Tus agentes de IA olvidan todo entre sesiones. Connapse soluciona eso.
Cada vez que inicias una nueva conversación, tu agente de IA comienza desde cero: sin memoria de investigaciones pasadas, sin acceso a tus documentos, sin conocimiento acumulado. Connapse es un backend de conocimiento de código abierto que proporciona a los agentes memoria persistente y buscable. Sube documentos o apúntalo a tus buckets existentes de Amazon S3, contenedores de Azure Blob Storage o sistemas de archivos locales. Los agentes consultan y construyen su propio corpus de investigación a través de 11 herramientas MCP, API REST o CLI. Aislado en contenedores, búsqueda híbrida (vectorial + palabras clave), autohospedado y privado. Despliega en 60 segundos con Docker. Construido sobre .NET 10.
Los agentes de IA consultan tu base de conocimiento a través del servidor MCP, recibiendo respuestas estructuradas con citas de fuentes de tus documentos.
Cambia los proveedores de embedding, ajusta los parámetros de fragmentación y configura la búsqueda: todo en tiempo de ejecución, sin reiniciar.
git clone https://github.com/Destrayon/Connapse.git && cd Connapse && docker-compose up -d
# Open http://localhost:5001.NET 10 SDK (para desarrollo)
(Opcional) Ollama para embeddings locales
# Clone the repository
git clone https://github.com/Destrayon/Connapse.git
cd Connapse
# Set required auth environment variables (or use a .env file)
export CONNAPSE_ADMIN_EMAIL=admin@example.com
export CONNAPSE_ADMIN_PASSWORD=YourSecurePassword123!
export Identity__Jwt__Secret=$(openssl rand -base64 64)
# Start all services (PostgreSQL, MinIO, Web App)
docker-compose up -d
# Open http://localhost:5001 — log in with the admin credentials aboveLa primera ejecución hará lo siguiente:
Descargará las imágenes de Docker (~2-5 minutos)
Inicializará PostgreSQL con la extensión pgvector y ejecutará las migraciones de EF Core
Creará los buckets de MinIO
Sembrará la cuenta de administrador (desde variables de entorno) e iniciará la aplicación web
# Start infrastructure only (database + object storage)
docker-compose up -d postgres minio
# Run the web app locally
dotnet run --project src/Connapse.Web
# Run all tests
dotnet test
# Run just unit tests
dotnet test --filter "Category=Unit"Instala la CLI (elige una opción):
# Option A: .NET Global Tool (requires .NET 10)
dotnet tool install -g Connapse.CLI
# Option B: Download native binary from GitHub Releases (no .NET required)
# https://github.com/Destrayon/Connapse/releasesUso básico:
# Authenticate first
connapse auth login --url https://localhost:5001
# Create a container (project)
connapse container create my-project --description "My knowledge base"
# Upload files
connapse upload ./documents --container my-project
# Search
connapse search "your query" --container my-project
# Update to latest release (--pre to include alpha/pre-release builds)
connapse update
connapse update --preConnapse incluye un servidor de Protocolo de Contexto de Modelo (MCP) para la integración con Claude y cualquier cliente MCP.
Configuración: Crea una clave de API de agente a través de la interfaz web (Configuración → Claves de API de agente) o CLI (connapse auth agent-key create), luego añade el fragmento de configuración para tu cliente:
claude mcp add connapse --transport streamable-http http://localhost:5001/mcp --header "X-Agent-Api-Key: YOUR_API_KEY"Añade a tu claude_desktop_config.json:
{
"mcpServers": {
"connapse": {
"transport": "streamable-http",
"url": "http://localhost:5001/mcp",
"headers": {
"X-Agent-Api-Key": "YOUR_API_KEY"
}
}
}
}Añade a tu .vscode/settings.json (VS Code) o a la configuración MCP de Cursor:
{
"mcp": {
"servers": {
"connapse": {
"transport": "streamable-http",
"url": "http://localhost:5001/mcp",
"headers": {
"X-Agent-Api-Key": "${input:connapseApiKey}"
}
}
}
}
}VS Code solicitará la clave de API en el primer uso.
El servidor MCP expone 11 herramientas:
Herramienta | Descripción |
| Crea un nuevo contenedor para organizar archivos |
| Lista todos los contenedores con conteo de documentos |
| Elimina un contenedor |
| Obtiene estadísticas del contenedor (documentos, fragmentos, almacenamiento, embeddings) |
| Sube un solo archivo a un contenedor |
| Sube hasta 100 archivos en una sola operación |
| Lista archivos y carpetas en una ruta |
| Recupera el contenido de texto completo analizado de un documento |
| Elimina un solo archivo de un contenedor |
| Elimina hasta 100 archivos en una sola operación |
| Búsqueda semántica, por palabras clave o híbrida dentro de un contenedor |
Referencia completa: Consulta docs/mcp-tools.md para tablas de parámetros, formatos de retorno, casos de error y ejemplos de uso.
Protecciones de escritura: Los contenedores de Amazon S3 y Azure Blob Storage son de solo lectura (sincronizados desde la fuente). Los contenedores del sistema de archivos respetan las banderas de permisos por contenedor. Las herramientas de subida y eliminación devolverán un error para los contenedores que bloqueen las escrituras.
"Crea un contenedor llamado 'project-research' para mis notas de arquitectura"
"Sube todos los PDF de mi carpeta de descargas al contenedor project-research"
"Busca en mi contenedor project-research información sobre estrategias de limitación de tasa"
"Lista todos los archivos en la carpeta /notes/ de mi contenedor project-research"
"Obtén el texto completo de distributed-systems-notes.md de project-research"
"Elimina meeting-2026-03-14.md de project-research y sube esta versión actualizada"
"Elimina todos los archivos en la carpeta /drafts/ de project-research"
"¿Cuántos documentos y fragmentos hay en mi contenedor project-research?"
Conexión rechazada en localhost:5001 — Docker no se está ejecutando o hay conflicto de puertos. Comprueba docker compose ps y docker compose logs web.
401 No autorizado / La clave de API no funciona — Verifica la clave en Configuración > Claves de API de agente. Las claves se muestran una vez al crearlas.
Las herramientas no aparecen en Claude — Reinicia tu cliente MCP después de los cambios de configuración. Verifica el endpoint con curl http://localhost:5001/mcp.
Las subidas fallan o se agota el tiempo de espera — Comprueba que el tipo de archivo esté en la lista de permitidos. El tamaño máximo de archivo depende de la configuración del servidor.
La búsqueda no devuelve resultados — Los documentos necesitan tiempo para ser procesados (embeddings) después de la subida. Comprueba las estadísticas del contenedor para ver el progreso.
Related MCP server: mnemostack
🗂️ Conocimiento aislado en contenedores — Cada proyecto obtiene su propio índice vectorial, conector de almacenamiento y configuración de búsqueda. Sin contaminación cruzada entre proyectos, equipos o clientes.
🔍 Búsqueda híbrida — Similitud vectorial + texto completo de palabras clave con fusión configurable (combinación convexa, DBSF, AutoCut). Obtén resultados que la búsqueda puramente vectorial pierde.
🧠 IA multi-proveedor — Cambia entre Ollama, OpenAI, Azure OpenAI y Anthropic tanto para embeddings como para LLM, en tiempo de ejecución, por contenedor, sin reiniciar.
🔌 Indexa tu almacenamiento existente — Conecta MinIO, sistema de archivos local (observación de archivos en vivo), Amazon S3 (autenticación IAM) o Azure Blob Storage (identidad administrada). Tus archivos permanecen donde están.
🤖 4 superficies de acceso — Interfaz web, API REST, CLI (binarios nativos) y servidor MCP (11 herramientas para Claude). Construido para humanos, scripts y agentes de IA por igual.
🔐 Autenticación empresarial — RBAC de varios niveles (Cookie + OAuth 2.1 + PAT + JWT) con AWS IAM Identity Center y vinculación de identidad de Azure AD. Los permisos de la nube son la fuente de verdad.
🐳 Despliegue con un comando — Docker Compose con PostgreSQL + pgvector, MinIO y Ollama opcional. Registro de auditoría estructurado y limitación de tasa integrados.
