Un servidor MCP local que permite que varias herramientas de IA compartan el estado estructurado del proyecto — decisiones, tareas, errores — para que se coordinen sin tener que volver a explicar todo.
Claude Code Cursor Codex
│ │ │
│ read/write │ read/write │
└──────────────┼─────────────┘
▼
┌───────────────────────┐
│ samskriti-shared-layer │ (local MCP server, stdio)
└───────────┬───────────┘
▼
┌───────────────────┐
│ SQLite store │ ~/.samskriti/ (100% local)
└───────────────────┘Tomas una decisión con una herramienta de IA, luego cambias a otra y tienes que volver a explicar todo desde cero. Cada asistente arranca sin contexto, sin saber qué se ha decidido, probado o descartado. Este servidor les ofrece un registro estructurado y compartido de tu proyecto para que cualquier herramienta pueda leer lo que las otras han escrito.
Related MCP server: session-coord-mcp
Instala con pipx (recomendado: así el comando samskriti-shared-layer queda en tu PATH para que tus herramientas de IA puedan encontrarlo):
pipx install git+https://github.com/Escalate17/samskriti-shared-layer¿No tienes pipx? Instálalo primero: python3 -m pip install --user pipx && python3 -m pipx ensurepath (y reinicia la terminal).
Para comprobar que la instalación ha funcionado:
samskriti-shared-layer --helpSi ves el texto de ayuda, ya está todo listo para conectarlo.
samskriti-shared-layer setup # Claude Code
samskriti-shared-layer setup --cursor # Cursor
samskriti-shared-layer setup --codex # Codex
samskriti-shared-layer setup --all # all threeEsto escribe el bloque de configuración de MCP en el archivo correspondiente (haciendo antes una copia de seguridad de cualquier configuración existente), para que no tengas que editar el JSON a mano. A continuación, cierra y vuelve a abrir tu herramienta — los servidores MCP solo se cargan al iniciar la herramienta, así que una sesión en curso no lo verá hasta que la reinicies.
Añade el servidor a la configuración MCP de tu herramienta de IA y reiníciala por completo.
Claude Code (~/.claude.json):
{
"mcpServers": {
"samskriti-shared-layer": {
"command": "samskriti-shared-layer",
"args": []
}
}
}Cursor (~/.cursor/mcp.json):
{
"mcpServers": {
"samskriti-shared-layer": {
"command": "samskriti-shared-layer",
"args": []
}
}
}Codex (~/.codex/config.toml):
[mcp_servers.samskriti-shared-layer]
command = "samskriti-shared-layer"
args = []Si tu herramienta no encuentra el comando, es un problema de PATH: ejecuta
which samskriti-shared-layerpara obtener la ruta completa y usa esa ruta como valor decommand.
En Claude Code, escribe /mcp — deberías ver samskriti-shared-layer listado con sus 8 herramientas. (Cursor y Codex tienen indicadores de estado MCP similares en su configuración.)
record_project_entry — almacena una entrada (goal, update, decision, convention, bug, task, rejected_idea).
get_project_state — lee un resumen legible, agrupado por categoría.
search_project_state — búsqueda por palabras clave en las entradas.
update_project_entry — edita el título, el contenido o el estado de una entrada.
list_projects — lista todos los proyectos registrados.
Además, tres atajos — catchup, open y log — para las acciones más comunes. Consulta Comandos auxiliares más abajo.
¿Ya lo tienes instalado? Ejecuta
pipx reinstall samskriti-shared-layerpara incorporar los nuevos comandos. Si instalaste una versión anterior (aparece comosamskriti-shared-layer-localenpipx list), migra una vez:pipx uninstall samskriti-shared-layer-local && pipx install git+https://github.com/Escalate17/samskriti-shared-layer.
/samEscribir "usa el MCP samskriti-shared-layer…" cada vez es tedioso. Tanto Claude Code como
Cursor admiten comandos de barra personalizados: archivos Markdown de prompt que colocas en una carpeta.
No se vinculan directamente a una herramienta, pero inyectan un prompt que le indica al agente que use
este servidor, así que /sam <message> hace lo correcto. (Codex no tiene mecanismo de comando de barra
para MCP; basta con decir "usa samskriti-shared-layer para…" — el agente elige la herramienta.)
Claude Code — guarda slash-commands/claude-code/sam.md en uno de:
~/.claude/commands/sam.md (disponible en todos los proyectos), o
<your-project>/.claude/commands/sam.md (solo en ese proyecto).
Después, en Claude Code: /sam what's open o /sam log we're dropping the Redis cache.
El marcador $ARGUMENTS del archivo recibe todo lo que escribes después de /sam.
Cursor (1.6+) — guarda slash-commands/cursor/sam.md en:
~/.cursor/commands/sam.md (global), o
<your-project>/.cursor/commands/sam.md (solo en ese proyecto).
Luego escribe / en el cuadro de agente de Cursor, elige sam y añade tu mensaje.
