Skip to main content
Glama

Imf

by io.github.pipeworx-io

Get Data

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.

Input Schema

TableJSON 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

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed11 schema fields changed
    • changedInput schema / examples
      Previous value: -[
-  {
-    "country": "US",
-    "database_id": "IFS",
-    "end": "2023",
-    "frequency": "A",
-    "indicator": "NGDP_XDC",
-    "start": "2018"
-  },
-  {
-    "database_id": "WEO",
-    "end": "2024",
-    "frequency": "A",
-    "indicator": "NGDPD",
-    "start": "2020"
-  }
-]New value: +[
+  {
+    "dataset": "CPI",
+    "dimensions": {
+      "COICOP_1999": "_T",
+      "COUNTRY": "USA",
+      "FREQUENCY": "M",
+      "INDEX_TYPE": "CPI",
+      "TYPE_OF_TRANSFORMATION": "IX"
+    },
+    "end": "2024-04",
+    "start": "2024-01"
+  },
+  {
+    "dataset": "CPI",
+    "dimensions": {
+      "COUNTRY": "USA",
+      "FREQUENCY": "M"
+    },
+    "end": "2024-02",
+    "limit": 20,
+    "start": "2024-01"
+  }
+]
    • removedInput schema / properties / country
      Removed value: -{
-  "description": "ISO 2-letter country code, e.g. \"US\", \"GB\", \"JP\". Omit for all countries.",
-  "type": "string"
-}
    • removedInput schema / properties / database_id
      Removed value: -{
-  "description": "IMF database ID, e.g. \"IFS\", \"BOP\", \"DOT\", \"WEO\"",
-  "type": "string"
-}
    • addedInput schema / properties / dataset
      Added value: +{
+  "description": "Dataset id from get_datasets, e.g. \"CPI\", \"WEO\", \"BOP\", \"IMTS\".",
+  "type": "string"
+}
    • addedInput schema / properties / dimensions
      Added value: +{
+  "additionalProperties": {
+    "oneOf": [
+      {
+        "type": "string"
+      },
+      {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      }
+    ]
+  },
+  "description": "Map 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.",
+  "type": "object"
+}
    • changedInput schema / properties / end / description
      Previous value: -"End period, e.g. \"2023\" or \"2023-Q4\" or \"2023-12\""New value: +"End period, e.g. \"2025\", \"2024-12\", \"2024-Q4\"."
    • removedInput schema / properties / frequency
      Removed value: -{
-  "description": "Data frequency: \"A\" (annual), \"Q\" (quarterly), \"M\" (monthly)",
-  "type": "string"
-}
    • removedInput schema / properties / indicator
      Removed value: -{
-  "description": "Indicator code, e.g. \"NGDP_XDC\" for nominal GDP. Use search_indicators to find codes.",
-  "type": "string"
-}
    • addedInput schema / properties / limit
      Added value: +{
+  "description": "Max series to return, 1-100 (default 20).",
+  "type": "number"
+}
    • changedInput schema / properties / start / description
      Previous value: -"Start period, e.g. \"2018\" or \"2018-Q1\" or \"2018-01\""New value: +"Start period, e.g. \"2020\", \"2024-01\", \"2024-Q1\"."
    • changedInput schema / required
      Previous value: -[
-  "database_id",
-  "frequency",
-  "indicator"
-]New value: +[
+  "dataset"
+]
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the readOnlyHint and openWorldHint annotations, the description discloses that omitted dimensions are left open and return every code, that dimension schemas vary by dataset, and that the return includes {period, value} plus dimension values. These are useful behavioral details not fully captured by annotations.

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

Conciseness5/5

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

Five sentences, front-loaded with the core purpose, then a concrete example, a caveat, a behavioral rule, and the return format. Every sentence earns its place and there is no fluff or redundancy.

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?

Given the rich annotations, a fully described input schema, and an output schema, the description fills remaining gaps: open dimension behavior, dataset-specific schemas, and the return shape. It is complete enough for an agent to invoke correctly, especially with the pointer to search_indicators.

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

Parameters3/5

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

The input schema already provides full descriptions for all 5 parameters (100% coverage), so the baseline is 3. The description adds a concrete example call and a caveat about dataset-specific dimensions, but similar guidance already appears in the schema's dimensions description ('Use search_indicators to discover valid names and codes').

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 opens with 'Fetch an IMF time series', a specific verb and resource, and explains identification via dataset plus a dimensions map. This clearly differentiates it from siblings like get_datasets (list datasets) and search_indicators (discover dimensions).

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?

Explicitly states 'Dimension names and order differ per dataset — use search_indicators to see what a dataset accepts', naming the correct alternative tool for discovery. This gives clear context on when to use get_data versus search_indicators and implies prerequisites.

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

All Imf toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation2/5

Several natural-language query tools (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, validate_claim) have heavily overlapping purposes, and ask_pipeworx_beta currently behaves identically to ask_pipeworx. The five Polymarket tools also have subtle boundaries, though the IMF, memory, and subscription clusters are clearly separated.

Naming Consistency4/5

Most tools follow a clean snake_case verb_noun pattern (get_data, resolve_entity, subscribe, compare_entities). Minor deviations exist: noun-first names like entity_profile and ai_visibility_check, brand-prefixed names like pipeworx_feedback and pipeworx_trending, and ask_pipeworx_beta using a suffix instead of an underscore.

Tool Count2/5

34 tools is well above the range that remains easily navigable, and the count is inflated by many meta-tools, overlapping query entry points, and five distinct Polymarket tools. The server is named Imf, yet it also carries npm dependency scanning, llms.txt generation, AI visibility checks, and prediction-market tooling, making the scope feel unfocused.

Completeness3/5

Subdomain lifecycles are reasonably covered: memory has remember/recall/forget, subscriptions have subscribe/list/unsubscribe/recent_alerts, and data access has discovery, lookup, grounding, and research paths. However, the overall domain is so broad that a complete surface is hard to define, and the IMF-specific portion is thin (only get_data, get_datasets, and search_indicators).

Resources