Skip to main content
Glama
Sign In

DataPulse

by io.github.r3dz4r
OverviewDiscussionsAdmin

Find Malaysian Public Data

search_datasets
Read-onlyIdempotent

Use for discovery only: find DataPulse's 447 Malaysian public datasets by topic, source, or licence—for example, 'Malaysian public data inflation', licence and attribution, or a government dataset source. Returns ranked matches with id, title, source, licence, published status, and score. This is not trust verification: a status is published pipeline context, not proof that a dataset is current or reliable. For pre-trust use search_datasets → verify_dataset → get_provenance. Use it to discover candidates; do not use it for a trust decision—use verify_dataset instead. It reads published catalogue data, so no match means the published catalogue has no matching entry; DataPulse is read-only, requires no API key, and the edge limits clients to roughly one request per second with a small burst, so pace or retry.

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": {
      "query": "<query>"
    },
    "name": "search_datasets"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum highest-ranked discovery matches to return, e.g. 10; omitted defaults to 10 and does not change ranking.
queryYesTopic or task phrasing used to rank discovery candidates, e.g. 'Malaysian public data inflation'; use a returned id with get_dataset.
sourceNoOptional publisher/source substring filter applied before ranking, e.g. 'OpenDOSM'; omit it to search every source.
licenceNoOptional exact licence name or supported alias applied before ranking, e.g. 'CC BY 4.0'; omit it to search every licence.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / licence / description
      Previous value: -"Optional exact licence name or supported alias for reuse discovery, e.g. 'CC BY 4.0'; this does not verify attribution compliance."New value: +"Optional exact licence name or supported alias applied before ranking, e.g. 'CC BY 4.0'; omit it to search every licence."
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum discovery matches to return; integer from 1 to 50, e.g. 10."New value: +"Maximum highest-ranked discovery matches to return, e.g. 10; omitted defaults to 10 and does not change ranking."
    • changedInput schema / properties / query / description
      Previous value: -"Topic or task phrasing for Malaysian public-data discovery only, e.g. 'Malaysian public data inflation'; verify a result separately."New value: +"Topic or task phrasing used to rank discovery candidates, e.g. 'Malaysian public data inflation'; use a returned id with get_dataset."
    • changedInput schema / properties / source / description
      Previous value: -"Optional case-insensitive publisher/source filter, e.g. 'OpenDOSM'."New value: +"Optional publisher/source substring filter applied before ranking, e.g. 'OpenDOSM'; omit it to search every source."
  2. Changed5 schema fields changed
    • changedInput schema / properties / licence / description
      Previous value: -"Optional exact licence name or supported alias, e.g. 'CC BY 4.0'."New value: +"Optional exact licence name or supported alias for reuse discovery, e.g. 'CC BY 4.0'; this does not verify attribution compliance."
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum ranked matches to return; integer from 1 to 50, e.g. 10."New value: +"Maximum discovery matches to return; integer from 1 to 50, e.g. 10."
    • changedInput schema / properties / query / description
      Previous value: -"Free-text search terms; natural language is allowed, e.g. 'inflation cpi'."New value: +"Topic or task phrasing for Malaysian public-data discovery only, e.g. 'Malaysian public data inflation'; verify a result separately."
    • changedInput schema / properties / query / examples
      Previous value: -[
-  "inflation cpi"
-]New value: +[
+  "Malaysian public data inflation"
+]
    • changedInput schema / properties / source / description
      Previous value: -"Optional case-insensitive source-name substring, e.g. 'OpenDOSM'."New value: +"Optional case-insensitive publisher/source filter, e.g. 'OpenDOSM'."
  3. Changed3 schema fields changed
    • addedInput schema / properties / licence / examples
      Added value: +[
+  "CC BY 4.0",
+  "Open Government Licence (Malaysia)"
+]
    • addedInput schema / properties / query / examples
      Added value: +[
+  "inflation cpi"
+]
    • addedInput schema / properties / source / examples
      Added value: +[
+  "OpenDOSM",
+  "data.gov.my",
+  "MET Malaysia"
+]
  4. Changed4 schema fields changed
    • addedInput schema / properties / licence / description
      Added value: +"Optional exact licence name or supported alias, e.g. 'CC BY 4.0'."
    • addedInput schema / properties / limit / description
      Added value: +"Maximum ranked matches to return; integer from 1 to 50, e.g. 10."
    • addedInput schema / properties / query / description
      Added value: +"Free-text search terms; natural language is allowed, e.g. 'inflation cpi'."
    • addedInput schema / properties / source / description
      Added value: +"Optional case-insensitive source-name substring, e.g. 'OpenDOSM'."
  5. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the readOnly/idempotent/destructive annotations, it discloses what the annotations cannot: no API key required, an edge rate limit of roughly one request per second with small burst, and the semantic caveat that a 'published' status is pipeline context rather than proof of currency. It also explains that an empty result means the published catalogue genuinely has no match, which prevents false-negative reasoning.

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

Conciseness3/5

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

The discovery framing and rate limit are front-loaded and useful, but the trust caveat is restated three times ('This is not trust verification,' 'do not use it for a trust decision,' 'not proof that a dataset is current or reliable'). The overlap between the second and third sentences could be compressed into one.

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?

The tool has an output schema and full annotation coverage, and the description fills the remaining gaps an agent needs: when to call it, what the ranking means, what an empty result implies, and how to chain into verification. Nothing necessary for correct invocation is missing.

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?

Schema description coverage is 100%, so query, source, licence, and limit are already fully documented, including substring-versus-exact matching and pre-ranking filter order. The description adds only the framing that results are ranked matches over those filters, which is marginal value on top of the schema; baseline 3 applies.

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 a specific verb and scope: 'Use for discovery only: find DataPulse's 447 Malaysian public datasets by topic, source, or licence,' and immediately names the resource inventory (447 datasets) plus the dimensions searched. It also explicitly distinguishes itself from the sibling verify_dataset, so an agent can route without opening either schema.

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?

It gives the positive case ('Use it to discover candidates'), the negative case ('do not use it for a trust decision—use verify_dataset instead'), and the intended sequence ('search_datasets → verify_dataset → get_provenance'). Alternatives and the condition that selects them are stated outright rather than inferred.

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

All DataPulse toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources