Skip to main content
Glama
HorizunGroup

Horizun PBI MCP

Official
by HorizunGroup

pbi_open_and_refresh

Destructive

Open a Power BI project and refresh it immediately in one call, returning row counts by table. Reuses an open session if available.

Instructions

Abre el proyecto en Power BI Desktop y lo refresca, en una llamada.

Es la secuencia real de trabajo y siempre eran dos llamadas de unos catorce segundos cada una, porque un .pbip recien abierto trae el modelo SIN DATOS: abrirlo sin refrescar no sirve para comprobar nada.

path y pbip_path son el mismo parametro -el segundo es como lo llama pbi_session_info-, y se pueden omitir los dos: entonces se usa el proyecto .pbip activo.

Devuelve lo mismo que las dos por separado, incluido rows_by_table. Si el archivo ya estaba abierto se reutiliza esa sesion (reuse_open).

Si el refresh falla, la ventana se DEJA ABIERTA: ya cargo bien, y cerrarla borraria justo el contexto que hace falta para ver por que fallo. Sale en desktop_left_open.

Exige confirm=true desde 2.0.0. Abre una aplicacion y refresca: los dos efectos son visibles y el segundo descarta lo que hubiera en memoria sin guardar.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathNo
typeNofull
tablesNo
confirmNo
timeoutNo
pbip_pathNo
request_idNo
reuse_openNo
refresh_timeout_secondsNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description goes beyond annotations by detailing the failure behavior (window stays open if refresh fails, with desktop_left_open), the reuse_open option, and the destructive nature (discards unsaved memory data). It also warns about the confirm requirement. This aligns with destructiveHint=true and provides valuable context for the agent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is reasonably concise for the complexity it covers. It is well-structured with paragraphs, each addressing a distinct aspect (purpose, parameter alias, return behavior, failure handling, security requirement). Some redundancy exists (e.g., mentioning the two-call history in the first paragraph) but overall it earns its length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (9 params, destructive, with output schema), the description is quite complete. It covers the operational workflow, failure handling, and key parameter relationships. It does not describe all parameters or the exact output format, but the presence of an output schema lessens that need. It effectively conveys the behavioral contract.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema coverage, the description must explain parameters. It clarifies that path and pbip_path are aliases, optional, and default to the active project. It mentions reuse_open and confirm effects. However, it does not explain type, tables, timeout, request_id, or refresh_timeout_seconds, leaving gaps for those parameters. Still, it covers the most critical ones.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Abre el proyecto en Power BI Desktop y lo refresca, en una llamada.' It names the specific verb (open and refresh) and the resource (Power BI Desktop project), and distinguishes itself from siblings like pbi_open_pbip_project and pbi_refresh_model by emphasizing the single-call combination.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage context: it calls out that opening without refreshing is useless for a .pbip with no data, explains that path/pbip_path can be omitted for the active project, and mentions that confirm=true is required since version 2.0.0. It also differentiates from separate calls by explaining the efficiency gain, giving clear when-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/HorizunGroup/horizun-pbi-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server