📄 Ingesta multiformato: PDF, documentos de Office, Markdown, texto plano: analizados, fragmentados e integrados automáticamente
⚡ Procesamiento en tiempo real: Ingesta en segundo plano con actualizaciones de progreso en vivo a través de SignalR
🎛️ Configuración en tiempo de ejecución: Cambia la estrategia de fragmentación, el modelo de embedding y los ajustes de búsqueda por contenedor sin reiniciar
☁️ Vinculación de identidad en la nube: AWS IAM Identity Center (flujo de autenticación de dispositivo) + Azure AD (OAuth2+PKCE) con cumplimiento de alcance derivado de IAM
👥 Acceso solo por invitación: Registro de usuarios controlado por el administrador con cuatro roles (Administrador / Editor / Visor / Agente)
🤖 Gestión de agentes: Entidades de agente dedicadas con ciclo de vida de clave de API, permisos con alcance y pistas de auditoría
📋 Registro de auditoría: Pista de auditoría estructurada para subidas, eliminaciones, operaciones de contenedor y eventos de autenticación
📦 Distribución CLI: Binarios nativos autocontenidos (Windows/Linux/macOS) y herramienta global .NET a través de NuGet
🔄 Búsqueda entre modelos: Cambia los modelos de embedding a mitad del proyecto: respaldo automático de Semántico→Híbrido para vectores heredados
Desarrolladores de agentes de IA que necesitan un backend de conocimiento que sus agentes puedan consultar y construir: sube investigación, cura un corpus y búscalo a través de MCP o API REST
Equipos de .NET / Azure que desean una plataforma RAG que se ajuste a su stack existente y a su identidad en la nube
Equipos empresariales que necesitan bases de conocimiento aisladas por proyecto con RBAC adecuado y pistas de auditoría
Cualquiera que esté cansado de volver a subir archivos: apunta Connapse a tu almacenamiento existente de Amazon S3/Azure Blob Storage/sistema de archivos
Este proyecto está en desarrollo activo (v0.3.2) y acercándose a la preparación para producción.
v0.3.x añade arquitectura de conector en la nube con control de acceso basado en IAM, soporte para embeddings y LLM de múltiples proveedores, vinculación de identidad en la nube (AWS SSO + Azure AD) y limitación de tasa.
✅ Autenticación y autorización (v0.2.0)
✅ Control de acceso basado en roles (Administrador / Editor / Visor / Agente)
✅ Registro de auditoría
✅ Vinculación de identidad en la nube — AWS IAM Identity Center + Azure AD OAuth2+PKCE (v0.3.0)
✅ Cumplimiento de alcance derivado de IAM — los permisos de la nube son la fuente de verdad (v0.3.0)
✅ Limitación de tasa — middleware integrado de ASP.NET Core con políticas por usuario y por IP (v0.3.2)
⚠️ Establece un Identity__Jwt__Secret fuerte en producción — consulta la guía de despliegue
Consulta SECURITY.md para conocer la política de seguridad completa.
┌──────────────────────────────────────────────────────────────────────┐
│ Access Surfaces │
│ Web UI (Blazor) │ REST API │ CLI │ MCP Server │
└─────────────┬────────────────────────────────────────────────────────┘
│
┌─────────────▼────────────────────────────────────────────────────────┐
│ Core Services Layer │
│ Document Store │ Vector Store │ Search │ Ingestion │
└─────────────┬────────────────────────────────────────────────────────┘
│
┌─────────────▼────────────────────────────────────────────────────────┐
│ Connectors Layer │
│ MinIO │ Filesystem │ Amazon S3 │ Azure Blob Storage │
└─────────────┬────────────────────────────────────────────────────────┘
│
┌─────────────▼────────────────────────────────────────────────────────┐
│ Infrastructure │
│ PostgreSQL+pgvector │ MinIO (S3) │ Ollama (optional) │
└──────────────────────────────────────────────────────────────────────┘[Upload] → [Parse] → [Chunk] → [Embed] → [Store] → [Searchable]
↓
[Metadata]
↓
[Document Store]Objetivo: < 30 segundos desde la subida hasta que sea buscable.
Tecnologías clave:
Base de datos: PostgreSQL 17 + pgvector para embeddings vectoriales
Almacenamiento de objetos: Abstracción de almacenamiento administrado: MinIO (compatible con S3) por defecto, anulable por despliegue
Backend: ASP.NET Core 10 Minimal APIs
Frontend: Blazor Server (modo interactivo)
Embeddings: Ollama (por defecto), OpenAI, Azure OpenAI (configurable)
LLM: Ollama, OpenAI, Azure OpenAI, Anthropic (configurable)
Búsqueda: Híbrida vectorial + palabras clave con fusión de combinación convexa
Conectores: Almacenamiento administr
Delete up to 100 files in one call. Returns per-file success/failure results.
| Name | Required | Description | Default |
|---|---|---|---|
| containerId | Yes | Container ID or name | |
| fileIds | Yes | JSON array of file (document) IDs to delete, e.g. ["id1","id2"]. Max 100. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds valuable behavioral details beyond the destructiveHint annotation, such as the batch limit and per-file result format.
