MCP local en Node.js + TypeScript para exponer tu vault de Obsidian a VS Code + GitHub Copilot.
Ha sido diseñado para uso local mediante stdio, con enfoque en leer y escribir notas Markdown dentro de tu vault.
npm install -g obsidian-mcp-local
Related MCP server: Obsidian MCP Server
search_notes(query)
busca por texto en la ruta, frontmatter y contenido de las notas
devuelve resultados clasificados con un pequeño extracto
get_note(path)
abre una nota del vault
devuelve path, frontmatter y content
create_note(path, content, overwrite?)
crea una nota nueva
opcionalmente sobrescribe una nota existente
append_to_note(path, content)
añade contenido al final de una nota existente
find_by_tag(tag)
encuentra notas por etiqueta
admite tags en el frontmatter y etiquetas inline en el contenido
solo accede a archivos dentro del vault configurado
ignora directorios como:
.obsidian
.git
node_modules
trabaja solo con archivos .md
normaliza rutas para evitar el acceso fuera del directorio base
obsidian-mcp-local/
package.json
tsconfig.json
README.md
.vscode/
mcp.example.json
src/
index.tsNode.js 20+
npm
VS Code con GitHub Copilot
un vault de Obsidian local
En el directorio del proyecto:
npm install
npm run buildPara desarrollo:
npm run devPara ejecutar la versión compilada:
npm startnpm install
npm run buildCopia el contenido de .vscode/mcp.example.json a tu .vscode/mcp.json en el espacio de trabajo donde vayas a usar Copilot.
Ejemplo: utilizando localmente:
{
"servers": {
"obsidian-local-vault": {
"type": "stdio",
"command": "node",
"args": ["C:/caminho/para/obsidian-mcp-local/dist/index.js"],
"env": {
"OBSIDIAN_VAULT_PATH": "D:/Obsidian/Vault"
}
}
}
}utilizando vía npx (sin necesidad de build local):
{
"servers": {
"obsidian-local-vault": {
"command": "npx",
"args": ["-y", "obsidian-mcp-local"],
"env": {
"OBSIDIAN_VAULT_PATH": "D:/Obsidian/Vault"
}
}
}
}Sustituye:
C:/caminho/para/obsidian-mcp-local/dist/index.js
D:/Obsidian/Vault
por las rutas reales de tu máquina.
Después de esto, Copilot debería descubrir el servidor MCP.
“Busca en mi vault notas sobre .NET”
“Abre la nota knowledge/backend/dotnet.md”
“Crea una nota en inbox/ideias-mcp.md con un resumen de lo que discutimos”
“Añade al final de la nota daily/2026-04-06.md el texto - testar MCP local”
“Encuentra notas con la etiqueta #arquitetura”
append_under_heading
análisis de [[wikilinks]]
get_backlinks(note)
índice en SQLite para búsqueda rápida
lista blanca de carpetas para escritura (inbox/, daily/, scratch/)
bloqueo configurable de escritura en determinadas carpetas
Este proyecto no depende de que Obsidian esté abierto.
Opera directamente sobre los archivos del vault.
Si habilitas la escritura tanto en Obsidian como en VS Code, el control de concurrencia queda bajo tu responsabilidad.
El proyecto actualmente asume que el vault es una carpeta Markdown local.
La implementación está en:
src/index.ts
Uso personal / base inicial para personalización.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| content | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| content | Yes | ||
| overwrite | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| tag | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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.
v1.0.2append_to_notecreate_notefind_by_tagget_notesearch_notesScored across 5 tools
Each tool name clearly indicates a distinct operation: create, get, append, search, and find by tag. No significant overlap is apparent.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., create_note, search_notes), making the set predictable.
Five tools cover essential note operations (create, retrieve, modify, search, tag) without unnecessary bloat or deficiency for the domain.
The set includes create, read, update (via append), and search operations but lacks a delete operation, which is a notable gap for a complete CRUD surface.
Search and reason over your Obsidian-style Markdown vault, right from ChatGPT.
Connect AI assistants to your GitHub-hosted Obsidian vault to seamlessly access, search, and analy…
Search your Obsidian vault to quickly find notes by title or keyword, summarize related content, a…
Personal context for every AI: search, read, and write back to your private Markdown library.
