Búsqueda semántica sobre archivos markdown. Encuentra notas relacionadas por significado, no solo por palabras clave. Detecta duplicados antes de crear nuevas notas.
Admite dos transportes de servidor:
stdio MCP — Para integración con Claude Code (un proceso por sesión)
HTTP — MCP-sobre-HTTP + REST combinados en un solo puerto; un proceso activo compartido por todos los clientes
Búsqueda semántica usando sentence-transformers
Detección de notas duplicadas/similares
Índice de actualización automática con monitor de archivos
Soporte para múltiples directorios
Extracción de etiquetas en línea (#tag-name)
Related MCP server: mcp-recall-md
Instalación solo CPU — recomendado para macOS (cualquier Mac, Apple Silicon o Intel) y Linux/Windows sin una GPU NVIDIA. Ahorra ~5GB de binarios CUDA. En macOS, la GPU de Apple (MPS) se detecta y utiliza automáticamente a través del backend MPS integrado de PyTorch; la etiqueta "CPU" se refiere solo a la ausencia de CUDA, no al dispositivo de cómputo en tiempo de ejecución.
uv tool install --index https://download.pytorch.org/whl/cpu \
git+https://github.com/bborbe/semantic-searchInstalación CUDA — solo para Linux/Windows con una GPU NVIDIA dedicada. No aplicable a macOS (NVIDIA CUDA no es compatible en Mac).
uv tool install git+https://github.com/bborbe/semantic-searchuv tool upgrade semantic-searchGenera un proceso por sesión de Claude Code. Es simple, pero cada sesión carga su propia copia del modelo de ~400 MB–1 GB.
claude mcp add -s project semantic-search \
--env CONTENT_PATH=/path/to/vault \
-- \
uvx --from git+https://github.com/bborbe/semantic-search semantic-search-mcpHerramientas disponibles:
search_related(query, top_k=5) — Encuentra notas semánticamente relacionadas
check_duplicates(file_path) — Detecta notas duplicadas/similares
Un único proceso de larga ejecución sirve MCP-sobre-HTTP en /mcp además de REST en /search, /duplicates, /health, /reindex. Todas las sesiones de Claude Code y clientes REST comparten un único indexador activo.
CONTENT_PATH=/path/to/vault semantic-search-http --host 127.0.0.1 --port 8321Apunte Claude Code hacia él mediante la configuración de MCP:
{
"mcpServers": {
"semantic-search": {
"type": "http",
"url": "http://127.0.0.1:8321/mcp"
}
}
}Endpoints REST:
Endpoint | Método | Descripción |
| POST | MCP-sobre-HTTP (Claude Code) |
| GET | Búsqueda semántica |
| GET | Encontrar notas duplicadas |
| GET | Comprobación de estado con estadísticas del índice |
| GET/POST | Forzar reconstrucción del índice |
Consultas de ejemplo:
# Search
curl 'http://127.0.0.1:8321/search?q=kubernetes+deployment'
# Find duplicates
curl 'http://127.0.0.1:8321/duplicates?file=notes/my-note.md'
# Health check
curl 'http://127.0.0.1:8321/health'Este repositorio también se distribuye como un plugin del marketplace de Claude Code con comandos para configuración, búsqueda e investigación.
claude plugin marketplace add bborbe/semantic-search
claude plugin install semantic-searchclaude plugin marketplace update semantic-search
claude plugin update semantic-search@semantic-search# One-shot interactive setup: installs the binary, writes the launchd/systemd
# unit, registers the MCP server in your Claude config.
/semantic-search:configure
# Search indexed markdown
/semantic-search:search kubernetes deployment
# Multi-step research across results
/semantic-search:research kafka backup strategyComando | Descripción |
| Instala |
| Búsqueda semántica a través del servidor MCP en ejecución |
| Investigación de varios pasos: buscar, categorizar, leer fuentes principales, sintetizar |
Para un uso de estilo producción, ejecute semantic-search-http como un servicio en segundo plano para que cada sesión de Claude Code (y cualquier cliente REST) comparta un proceso activo.
Plataforma | Guía |
macOS (launchd) | |
Linux (systemd) |
Ejemplo rápido (macOS):
launchctl load ~/Library/LaunchAgents/com.github.bborbe.semantic-search-http.plistEjemplo rápido (Linux):
systemctl --user enable --now semantic-search-http.serviceComandos de ejecución única sin necesidad de ejecutar un servidor:
# Search
CONTENT_PATH=/path/to/vault semantic-search search "kubernetes deployment"
# Find duplicates
CONTENT_PATH=/path/to/vault semantic-search duplicates path/to/note.mdBinario | Propósito |
| Servidor HTTP combinado: MCP en |
| Servidor MCP stdio: uno por sesión de Claude Code. Usar cuando el servicio HTTP no esté configurado. |
| Solo CLI: comandos de ejecución única |
Variable | Descripción | Predeterminado |
| Directorio a indexar (separado por comas para múltiples) |
|
| Nivel de registro (DEBUG, INFO, WARNING, ERROR) |
|
Indexe múltiples directorios separando las rutas con comas:
CONTENT_PATH=/path/to/vault1,/path/to/vault2,/path/to/docsTodos los directorios se indexan juntos y se buscan como un índice unificado.