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?
Two sentences, front-loaded with purpose and limits, no unnecessary words.
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 output schema, description compensates by noting per-file results. Covers key constraints (limit, return format). Could mention error handling for missing files, but sufficient.
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 already describes both parameters fully (100% coverage). The description does not add new semantic value beyond 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 action (delete), resource (files), and limits (up to 100, one call), distinguishing it from single-file deletion and bulk upload.
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?
Implies usage for deleting multiple files up to 100, but lacks explicit when-to-use vs alternatives or when-not-to-use scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Upload up to 100 files in one call. Each file is parsed, chunked, and embedded. Returns per-file results.
| Name | Required | Description | Default |
|---|---|---|---|
| containerId | Yes | Container ID or name | |
| files | Yes | JSON array of file objects. Each object: {"filename":"name.txt", "content":"...", "encoding":"text|base64", "folderPath":"/optional/"}. Max 100. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses the processing pipeline (parse, chunk, embed) but lacks details on error handling for partial failures, file size limits, or supported formats. Adequate but not comprehensive.
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?
Two sentences, no filler. Every sentence provides essential information: capacity, processing, and return type.
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 exists, so description should clarify return values. 'Returns per-file results' is vague; could specify status, errors, or IDs. Also missing constraints like file size, timeout, or authentication requirements.
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%, both parameters are documented. The description adds 'Max 100' which reinforces the schema's 'max 100' constraint in files parameter description, but no new meaning beyond schema.
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 specific verb 'Upload' with resource 'files', states the limit 'up to 100', and explains the processing pipeline ('parsed, chunked, and embedded'). It clearly distinguishes from sibling 'upload_file' which handles single files.
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 bulk usage via 'up to 100 files' but does not explicitly state when to use this over single upload or alternatives like 'search_knowledge'. No when-not or alternative tool names are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create a new container for organizing documents. Use when setting up a new knowledge domain or project.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Container name (lowercase alphanumeric and hyphens, 2-128 chars) | |
| description | No | Optional description for the container |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It only states creation purpose, lacking details on permissions, side effects, or duplicate handling. Adequate but 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?
Two clear sentences, front-loaded with action, no unnecessary words.
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 (e.g., created container info). Adequate for simple tool but incomplete on expected response.
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 both parameters. Description repeats the same meaning, adding no extra value. Baseline 3.
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?
Clearly states action (create), resource (container), and purpose (organizing documents). Distinguishes from sibling tools like container_delete or container_list.
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?
Explicitly says 'Use when setting up a new knowledge domain or project', providing clear context. Does not mention exclusions or alternatives, but context is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Delete a container. MinIO containers must be emptied first. Filesystem/S3/Azure files are not deleted — only the index is removed.
| Name | Required | Description | Default |
|---|---|---|---|
| containerId | Yes | Container ID or name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the destructiveHint annotation, the description adds important behavioral details: files are not deleted, only the index is removed, and MinIO containers must be emptied first.
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?
Two concise sentences, front-loaded with the action and followed by key constraints, with no unnecessary words.
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 tool with one parameter and no output schema, the description covers the essential behavior, prerequisites, and what is not deleted, though it could mention irreversibility.
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%, and the description does not add additional meaning beyond the schema's parameter 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?
The description clearly states the tool deletes a container, and differentiates from sibling tools like delete_file by clarifying that files are not deleted, only the index.
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?
It specifies a prerequisite (MinIO containers must be emptied) and clarifies what is not affected, but does not explicitly compare to alternatives like bulk_delete.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all containers with document counts. Use to discover available knowledge bases before searching.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, so the description doesn't need to repeat these. It adds the return of document counts, but lacks details on pagination or performance. With annotations covering safety, this is adequate.
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 two sentences (12 words) that are front-loaded and contain no fluff. 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?
Given no parameters and no output schema, the description covers the tool's purpose and usage context well. It mentions 'document counts,' giving insight into return data, but could be slightly more detailed on output format.
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, so schema coverage is 100%. The description adds no parameter info, which is appropriate. Baseline 4 for 0 parameters.
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 lists all containers with document counts and specifies its use for discovering knowledge bases before searching. This differentiates it from sibling tools like container_stats or container_create.
