AI Web Research & Research Brief Agent

Get dataset items

get-dataset-items

Read-onlyIdempotent

Get items (rows) from a dataset — the output/results produced by an Actor run. Returns the rows themselves, not dataset metadata, counts, or a schema. When the user provides a datasetId and asks to retrieve results, output, data, or rows, call this tool directly. Default limit is 20. Use clean=true to skip empty items and hidden fields.

USAGE:

Use when you need to read data from a dataset (all items or only selected fields).

USAGE EXAMPLES:

user_input: Retrieve results from dataset abc123
user_input: Get only metadata.url and title from dataset username~my-dataset

This tool requires an x402 payment. Include a valid x402 payment signature in the request metadata (_meta["x402/payment"]). Your MCP client must support the x402 payment protocol.

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": {
      "datasetId": "<datasetId>"
    },
    "name": "get-dataset-items"
  }
}

Input Schema

Name	Required	Description
`desc`	No	If true, results are returned in reverse order (newest to oldest).
`omit`	No	Comma-separated list of fields to exclude from results.
`clean`	No	If true, returns only non-empty items and skips hidden fields (starting with #). Shortcut for skipHidden=true and skipEmpty=true.
`limit`	No	Maximum number of items to return. Default is 20.
`fields`	No	Comma-separated list of fields to include in results. Fields in output are sorted as specified. Use dot notation for nested objects (e.g. "metadata.url"); the server auto-flattens parent prefixes and returns flat keys, unless the parent itself is listed (e.g. "metadata,metadata.url" returns metadata whole). A dotted path to or through an array (e.g. "results.url") returns nothing: select its top-level field (e.g. "results") for every element. Items that have none of the requested fields come back as {}, or are dropped when clean=true.
`offset`	No	Number of items to skip at the start. Default is 0.
`flatten`	No	Comma-separated list of fields to flatten (e.g. flatten="metadata" turns {"metadata":{"url":"x"}} into {"metadata.url":"x"}). Normally derived automatically from dot-notation in `fields`; specify only as a diagnostic override.
`datasetId`	Yes	Dataset ID, name (resolved against your own datasets), or full name as username~name.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 10, 2026

changedInput schema / properties / fields / description

Previous value: -"Comma-separated list of fields to include in results. Fields in output are sorted as specified. Use dot notation for nested objects (e.g. \"metadata.url\"); the server auto-flattens parent prefixes."New value: +"Comma-separated list of fields to include in results.\nFields in output are sorted as specified.\nUse dot notation for nested objects (e.g. \"metadata.url\"); the server auto-flattens parent prefixes and returns flat keys, unless the parent itself is listed (e.g. \"metadata,metadata.url\" returns metadata whole).\nA dotted path to or through an array (e.g. \"results.url\") returns nothing: select its top-level field (e.g. \"results\") for every element.\nItems that have none of the requested fields come back as {}, or are dropped when clean=true."

changedInput schema / properties / flatten / description

Previous value: -"Comma-separated list of fields to flatten (e.g. flatten=\"metadata\" turns {\"metadata\":{\"url\":\"x\"}} into {\"metadata.url\":\"x\"}). Normally derived automatically from dot-notation in `fields`; specify only as a diagnostic override."New value: +"Comma-separated list of fields to flatten (e.g. flatten=\"metadata\" turns {\"metadata\":{\"url\":\"x\"}} into {\"metadata.url\":\"x\"}).\nNormally derived automatically from dot-notation in `fields`; specify only as a diagnostic override."

Changed1 schema field changedOct 30, 2026

changedInput schema / properties / datasetId / description

Previous value: -"Dataset ID or username~dataset-name."New value: +"Dataset ID, name (resolved against your own datasets), or full name as username~name."

First observedSep 30, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuine non-annotation context: the default limit of 20, the semantics of clean=true, and — most importantly — that the call requires an x402 payment signature in _meta["x402/payment"], which an agent cannot infer from the schema.

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 distinction in the first two sentences, then usage, then examples, then the payment caveat. Slight redundancy: 'Default limit is 20' duplicates the schema, and the USAGE block largely echoes the preceding paragraph.

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?

For an 8-parameter read tool with a fully documented schema and an output schema, the description covers the essential unknowns — what is returned vs. not returned, default page size, and the payment gate. Nothing critical is missing, though pagination semantics across offset/limit are left entirely to the schema.

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% and the parameter docs are unusually detailed (fields dot-notation, flatten override, clean shortcut), so the baseline is 3. The description only restates the limit default and clean behavior already documented in the schema, adding no new parameter meaning.

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 ('Get items (rows) from a dataset') and immediately delimits the scope: the output/results of an Actor run, not dataset metadata, counts, or a schema. An agent can distinguish this from the sibling run/store tools without opening any schema.

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?

Gives an explicit trigger condition ('When the user provides a datasetId and asks to retrieve results, output, data, or rows, call this tool directly') plus a USAGE line and two concrete input examples. It never names a when-not case or an alternative sibling, so it stops short of a full routing rule.

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

All AI Web Research & Research Brief Agent tools Inspect

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.