Aún no existe una función de cliente que vincule directamente un comando de barra a una llamada MCP: este archivo de comando es el equivalente admitido más cercano, y funciona hoy.
Tres atajos envuelven las acciones más comunes. Nunca los invocas directamente por nombre de herramienta:
se activan con /sam más texto en lenguaje natural, o simplemente preguntando en lenguaje natural.
Quieres… | Herramienta | Qué hace |
Ponerte al día |
| Resumen del proyecto: entradas recientes y cuántas tareas siguen abiertas. |
Ver lo abierto |
| Lista las tareas activas (abiertas), cada una con su ID. |
Registrar una decisión |
| Registra una decisión rápidamente; el título se deduce automáticamente del texto si lo omites. |
Dos formas de invocarlo — ambas funcionan:
Comando de barra /sam (Claude Code / Cursor, una vez añadido el archivo de comando de arriba):
/sam catch me up
/sam what's open
/sam log we're switching local storage to SQLiteEscribes /sam seguido de texto en lenguaje natural. No existe un comando independiente /catchup,
/open o /log — siempre es /sam más lo que quieras.
Lenguaje natural (funciona en cualquier herramienta MCP, incluida Codex):
use samskriti-shared-layer to catch me up
use samskriti-shared-layer to show what's open
use samskriti-shared-layer to log: we're switching local storage to SQLiteEn herramienta A (por ejemplo, Claude Code): "Registra una decisión en el proyecto 'demo': estamos usando SQLite para el almacenamiento local."
En herramienta B (por ejemplo, Cursor): "Obtén el estado del proyecto 'demo'."
La herramienta B lee la decisión que la herramienta A acaba de escribir, sin tener que volver a explicar nada.
100 % local. Sin nube, sin cuenta, tus datos nunca salen de tu máquina. El estado se guarda en una base de datos SQLite en ~/.samskriti/ (puedes cambiarlo con la variable de entorno SAMSKRITI_HOME o SAMSKRITI_PROJECT_DB). Las políticas de datos y privacidad de tu cliente de IA siguen siendo aplicables.
Esta es una de las tres cosas que mantengo bajo el nombre Samskriti, y comparten una premisa: el estado que importa debe calcularse y almacenarse explícitamente, no reconstruirse de una transcripción cada vez.
samskriti — un motor que calcula el estado emocional y relacional de un agente a partir de lo que ha experimentado, de forma determinista, fuera de cualquier modelo de lenguaje. C++ con un SDK de Python. (artículo)
samskriti-luau — el mismo modelo para Roblox, donde los NPCs recuerdan cómo los trató un jugador.
samskriti-shared-layer — este repositorio. La misma idea aplicada a tu proyecto en lugar de a un personaje: las decisiones, las tareas y las ideas descartadas viven en un registro estructurado que cualquier herramienta puede leer, en lugar de volver a deducirse del contexto en cada sesión.
Un asistente de IA que empieza sin contexto sobre tu código, y un personaje de juego que olvida que le robaste la semana pasada, son el mismo fallo. Ambos piden a un modelo que reconstruya un estado que nunca se le dio. Este servidor es la versión poco glamurosa de la solución, y la que uso todos los días.
Fase temprana / en validación. Es un prototipo funcional que se está probando con flujos de trabajo reales. Se esperan errores, imperfecciones y funciones que falten; las incidencias y los comentarios son muy bienvenidos.
MIT — consulta LICENSE.
Returns a concise, readable summary of project state, grouped by category.
| Name | Required | Description | Default |
|---|---|---|---|
| project | Yes | Project name or absolute root path | |
| category | No | Optional specific category to filter by |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It states the output is 'concise, readable summary, grouped by category' but does not disclose read-only nature, performance, or any side effects. Minimal behavioral insight.
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?
Single sentence, no fluff, front-loaded with verb and object. Every word adds value.
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 read tool with full schema parameter coverage and no output schema, the description adequately conveys categorization. However, it does not specify what 'state' includes (e.g., status, metrics), leaving some ambiguity.
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 parameter descriptions. The description adds 'grouped by category' hinting at the category parameter, but this is already implied by the parameter description. Meets baseline.
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 uses a specific verb 'Returns' and resource 'summary of project state' making the purpose clear. It implicitly distinguishes from siblings like list_projects (list only) and search_project_state (search), but does not explicitly differentiate.
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?
No guidance on when to use this tool versus alternatives such as search_project_state or list_projects. The description provides no context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns a list of all known projects tracked by Samskriti V1.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must fully disclose behavior. It only states it returns a list; no mention of pagination, ordering, performance characteristics, or potential large results. This lack of detail can cause agent uncertainty.
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 single sentence with no wasted words. All information is front-loaded and clear.
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 parameters or output schema, the description is minimal. It covers the basic purpose but lacks details on return format, ordering, or any limitations. For a simple listing tool, it is adequate but could be more complete (e.g., 'Returns an array of project objects with id and name').
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?