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 explicitly says 'Use to discover available knowledge bases before searching,' providing clear context for when to use it. It lacks explicit exclusion guidance but is sufficient given the sibling context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get container statistics: document counts, chunk count, storage size, and embedding model info.
| Name | Required | Description | Default |
|---|---|---|---|
| containerId | Yes | Container ID or name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only and idempotent behavior. The description adds value by specifying the exact statistics returned, providing context beyond what annotations offer. No contradictions.
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 that efficiently conveys the tool's purpose and output details with no unnecessary words.
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-only tool with one parameter and no output schema, the description fully covers what the tool returns and its use case, making it complete.
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 coverage for the single parameter (containerId) with a clear description. The tool description does not add additional semantic meaning for the parameter, so baseline 3 is appropriate.
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 'Get container statistics' and lists specific data (document counts, chunk count, storage size, embedding model info), making it distinct from siblings like container_list which only list container IDs or names.
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 the tool is for retrieving statistics of a specific container but does not explicitly state when to use it over alternatives or provide exclusions. No guidance on prerequisites (e.g., container must exist).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Delete a file and all its chunks and vectors. To update a file, delete it first then re-upload with upload_file.
| Name | Required | Description | Default |
|---|---|---|---|
| containerId | Yes | Container ID or name | |
| fileId | Yes | File (document) ID to delete |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already flag destructiveHint=true. The description adds value by specifying that chunks and vectors are also deleted, giving a fuller scope of the operation's effects. It does not contradict annotations.
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?
Two concise sentences: first clearly states the purpose, second provides a practical usage tip. No fluff, front-loaded, every sentence 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 destructive tool with full schema coverage and an annotation, the description adequately covers the deletion scope and provides an update workflow hint. It could mention irreversibility or permissions, but these are implied by the destructive hint. Overall sufficient.
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 already documents both parameters (containerId and fileId) with descriptions, achieving 100% coverage. The description does not add extra semantic detail beyond what the schema provides, so the baseline score of 3 is appropriate.
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 'Delete a file and all its chunks and vectors', which specifies the verb (delete) and resource (file and associated data). It also distinguishes from siblings like bulk_delete by implying single-file deletion via the fileId parameter, and provides additional context about 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 includes explicit guidance for updating: 'To update a file, delete it first then re-upload with upload_file.' However, it does not explicitly warn against using this tool for bulk deletions or when to prefer bulk_delete, though the parameterization hints at single-file usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve a document's full text by ID or path. Returns extracted text for binary formats (PDF, DOCX, PPTX).
| Name | Required | Description | Default |
|---|---|---|---|
| containerId | Yes | Container ID or name | |
| fileId | Yes | Document ID (UUID) or virtual path (e.g., '/docs/readme.md') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint and idempotentHint. Description adds that it returns extracted text for binary formats (PDF, DOCX, PPTX) beyond what annotations convey.
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?
Two front-loaded sentences, no waste, clearly communicate purpose and key behavior.
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 retrieval tool with 2 required parameters, description covers purpose, return value (full text, extraction for binaries). Lacks error handling or response format, but sufficient for typical use.
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 good descriptions for both parameters. Description restates 'by ID or path' but adds no new semantic detail beyond schema.
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 verb 'Retrieve' and resource 'document's full text', specifies query by ID or path, and mentions handling of binary formats. Distinguishes from siblings like list_files (metadata) and search_knowledge.
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?
Implied usage context as a read-only retrieval tool, but no explicit when-to-use or alternatives (e.g., 'for metadata use list_files'). Clear enough for an agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List files and folders at a path within a container. Use to browse container contents before retrieving documents.
| Name | Required | Description | Default |
|---|---|---|---|
| containerId | Yes | Container ID or name | |
| path | No | Folder path to list (default: root '/') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered. The description adds the browsing context but does not disclose additional behavioral traits such as pagination or error handling, which would provide further transparency.
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 extremely concise with two sentences: one for the core function and one for usage guidance. Every word is necessary and no information is redundant.
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 list operation with two parameters and no output schema, the description is fairly complete. It covers what the tool does and when to use it, though it could mention the return structure (e.g., list of file names) to be fully self-contained.
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 the baseline is 3. The description does not add any parameter details beyond what the schema already provides for containerId and path.
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 'list' and specifies the resource 'files and folders at a path within a container'. It also provides context by stating its use case 'before retrieving documents', which distinguishes it from siblings like get_document, upload_file, and delete_file.
