Skip to main content
Glama

Opendosm My

by io.github.pipeworx-io

Opendosm Get Dataset

opendosm_get_dataset
Read-onlyIdempotent

Fetch records from an official Malaysian statistics dataset (data.gov.my / OpenDOSM, Dept of Statistics Malaysia). Keyless, authoritative. The dataset id is REQUIRED — there is no listing endpoint, so use opendosm_list_datasets or opendosm_dataset_meta to discover ids and their columns. Verified high-value ids: cpi_headline (Headline Consumer Price Index, monthly (1980–present).); cpi_core (Core CPI (excludes volatile items), monthly.); gdp_qtr_real (Real GDP, quarterly (constant 2015 prices).); economic_indicators (Leading / coincident / lagging economic indicator indices, monthly.); ipi (Industrial Production Index, monthly (seasonally adjusted + absolute).); lfs_month (Labour force survey, monthly: unemployment rate, participation rate, employment.); fuelprice (Weekly retail fuel prices (RON95, RON97, diesel) in MYR per litre.); hh_income (Household income: mean and median (MYR), by survey year.); population_malaysia (Malaysia population by age / sex / ethnicity (thousands), annual.); population_state (Population by state, age, sex, ethnicity (thousands).); births (Live births by state and date.); deaths (Deaths: absolute count and crude rate, annual.). Filter syntax is value@column (e.g. filter="overall@division" keeps only rows where division=overall). Range syntax is column[start:end] on NUMERIC columns only, either bound optional (e.g. range="index[130:140]", range="index[135:]"). Date ranges are NOT supported by range; instead use sort="-date" with limit to get the most recent rows. sort="-col" is descending, sort="col" ascending.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesDataset id, e.g. "cpi_headline", "lfs_month", "fuelprice". Required.
sortNoSort column; prefix "-" for descending, e.g. "-date" for newest first.
limitNoMax records to return. Omit for full series (can be large).
rangeNoNumeric range, format column[start:end] (bounds optional), e.g. "index[130:140]". Numeric columns only — not dates.
filterNoExact-match filter, format value@column, e.g. "overall@division".

Schema Changelog

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

  1. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "id": "cpi_headline",
+    "limit": 12,
+    "sort": "-date"
+  },
+  {
+    "filter": "overall@division",
+    "id": "lfs_month",
+    "range": "index[130:140]"
+  }
+]
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds that it's keyless and authoritative, and importantly clarifies that date ranges are not supported by 'range' but by sort with limit. No contradictions.

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?

Well-structured with core purpose first, then parameter details, then examples. Every sentence adds value, though slightly lengthy. Could be trimmed slightly but remains clear and informative.

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 no output schema, description covers all necessary context: how to discover dataset IDs, parameter usage with examples, limitations (date ranges), and list of high-value IDs. Fully adequate for agent invocation.

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

Parameters5/5

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

With 100% schema coverage, description adds significant value: explains filter syntax (value@column), range syntax (column[start:end]), and sort prefix for descending. Provides examples and boundary details, far beyond schema descriptions.

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 it fetches records from Malaysian statistics datasets, specifies keyless authoritative source, and distinguishes from siblings by noting no listing endpoint and recommending opendosm_list_datasets or opendosm_dataset_meta for ID discovery. It also lists high-value dataset IDs.

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 requires dataset ID, provides examples of filter and range syntax, explains that date ranges are not supported by range and suggests using sort and limit instead. Gives clear guidance on when to use sibling tools for ID discovery.

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

All Opendosm My 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

A4.1/5.0
Disambiguation3/5

The set includes three nearly-identical ask_pipeworx variants (base, beta, grounded) that differ only subtly, and deep_research overlaps with ask_pipeworx for multi-part queries. Several company/prediction tools also share adjacent purposes (entity_profile vs recent_changes vs compare_entities; polymarket_arbitrage vs polymarket_edges), though detailed descriptions help. Overall, an agent could mis-select between these overlapping tools.

Naming Consistency4/5

Most tools follow a verb_noun or consistent prefix pattern (opendosm_*, polymarket_*), and the ask_pipeworx family is internally consistent. However, a few are noun phrases (entity_profile, ai_visibility_check, recent_alerts) and some verbs aren't uniform (list_datasets vs dataset_meta vs get_dataset). The mixture is readable but not fully consistent.

Tool Count2/5

34 tools is well above the typical focused server range and includes a clearly redundant experimental variant (ask_pipeworx_beta) plus many loosely-related utility functions (memory, subscriptions, dependency scanning, llms.txt generation). While the broad scope justifies some size, the count feels excessive for the 'Opendosm My' name, which suggests a narrower Malaysian-statistics focus.

Completeness4/5

For the apparent overarching goal of a multi-domain research/query platform, the surface is quite complete: data lookup, deep research, entity comparison, claim verification, prediction-market analysis, memory, and subscriptions are all covered. The Malaysian OpenDOSM component itself has list/meta/get lifecycle. Minor gaps (e.g., no direct dataset search beyond curated lists, no way to execute arbitrary Pipeworx tools directly) are workable.

Resources