more explicitly, but the statement that it returns 'que skill DYNAMIS invocar y el cluster fuente' is sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'problema' is described in the schema with 'Descripcion del problema u objetivo'. The tool description adds that it uses the problem to return a skill and cluster, but does not add further semantics beyond the schema. Since schema coverage is 100%, a baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool returns which DYNAMIS skill to invoke and the source cluster given a problem. It uses a specific verb 'devuelve' (returns) and distinguishes itself from siblings by being a meta-index tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says 'Usalo PRIMERO cuando no sepas que skill aplica' (Use it FIRST when you don't know which skill applies), providing clear when-to-use guidance. It does not explicitly list alternatives but implies its role as a router.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Devuelve el sesgo Vinícius del cluster (porcentaje de fichas suyas) y la lectura de confianza. Regla: cuanto mas alto el %, mas tratar los ★ como hipotesis fuerte de un arquitecto y menos como verdad del campo. En G/H/I contrastar con fuentes externas antes de adoptar como ley.
| Name | Required | Description | Default |
|---|---|---|---|
| cluster | Yes | Letra de cluster: A, C, D, E, F, G, H, I |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries full burden. It discloses the tool returns two values (bias and confidence) and adds behavioral context via the interpretation rule. No destructive actions mentioned, but the tool appears read-only.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (two sentences plus a rule) and front-loaded with the main action. Every sentence adds value, though the rule could be integrated more efficiently.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description explains return values (bias percentage and confidence reading) and provides context for interpretation. Sufficient for the tool's simple use case.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already describes the single parameter 'cluster' with allowed values. The description adds no additional meaning about the parameter beyond its return values, so baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns the 'Vinícius bias' (percentage of its tokens) and confidence reading, with specific verbs and resource. It distinguishes from siblings like 'auditar_cluster' by focusing on bias metric.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides a rule for interpreting high percentages (treat as hypothesis) and specific guidance for clusters G/H/I (cross-check). However, it does not explicitly state when to use this tool vs alternatives, leaving usage context implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Anti-fantasma: verifica si un experto esta en EXPERTOS FUENTE de un cluster antes de citarlo. Devuelve valido/no valido + la lista de expertos fuente del cluster.
| Name | Required | Description | Default |
|---|---|---|---|
| cluster | Yes | Letra de cluster: A, C, D, E, F, G, H, I | |
| experto | Yes | Nombre del experto a validar |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It states the output (valid/invalid + source list) and context, but does not disclose read-only nature, authorization needs, or side effects. It is adequate but not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with a key front-loaded term ('Anti-fantasma'). Every word adds value; no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple verification tool with two parameters and no output schema, the description fully explains input purpose and output format. It is complete for the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear descriptions for both parameters. The description adds context about the 'anti-fantasma' purpose and the source experts check, providing meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool verifies if an expert is in the source experts of a cluster before citing, and returns validity plus the source list. This distinguishes it from sibling tools like auditar_cluster or buscar_doctrina.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage before citing an expert ('anti-fantasma'), providing clear context. However, it does not explicitly state when not to use it or mention alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0auditar_clusterbuscar_doctrinaget_benchmarklistar_huecosque_skill_aplicasesgo_clustervalidar_atribucionScored across 7 tools
Each tool targets a distinct aspect of the DYNAMIS framework: auditing, searching doctrine, benchmarks, gaps, skill selection, bias, and attribution. No two tools have overlapping purposes, making selection unambiguous.
Most tools use Spanish snake_case with a verb_noun pattern (e.g., auditar_cluster, buscar_doctrina), but 'get_benchmark' mixes English, 'sesgo_cluster' is noun_noun, and 'que_skill_aplica' is a question phrase. The pattern is inconsistent across the set.
With 7 tools, the server covers a well-scoped domain without being too sparse or overloaded. Each tool addresses a necessary function for interacting with the DYNAMIS knowledge system.
The set provides reasonable coverage for querying and auditing the framework, including gaps and bias. Minor omissions like a tool to list all clusters or expert details exist, but core workflows are supported.
MCP server for skill documentation, generated by doc2mcp.
MCP server for innovationlab documentation, generated by doc2mcp.
Autopilot MCP server for GEO analyses, reports, content, audits, memories and agents.
MCP server for the Inistate platform: module discovery, entry management, and activity submission.