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 advises using this tool to browse container contents before retrieving documents, giving clear context. However, it does not explicitly exclude other uses or mention alternatives beyond the implied contrast with get_document.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search a container using semantic, keyword, or hybrid mode. Returns ranked document chunks with scores. Use when answering questions from stored knowledge.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The search query text | |
| containerId | Yes | Container ID or name to search within | |
| mode | No | Search mode: Semantic (vector), Keyword (full-text), or Hybrid (both). Default: Hybrid | |
| topK | No | Number of results to return. Default: 10 | |
| path | No | Optional: Filter results to a folder subtree (e.g., '/docs/') | |
| minScore | No | Minimum similarity score floor (0.0-1.0). Defaults to 0.05. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true, so the main behavioral traits are covered. The description adds 'Returns ranked document chunks with scores,' which gives some extra context but is not critical. No destructive behavior or auth needs are mentioned, but annotations suffice.
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 two sentences long, with the first sentence covering purpose and behavior, and the second giving usage guidance. Every sentence adds value, and there is no unnecessary text.
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 100% schema coverage, the presence of annotations, and no output schema, the description is fairly complete. It covers purpose, usage, and return type. However, it could briefly mention that results are from the specified container, but that is implicit in the first sentence.
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 each parameter having a description in the input schema. The tool description does not add any additional information about the parameters beyond what the schema already provides, so baseline 3 is appropriate.
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 a container') and specifies the modes (semantic, keyword, hybrid). It also mentions the return type ('ranked document chunks with scores'), making the tool's purpose distinct from siblings like container_list or get_document.
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 explicitly suggests using the tool 'when answering questions from stored knowledge,' providing a clear use case. However, it does not mention when not to use it or compare to alternatives, which would make it a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Upload a file to be parsed, chunked, embedded, and made searchable. Provide either 'content' (base64) or 'textContent' (raw text), not both.
| Name | Required | Description | Default |
|---|---|---|---|
| containerId | Yes | Container ID or name | |
| content | No | Base64-encoded file content. For binary files (PDF, DOCX, images). Mutually exclusive with textContent. | |
| textContent | No | Raw text content for text-based files (Markdown, TXT, CSV, JSON, etc.). Mutually exclusive with content. | |
| fileName | No | Original file name with extension | |
| path | No | Destination folder path (e.g., '/docs/2026/') | |
| strategy | No | Chunking strategy: Semantic, FixedSize, or Recursive. Default: Semantic |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full burden. It mentions the processing pipeline (parse, chunk, embed) and mutual exclusivity of content types, but does not disclose failure modes, idempotency, permissions, or response format. This is adequate but not rich.
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?
Two sentences with no waste. The purpose is front-loaded, and essential usage hint is included. Every sentence 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?
With 6 parameters (1 required), schema covers all, and no output schema, the description is fairly complete. It explains the overall goal and key constraint. However, it omits details on return value or confirmation. Still, it is adequate for an agent to understand and use the 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 coverage is 100%, so baseline is 3. The description reiterates the mutual exclusivity of content and textContent already in schema descriptions, adding minimal extra meaning. No new parameter semantics beyond the schema.
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 ('Upload a file') and the resource, and describes the processing pipeline ('parsed, chunked, embedded, and made searchable'). This distinguishes it from sibling tools like bulk_upload (multiple files) and delete_file (deletion).
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 gives a parameter usage guideline ('Provide either content or textContent, not both') but lacks explicit guidance on when to use this tool over siblings like bulk_upload or search_knowledge. No when-not-to-use or alternative recommendations are provided.
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.
v0.3.2bulk_deletebulk_uploadcontainer_createcontainer_deletecontainer_listcontainer_statsdelete_fileget_documentlist_filessearch_knowledgeupload_fileScored across 11 tools
Each tool targets a distinct operation: container management, file operations, bulk actions, and search. No two tools have overlapping purposes; even delete_file and bulk_delete are clearly scoped by single vs batch.
All tools follow a consistent verb_noun snake_case pattern (e.g., container_create, upload_file, search_knowledge). No mixed conventions or vague verbs.
11 tools is well-scoped for a knowledge management server, covering container CRUD, file operations, bulk operations, and search. No redundancy or missing essential operations.
Covers most lifecycle operations: container create/list/delete, file upload/get/list/delete, bulk upload/delete, and search. Missing container update and folder creation, but these are minor gaps that agents can work around.
Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
Multi-engine search for AI agents. Trust scoring, local corpus, MCP-native. Self-hostable, BYOK.
Governed, auditable knowledge your team curates for its AI assistants, self-hostable
MCP-first toolbox for agents: KV storage, auth, queue, and utility tools. Free in early access.
