Skip to main content
Glama

IMF (Unofficial)

Imf Get Data

imf_get_data
Read-onlyIdempotent

Fetch an IMF time series. Identify the series by dataset plus a dimensions map of named codes, e.g. get_data({dataset:"CPI", dimensions:{COUNTRY:"USA", INDEX_TYPE:"CPI", COICOP_1999:"_T", TYPE_OF_TRANSFORMATION:"IX", FREQUENCY:"M"}, start:"2024-01"}). Dimension names and order differ per dataset, use search_indicators to see what a dataset accepts. Any dimension you omit is left open, returning every code for it. Returns observations as {period, value} plus the dimension values of each series.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "end": "2024-04",
      "start": "2024-01",
      "dataset": "CPI",
      "dimensions": {
        "COUNTRY": "USA",
        "FREQUENCY": "M",
        "INDEX_TYPE": "CPI",
        "COICOP_1999": "_T",
        "TYPE_OF_TRANSFORMATION": "IX"
      }
    },
    "name": "imf_get_data"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoEnd period, e.g. "2025", "2024-12", "2024-Q4".
limitNoMax series to return, 1-100 (default 20).
startNoStart period, e.g. "2020", "2024-01", "2024-Q1".
datasetYesDataset id from get_datasets, e.g. "CPI", "WEO", "BOP", "IMTS".
dimensionsNoMap of dimension code to value, e.g. {"COUNTRY":"USA","FREQUENCY":"M"}. A value may be a list to OR codes together: {"COUNTRY":["USA","GBR"]}. Omitted dimensions match everything. Use search_indicators to discover valid names and codes.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so safety is covered. The description adds genuinely useful behavior beyond that: the per-dataset variability of dimension names and order, the fan-out effect of omitted dimensions, and the return shape ({period, value} plus each series' dimension values).

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 the core action, then the addressing model, then the caveat, then the return shape — a sensible information order. The inline example is long but earns its place by demonstrating the nested dimensions map; minor repetition of the omitted-dimension rule already present in the schema.

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

Completeness5/5

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

For a 5-parameter tool with a nested map, full schema coverage and an output schema, this description covers everything an agent needs: how to address a series, where to discover valid codes, how omissions behave, and what comes back. Nothing material is missing.

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. The description adds meaning beyond the schema by showing a fully populated `dimensions` map with real dimension codes and by warning that names and order differ per dataset — context the schema's generic example cannot convey.

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 and resource ('Fetch an IMF time series') and immediately specifies the addressing model: dataset id plus a `dimensions` map of named codes. The concrete CPI example makes the call shape unambiguous, so an agent can distinguish this from discovery siblings like get_datasets and search_indicators.

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

Usage Guidelines4/5

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

Explicitly routes the agent to search_indicators for valid dimension names and codes, and explains the omission semantics ('Any dimension you omit is left open, returning every code for it'). It does not state when to prefer a different retrieval path or warn about result-size blowups, but the discovery prerequisite is clearly covered.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.