mcp-bcrp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BCRP_TIMEOUT | No | HTTP request timeout in seconds | 120 |
| BCRP_CACHE_DIR | No | Directory for metadata cache | User cache dir |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_seriesA | Search for BCRP economic indicators by keyword. Uses deterministic search with fuzzy matching. Returns the best match or an ambiguity error if multiple matches are equally scored. Args: query: Search term (e.g., "tipo de cambio", "inflacion", "PBI") Returns: JSON string with match result containing codigo_serie and confidence, or error details if ambiguous or not found. |
| get_dataA | Fetch time series data for specific BCRP series codes. Args: series_codes: List of BCRP series codes (e.g., ["PN01652XM", "PD04638PD"]) period: Date range in format 'YYYY-MM/YYYY-MM' or single 'YYYY-MM'. If None, returns all available data. Returns: JSON string with array of records containing 'time' and values. |
| get_tableB | Get a formatted table with custom column names. Args: series_codes: List of BCRP series codes to retrieve names: Optional custom names for columns (must match series_codes length) period: Date range in format 'YYYY-MM/YYYY-MM' or 'YYYY' Returns: JSON string with formatted table data. |
| plot_chartA | Generate a professional chart for BCRP series data. Returns the path to the saved PNG file. Args: series_codes: List of BCRP series codes to plot period: Date range in format 'YYYY-MM/YYYY-MM' (optional) title: Custom chart title (optional, uses series name if not provided) names: Custom names for each series in legend (optional) output_path: Custom output path for the chart (optional) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| economista_peruano | Prompt para actuar como un experto economista peruano (BCRP). Usa este prompt para analizar datos con rigor técnico y contexto local. |
| analista_financiero | Prompt para análisis de mercados financieros (Forex, Tasas). Enfocado en movimientos de corto plazo y niveles técnicos. |
| explorador_datos | Prompt para ayudar a descubrir códigos de series del BCRP. Actúa como un bibliotecario de la base de datos BCRP. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| get_metadata | Retorna resumen de metadatos en caché incluyendo conteo total. |
| get_key_indicators | Retorna lista de los principales indicadores económicos. |
| get_help | Retorna guía de uso del servidor MCP BCRP. |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: get_data retrieves raw time series data, get_table provides formatted tabular data, plot_chart generates visual charts, and search_series helps find series codes. There is no functional overlap between these tools, making selection straightforward for an agent.
All tool names follow a consistent verb_noun pattern with snake_case: get_data, get_table, plot_chart, and search_series. The naming convention is predictable and readable throughout the toolset.
With 4 tools, this server is well-scoped for working with BCRP economic data. Each tool serves a distinct purpose in the data workflow (search, retrieve raw data, format tables, visualize), and none feel extraneous or missing for the domain.
The toolset covers the essential workflow for BCRP data analysis: searching for series, retrieving data in different formats, and visualizing results. A minor gap exists in lacking update/delete operations, but these are likely unnecessary for read-only economic data access, and agents can work effectively with the provided tools.