Skip to main content
Glama
deenesjakoruzh
baalimago

slivingdoc

by baalimago
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Go
Hybrid

Cobertura de pruebas: 83.7% 😍👌

slivingdoc banner

Características

  • Semántica tipo Git: slivingdoc usa terminología que todos (y los agentes) conocemos, diseñada para facilitar su uso

  • Resolución automática de conflictos: haz commit sin miedo; confía en que todos los conflictos deben resolverse antes de ser aceptados

  • Procesamiento de alta velocidad: la solución es bastante simple conceptualmente, lo que permite una escala y paralelismo muy altos

  • Plug-and-play: configura el bucket, apunta a él y ¡empieza a sincronizar notas!

docs/slivingdoc-v1.md es el contrato completo aceptado que respalda estas garantías.

Related MCP server: Cellar

Primeros pasos

Agrégalo a tu entorno de agente:

{
  "mcpServers": {
    "slivingdoc": {
      "command": "npx",
      "args": [
        "-y",
        "slivingdoc",
        "serve",
        "--bucket",
        "my-notes",
        "--workspace-root",
        "/srv/notes"
      ],
      "env": {
        "AWS_ACCESS_KEY_ID": "<your-access-key-id>",
        "AWS_SECRET_ACCESS_KEY": "<your-secret-access-key>",
        "AWS_REGION": "us-east-1"
      }
    }
  }
}

El bucket debe existir, y las credenciales provienen de la cadena normal de AWS. ¿Aún no tienes una cuenta S3? examples/seaweedfs/ ejecuta un contenedor local de SeaweedFS con un tutorial paso a paso. También puedes descargar un binario nativo directamente desde el lanzamiento de GitHub (slivingdoc-v<semver>-<os>-<arch>) y ejecutarlo directamente.

Plataformas compatibles: Linux (amd64, ARMv7 de 32 bits, arm64), macOS (amd64, arm64) y Windows (amd64). El artefacto ARM de Linux de 32 bits es compatible con Raspberry Pi OS armhf.

Cómo funciona

El servidor expone dos herramientas MCP sobre stdio:

Herramienta

Entradas

Resultado en éxito

notes_pull

path

OK

notes_commit

path, message

OK

notes_pull escribe el cuaderno actual en tu directorio. notes_commit publica tus cambios e incorpora cambios concurrentes no conflictivos. Entre llamadas no hay ningún protocolo — los agentes editan los archivos con las herramientas que ya tienen, y los humanos pueden escribir en el mismo directorio con cualquier editor. El próximo commit también lleva sus cambios.

Los humanos también pueden ejecutar ambas operaciones directamente, sin un host MCP. Una ruta relativa se resuelve respecto al directorio de trabajo:

slivingdoc pull notes
# edit UTF-8 text files under notes/
slivingdoc commit notes -m "meeting summary"

El éxito imprime el informe de resultado unificado: el estado OK, la generación remota aceptada, los recuentos de inserciones y eliminaciones por archivo, y un resumen total. Un error de dominio sale con código distinto de cero e imprime un informe sincero: la categoría del error, el veredicto de reintentable, y cada archivo conflictivo con sus rangos de línea. El color aparece solo en una terminal real y se deshabilita con cualquier valor no vacío de NO_COLOR.

La parte de git

Dejar que todos los agentes escriban a la vez funcionaría, pero se verían superados por condiciones de carrera. Por lo tanto, slivingdoc tiene git integrado mediante libgit2 que efectivamente hace:

  1. git pull

  2. (posible resolución de conflictos local)

  3. git add .

  4. git commit -m "<mensaje del agente>"

  5. git push

  6. (posible resolución de conflictos local)

Todas estas operaciones de git se manejan localmente dentro de un espejo privado del directorio de notas, dejando una secuencia git "simplificada". Esto funciona gracias a dos compromisos: primero, el directorio local de notas es propenso a cambios en notes_pull, la precedencia la tiene el estado remoto, dejando marcadores de conflicto. Segundo, el sistema solo funciona para texto (UTF-8 limpio).

Configuración

serve, pull y commit leen las mismas banderas y variables de entorno. --bucket es obligatorio. Las banderas más comunes:

Banderas

Entorno

Valor por defecto

--bucket

SLIVINGDOC_BUCKET

— (obligatorio)

--workspace-root

SLIVINGDOC_WORKSPACE_ROOT

directorio de trabajo inicial

--endpoint

AWS_ENDPOINT_URL_S3

resolución de AWS

--region

AWS_REGION

us-east-1

slivingdoc serve -h imprime la referencia completa, y docs/running.md cubre todo lo que un operador necesita: todas las banderas, los permisos exactos de S3, el registro (LOG_LEVEL en stderr), las reglas del cuaderno, la recuperación de conflictos y la retención de puntos de control. El módulo de Terraform en terraform/ aprovisiona un bucket y un usuario IAM con privilegios mínimos para un cuaderno.

Desarrollo

  • AGENTS.md — la guía para desarrolladores y agentes: mapa de paquetes, flujos de operación, convenciones y las puertas de control de calidad.

  • docs/slivingdoc-v1.md — el contrato de arquitectura aceptado.

  • docs/build.md — la compilación nativa, desde la fuente de libgit2 fijada hasta la inspección de dependencias.

  • docs/testing.md — los comandos de prueba, las capas de prueba y la regla de no usar AWS en vivo.

  • docs/releasing.md — artefactos de lanzamiento, publicación confiable de npm y make release.

make qa #lint plus the full Go and npm test suites

Licencia

MIT — consulta LICENSE. Los avisos de terceros para libgit2 vinculado estáticamente están en NOTICE.

No afiliado con Paris Hilton.

Available Tools

2 tools
notes_commitA

Publish the caller's changes in the notebook directory and incorporate concurrent non-conflicting changes. Omit path or pass an empty string to use the server's notebook directory, which the result reports. message must be non-blank UTF-8 without U+0000, at most 16,384 bytes; it is retained in recent internal history only.

ParametersJSON Schema
NameRequiredDescriptionDefault
pathNoOptional absolute UTF-8 host path of the notebook directory, 1 through 4,096 bytes. Omit it or pass an empty string to use the server's notebook directory.
messageYesCommit message: non-blank UTF-8 without U+0000, at most 16,384 bytes.

TDQS

A3.6/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It does add real behavioral context beyond the name: default-path fallback, merge semantics for concurrent non-conflicting changes, and the notable fact that the message is retained only in recent internal history. However, it says nothing about permissions, failure/conflict behavior, or reversibility for what is effectively a mutation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the action and scope, followed by the constraints. The dense run of message constraints is necessary detail, though it makes the second sentence slightly overloaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter tool with no annotations and no output schema, the definition covers the default path, the merge behavior, and the message rules, and notes that the resolved directory is reported in the result. Error and conflict-resolution outcomes remain unstated, a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description genuinely adds meaning the schema lacks: the message's limited retention in internal history, and that the resolved notebook directory comes back in the result. These clarify semantics rather than restating constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (publish changes in the notebook directory) and adds the merge scope (incorporate concurrent non-conflicting changes). It never names the sibling notes_pull, so an agent must infer the pairing from the name alone, which keeps it short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: an agent can guess this is the write-side counterpart to notes_pull, but the description never says when to commit versus pull, nor any prerequisite such as needing local changes first. Minimum viable guidance, no explicit when/when-not.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

notes_pullA

Write the current notebook into the notebook directory and record the accepted state. Omit path or pass an empty string to use the server's notebook directory, which the result reports. Edit UTF-8 text files (without U+0000) there between notes_pull and notes_commit; notes_commit publishes the changes and incorporates concurrent non-conflicting changes.

ParametersJSON Schema
NameRequiredDescriptionDefault
pathNoOptional absolute UTF-8 host path of the notebook directory, 1 through 4,096 bytes. Omit it or pass an empty string to use the server's notebook directory.

TDQS

A3.9/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full load and does disclose meaningful behavior: the path-default rule, the UTF-8/no-U+0000 constraint on editable files, the accepted-state recording, and that notes_commit merges concurrent non-conflicting changes. It omits whether existing local files are overwritten or what permissions are required, which a mutation-adjacent tool would ideally state.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences with the primary action front-loaded and the default-behavior detail immediately after. Dense but every clause carries information; no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-optional-parameter tool with no annotations and no output schema, the description covers the default path, the edit window, file-format constraints, and the sibling's role. Return values are only partially addressed (it notes the result reports the directory), which keeps it from a 5.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single path parameter is fully documented there, including the 1–4,096 byte range. The description only restates the omit/empty-string default and adds that the result reports the directory, so baseline 3 is correct.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific action (materialize the current notebook into a notebook directory and record the accepted state) and clearly distinguishes itself from the sibling notes_commit, which 'publishes the changes.' The phrasing 'write the current notebook into the notebook directory' is slightly ambiguous about data direction, but the pull/commit pairing makes the intent recoverable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit workflow: edit the UTF-8 files 'between notes_pull and notes_commit,' with notes_commit handling publication and merge. It does not state when not to use it (e.g. if local edits already exist) or what happens on re-pull, so it stops short of full when/when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv0.1.0
    • First observednotes_commit
    • First observednotes_pull
Deploy Server
Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

TDQS

A3.7/5.0

Scored across 2 tools

Disambiguation5/5

notes_commit and notes_pull have clearly distinct purposes: one publishes local changes and incorporates concurrent changes, the other writes the current notebook into the directory. Their descriptions make the boundary unambiguous.

Naming Consistency5/5

Both tools follow a consistent notes_<verb> snake_case pattern. There are no deviations or mixed conventions.

Tool Count3/5

With only two tools, the set is borderline thin for a notebook version control system. While each tool earns its place, typical workflows require more operations.

Completeness2/5

The toolset covers only pull and commit, missing critical operations such as conflict resolution, status, history, and initialization. These significant gaps will cause agent failures in realistic use.

Maintenance

ActivityActive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Git MCP Server

    a-g-e-n-t-s
    A
    license
    Not graded
    quality
    D
    maintenance
    A secure and scalable Git MCP server giving AI agents powerful version control for local and (soon) serverless environments.
    91 npm
    Apache 2.0

  • Cellar

    fbereilh
    A
    license
    Not graded
    quality
    A
    maintenance
    An interactive notebook server that enables humans and AI agents to collaboratively edit and run Jupyter notebooks on a shared kernel, with real-time streaming and automatic MCP integration for agent access.
    18 npm
    MIT

  • git-courer

    blak0p
    A
    license
    Not graded
    quality
    A
    maintenance
    An MCP server that gives AI agents a full, safe interface to Git with automatic backups, isolated worktrees, and structured JSON outputs.
    43
    MIT