La primera ejecución descarga un pequeño modelo de incrustación (~90MB) e indexa sus archivos markdown (<1s para bóvedas típicas). El índice se actualiza automáticamente cuando los archivos cambian mediante un monitor del sistema de archivos.
Cada archivo markdown se indexa con componentes ponderados:
Componente | Peso | Notas |
Nombre de archivo | 3x | |
Frontmatter | 3x | |
Frontmatter | 2x | Fusionado con etiquetas en línea |
Frontmatter | 2x | |
Etiquetas en línea ( | 2x | Extraídas del cuerpo |
Primer encabezado H1 | 2x | |
Contenido del cuerpo | 1x | Primeras 500 palabras |
# Clone
git clone https://github.com/bborbe/semantic-search
cd semantic-search
# Install dev dependencies
make install
# Run checks
make check
# Run tests
make testLicencia BSD 2-Clause: consulte LICENSE.
Find notes that are potential duplicates of the given file.
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | Path to the file (absolute or relative to content directory) |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral details beyond the basic 'Find' action—such as how duplicates are determined, whether the operation is read-only, or any side effects. The burden falls on the description, which is 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?
The description is a single, front-loaded sentence with no wasted words, making it highly concise 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?
Given the tool's simplicity (one parameter, output schema present), the description conveys the main purpose adequately. However, it lacks guidance on when to use vs alternatives, which is somewhat a gap but not critical for such a straightforward tool.
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 description coverage is 100% for the single parameter, so the schema fully describes file_path. The description adds no extra semantic meaning beyond what the schema already states.
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 ('Find') and resource ('notes that are potential duplicates of the given file'), clearly distinguishing it from sibling tools like search_related and get_content.
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 checking duplicates but does not explicitly state when to use this tool versus alternatives, nor any exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch the content of a file from the indexed vault.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | File path (absolute or relative to an indexed root) | |
| query | No | Search string to find the best-matching line (only used when snippet=True) | |
| snippet | No | If True, return a snippet around the best-matching line instead of the full file | |
| context_lines | No | Number of lines before and after the match to include (default 20) |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the primary action but does not disclose edge cases (e.g., file not found, path resolution), or behavior around optional parameters like snippet and query despite their existence in the schema. This leaves significant behavioral aspects undisclosed.
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, tightly worded sentence that immediately conveys the core purpose. There is no fluff or redundancy, and the information is front-loaded. For the tool's purpose, this length is appropriately concise.
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 tool has moderate complexity with optional snippet/query parameters and an output schema, and the schema covers parameter semantics. However, the description is thin on operational context, such as how path resolution works or when to use snippet mode. While not incomplete for basic selection, the description itself needed to provide more contextual glue; the schema partially compensates, but gaps remain.
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 description coverage is 100%, so a baseline of 3 is appropriate. The description itself does not add any parameter semantics beyond the schema, but the schema already documents each parameter (path, query, snippet, context_lines) clearly. The description neither enhances nor detracts from what the schema provides.
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's action ('Fetch the content of a file') and the resource ('indexed vault'), using a specific verb and resource. It distinguishes itself from sibling tools 'search_related' and 'check_duplicates' by focusing on direct content retrieval rather than search or duplication checks.
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 no guidance on when to use this tool versus alternatives. It does not mention related tools or any exclusionary conditions (e.g., 'use search_related instead when looking for related content'). The intended usage is only implicitly derived from the tool's name and action.
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.
v0.1.0check_duplicatesget_contentsearch_relatedScored across 3 tools
Each tool serves a distinct purpose: semantic search, duplicate detection, and content retrieval. There is no overlap or ambiguity between them.
All tool names follow a consistent verb_noun pattern (search_related, check_duplicates, get_content) using snake_case. The naming is predictable and readable.
Three tools is an appropriate, focused set for a semantic search server. Each tool earns its place and the scope is well-defined.
The server covers the core needs of semantic search: finding related notes, detecting duplicates, and retrieving content. There are no missing operations that would hinder its stated purpose.
Search and reason over your Obsidian-style Markdown vault, right from ChatGPT.
Personal context for every AI: search, read, and write back to your private Markdown library.
Search your Obsidian vault to quickly find notes by title or keyword, summarize related content, a…
Markdown notes in folders, with files, that your AI assistant can read, write and organise.