No parameters exist, and schema coverage is 100%. Baseline score of 4 applies as description adds no parameter info but is not needed. The tool has no parameters to document.
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 a list of all known projects tracked by Samskriti V1, with a specific verb and resource. It distinguishes from siblings like get_project_state (single project) and search_project_state (filtered).
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?
No guidance on when to use this tool versus alternatives like search_project_state for filtered results. The description implies listing all projects but does not explicitly state when to prefer this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Stores a structured project-state entry (goal, update, decision, convention, bug, task, rejected_idea).
| Name | Required | Description | Default |
|---|---|---|---|
| project | Yes | Project name or absolute root path | |
| category | Yes | Category: goal, update, decision, convention, bug, task, rejected_idea | |
| title | Yes | Concise summary title | |
| content | Yes | Detailed description or payload | |
| source_agent | No | Optional name of the agent calling this tool (e.g. 'claude-code') | |
| status | No | Optional status: active, completed, resolved, superseded |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must disclose behavioral traits. It only says 'Stores' without clarifying if entries are appended or overwritten, or if duplicates are allowed.
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?
Single sentence is concise but omits important details. While not verbose, it does not fully earn its place given the missing behavioral and usage 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?
No output schema and description does not mention return value or success/error behavior. Does not explain whether entries are idempotent or require prior project existence.
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 has 100% coverage with descriptions for all parameters. Description adds no extra meaning beyond the schema, such as value formats or constraints.
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?
Description clearly states it stores a structured project-state entry and lists the allowed categories. It distinguishes from siblings like get_project_state (read) and update_project_entry (update).
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?
No guidance on when to use this tool versus update_project_entry or whether the project must already exist. Lacks prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the project state ledger using a simple keyword query.
| Name | Required | Description | Default |
|---|---|---|---|
| project | Yes | Project name or absolute root path | |
| query | Yes | Keywords to match against title/content |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must fully disclose behavioral traits. It only mentions 'simple keyword query' without explaining output format, pagination, case sensitivity, wildcards, or any side effects. This minimal information is insufficient for an agent to understand the tool's behavior beyond the basic intent.
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 a single, concise sentence with no extraneous words. However, it lacks structure such as front-loading key details or breaking down complex information. While efficient, it could be slightly more informative without losing conciseness.
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 absence of an output schema and annotations, the description should explain what the search returns. It does not mention the return format, whether results are filtered or sorted, or any limitations. This leaves a significant gap in context for the agent to correctly invoke and interpret the tool's output.
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 provides full descriptions for both parameters ('project' and 'query'), achieving 100% coverage. The description adds only the qualifier 'simple', which does not significantly enhance meaning beyond the schema. Therefore, it meets the baseline for high schema coverage without adding substantial value.
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 action ('Search'), the resource ('project state ledger'), and the method ('simple keyword query'). It effectively distinguishes this tool from its siblings (get_project_state, list_projects, record_project_entry, update_project_entry) by indicating a different purpose: searching instead of retrieving full state, listing, recording, or updating.
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-based searching but does not explicitly state when to use this tool versus alternatives. No guidance on when not to use it or which sibling might be better suited for specific scenarios is provided, leaving the agent to infer from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Update an existing project entry's title, content, or status.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Unique UUID of the entry to edit | |
| title | No | Optional new title | |
| content | No | Optional new content | |
| status | No | Optional new status (active, completed, resolved, superseded) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as permissions, idempotency, side effects, or error handling. For a mutation tool, this is a significant gap.
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 a single sentence of 10 words, front-loaded with the action and resource, with no extraneous information. Every word earns its place.
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 update tool with no output schema, the description covers the what and the modifiable fields. However, it lacks information on return values, error conditions, or idempotency, which would be helpful for an AI agent.
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 description adds value by listing the allowed status values in parentheses, which is not fully captured in the schema's description for the 'status' parameter. Schema coverage is 100%, so baseline is 3; the extra enum detail raises it to 4.
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 uses the specific verb 'Update' with the resource 'project entry' and lists the fields that can be modified (title, content, status). It clearly distinguishes from sibling tools like 'record_project_entry' (create) and 'get_project_state' (read).
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 implicitly conveys usage: modify an existing entry. However, it does not explicitly state when not to use it (e.g., for creating new entries) or provide alternatives. Despite this, the context is clear given the sibling tool names.
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.
v0.1.0get_project_statelist_projectsrecord_project_entrysearch_project_stateupdate_project_entryScored across 5 tools
Each tool has a distinct purpose: summarizing state, listing projects, recording entries, searching, and updating. No overlapping functionality.
All tool names follow a consistent verb_noun pattern (e.g., get_project_state, record_project_entry), ensuring predictability.
With 5 tools, the server covers essential operations without being overwhelming or insufficient for project state management.
Covers core operations (list, get, record, search, update) but lacks explicit project creation and deletion, which may be minor gaps.
Project management shared by people and AI agents, with persistent project state through MCP.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Hosted MCP server and Agent Skills for specs, engineering threads, and project memory.
