Skip to main content
Glama

bcrp_get_series

Fetch up to 10 BCRP time series by code and date range to retrieve exchange rates, interest rates, GDP, and other economic indicators.

Instructions

Fetch time series data from the BCRP (Banco Central de Reserva del Perú) API.

Accepts 1–10 series codes of the SAME frequency. Series codes can be found using bcrp_search_catalog or the bcrp://series-catalog resource.

Period format by frequency:

  • Monthly: YYYY-M (e.g. 2024-1 = January 2024, 2024-12 = December 2024)

  • Quarterly: YYYY-Q (e.g. 2024-1 = Q1 2024, 2024-4 = Q4 2024)

  • Daily: DD-MM-YYYY (e.g. 01-01-2025)

  • Annual: YYYY (e.g. 2024)

  • Leave both periods empty to get the most recent available data.

Important: All series in one call must have the same frequency (all daily, all monthly, etc.). Need MORE than 10 series, or a mix of frequencies? Use bcrp_get_series_long instead — up to 50 codes of any frequencies, returned as one tidy long table.

Responses are cached on disk between calls, so repeating a query is free. An empty series list means the code is valid but has no data in that range, not that the code is wrong — check it with bcrp_describe_series.

Example codes: PD04637PD (exchange rate), PD12301MD (policy rate), PN00196MM (total liquidity), PN03503MQ (GDP var%)

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "series_codes": "<series_codes>"
    },
    "name": "bcrp_get_series"
  }
}

Input Schema

NameRequiredDescriptionDefault
languageNoLanguage for series names: 'esp' (Spanish) or 'ing' (English)esp
end_periodNoEnd of date range. Same format as start_period.
series_codesYesList of 1–10 BCRP series codes (same frequency). E.g. ['PD04637PD', 'PD12301MD']
start_periodNoStart of date range. Format depends on series frequency: - Monthly: YYYY-M (e.g. '2020-1') - Quarterly: YYYY-Q (e.g. '2020-1') - Daily: DD-MM-YYYY (e.g. '01-01-2025') Leave empty for most recent data.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose real behavior: on-disk caching between calls, the same-frequency constraint across the array, and the semantics of an empty series list (valid code, no data in range). It stops short of describing authentication, rate limits, or the shape/units of the returned data.

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?

Front-loaded with purpose and scope, then organized into scannable blocks (period formats, same-frequency warning, sibling routing, empty-result note, examples). Some content duplicates the period-format text already present in the start_period schema, which is minor waste.

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?

There is no output schema, so the description should ideally say what comes back (table shape, units, columns); it only covers the empty-result case. Everything else an agent needs to call the tool correctly — code sourcing, frequency uniformity, period syntax, alternative for larger requests — is present.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds a genuinely schema-inexpressible cross-parameter constraint: every code in series_codes must share one frequency, which determines the accepted period formats. It also supplies concrete example codes (PD04637PD, PD12301MD) that make the code format unambiguous.

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?

States a specific verb+resource ('Fetch time series data from the BCRP API') and immediately bounds scope to 1–10 series codes of the same frequency. It differentiates itself from siblings by naming bcrp_search_catalog for code lookup, bcrp_describe_series for validation, and bcrp_get_series_long for >10 or mixed-frequency needs.

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?

Gives explicit routing: use this tool for up to 10 same-frequency codes, use bcrp_get_series_long for more than 10 or mixed frequencies, and use bcrp_search_catalog / the catalog resource to find codes. It also states a concrete usage shortcut (leave both periods empty for the most recent data) and clarifies when an empty result is not an error.

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