Lectura genérica de cualquier modelo Odoo vía XML-RPC (search_read). Útil para consultar categorías, clientes, productos, lotes, órdenes, etc. Ejemplo: model="product.category", fields=["id","name"], order="name asc". Para buscar un registro por ID: domain=[["id","=",42]]. Para buscar productos p...
AI agents call odooSearchRead to retrieve information from Olivia without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | number | — | Máximo de registros (default: 80) |
model | string | Yes | Nombre del modelo Odoo (ej: "product.template", "product.category", "res.partner", "stock.lot") |
order | string | — | Ordenamiento. Ej: "name asc", "id desc", "create_date desc" |
domain | array | — | Filtro Odoo domain (default: [] = todos). Ej: [["name","ilike","test"]] o [["id","=",5]] |
fields | array | — | Campos a retornar (default: [] = todos). Ej: ["id","name","list_price"] |
offset | number | — | Desde qué posición empezar, para paginación (default: 0) |
Parameters from the server's own tool schema.
This tool retrieves and queries data from Odoo without modifying, deleting, or executing operations. It supports filtering, sorting, and pagination on various Odoo models but produces no side effects. It is a straightforward read operation consistent with data retrieval tools.
From the tool's definition Tool description explicitly states 'Lectura genérica' (generic read) and describes search_read operations for querying models like product.category, customers, products, batches, orders with parameters like fields, domain, order, limit/offset.
Attacks that exploit this kind of access
Lectura genérica de cualquier modelo Odoo vía XML-RPC (search_read). Útil para consultar categorías, clientes, productos, lotes, órdenes, etc. Ejemplo: model="product.category", fields=["id","name"], order="name asc". Para buscar un registro por ID: domain=[["id","=",42]]. Para buscar productos por nombre: model="product.template", domain=[["name","ilike","miel"]]. Soporta paginación con limit/offset. It is categorised as a Read tool in the Olivia MCP Server, which means it retrieves data without modifying state.
odooSearchRead accepts 6 parameters: limit, model, order, domain, fields, offset. Required: model. The full parameter table on this page comes from the server's own tool schema.
Register the Olivia MCP server in PolicyLayer and add a rule for odooSearchRead: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Olivia. Nothing to install.
odooSearchRead is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the odooSearchRead rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for odooSearchRead. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
odooSearchRead is provided by the Olivia MCP server (@facusrod/olivia-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →