MCP-сервер на Node.js + TypeScript для предоставления доступа к вашему хранилищу Obsidian для VS Code + GitHub Copilot.
Он предназначен для локального использования через stdio с упором на чтение и запись Markdown-заметок внутри вашего хранилища.
npm install -g obsidian-mcp-local
Related MCP server: Obsidian MCP Server
search_notes(query)
поиск текста в пути, frontmatter и содержимом заметок
возвращает ранжированные результаты с небольшим фрагментом текста
get_note(path)
открывает заметку из хранилища
возвращает path, frontmatter и content
create_note(path, content, overwrite?)
создает новую заметку
опционально перезаписывает существующую заметку
append_to_note(path, content)
добавляет содержимое в конец существующей заметки
find_by_tag(tag)
находит заметки по тегу
поддерживает tags во frontmatter и встроенные теги в содержимом
доступ только к файлам внутри настроенного хранилища
игнорирует такие директории, как:
.obsidian
.git
node_modules
работает только с файлами .md
нормализует пути, чтобы предотвратить доступ за пределами базовой директории
obsidian-mcp-local/
package.json
tsconfig.json
README.md
.vscode/
mcp.example.json
src/
index.tsNode.js 20+
npm
VS Code с GitHub Copilot
локальное хранилище Obsidian
В директории проекта:
npm install
npm run buildДля разработки:
npm run devДля запуска скомпилированной версии:
npm startnpm install
npm run buildСкопируйте содержимое .vscode/mcp.example.json в ваш .vscode/mcp.json в рабочей области, где вы будете использовать Copilot.
Пример: использование локально:
{
"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"
}
}
}
}использование через npx (без необходимости локальной сборки):
{
"servers": {
"obsidian-local-vault": {
"command": "npx",
"args": ["-y", "obsidian-mcp-local"],
"env": {
"OBSIDIAN_VAULT_PATH": "D:/Obsidian/Vault"
}
}
}
}Замените:
C:/caminho/para/obsidian-mcp-local/dist/index.js
D:/Obsidian/Vault
на реальные пути на вашем компьютере.
После этого Copilot должен обнаружить MCP-сервер.
“Найди в моем хранилище заметки о .NET”
“Открой заметку knowledge/backend/dotnet.md”
“Создай заметку в inbox/ideias-mcp.md с кратким изложением того, что мы обсуждали”
“Добавь в конец заметки daily/2026-04-06.md текст - протестировать локальный MCP”
“Найди заметки с тегом #arquitetura”
append_under_heading
парсинг [[wikilinks]]
get_backlinks(note)
индекс в SQLite для быстрого поиска
белый список папок для записи (inbox/, daily/, scratch/)
настраиваемая блокировка записи в определенных папках
Этот проект не зависит от запущенного Obsidian.
Он работает напрямую с файлами хранилища.
Если вы включите запись как в Obsidian, так и в VS Code, контроль конкурентного доступа остается на ваше усмотрение.
Проект в текущем виде предполагает, что хранилище — это локальная папка с Markdown-файлами.
Реализация находится в:
src/index.ts
Личное использование / базовая основа для кастомизации.
| 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.
