Skip to main content
Glama
musharna

data-aggregator-mcp

by musharna
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

operate

Read-only

Inspect, preview, or run read-only SQL queries on remote Parquet/CSV/TSV files without downloading them, including schema, sample rows, column profiles, and SELECT results.

Instructions

Inspect or query a remote tabular file (Parquet/CSV/TSV) WITHOUT downloading it. op='schema' returns columns+types; 'preview' a small sample; 'head' the first n rows; 'sql' a read-only SELECT against the file (exposed as the view 'data', e.g. "SELECT * FROM data WHERE x > 1"). op='peek' profiles every column WITHOUT downloading — type, null-rate, approximate distinct count, min/max, and numeric quartiles (a DuckDB SUMMARIZE; like head/sql it reads the whole file, so it honors the source-size ceiling). Tool names in this text are this server's own; your client may list them with a prefix (in Claude Code, mcp__data-aggregator__resolve): call the name it lists. Addresses a file by catalog id + file name (resolve the id first to see files[] and access_modes). Requires the [operate] extra; fails loud if the file is not an operable tabular file.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nNoRow count for head/preview
idYesDataResource id (e.g. 'zenodo:1254563')
opYes
fileNoFile name within the record; optional when exactly one operable file is present.
queryNoRead-only SELECT for op='sql'.
columnsNoOptional column projection for head.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.75.3
    • changedInput schema / properties / id / description
      Previous value: -"DataResource id (e.g. 'zenodo:7654321')"New value: +"DataResource id (e.g. 'zenodo:1254563')"
  2. Changed1 schema field changedv0.54.1
    • addedInput schema / additionalProperties
      Added value: +false
  3. Changed1 schema field changedv0.46.0
    • addedInput schema / properties / n / minimum
      Added value: +1
  4. Changed1 schema field changedv0.40.0
    • changedInput schema / properties / op / enum
      Previous value: -[
-  "schema",
-  "preview",
-  "head",
-  "sql"
-]New value: +[
+  "schema",
+  "preview",
+  "head",
+  "sql",
+  "peek"
+]
  5. Addedv0.20.0

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the readOnlyHint annotation: it discloses that no download occurs, that 'sql' is read-only, that head/sql/peek read the whole file and therefore honor a source-size ceiling, and that peek is a DuckDB SUMMARIZE. These are non-obvious cost and side-effect traits an agent needs before choosing an op.

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 promise, then a dense op-by-op breakdown where each clause adds information. However, the aside about tool-name prefixes ('in Claude Code, mcp__data-aggregator__resolve') is client-specific noise that doesn't help invoke this tool and slightly dilutes the signal.

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?

Six parameters with mostly documented schema and no output schema, and the description sketches what each op returns (columns+types, sample rows, first n rows, column profile). Adequate for correct invocation; the main residual gap is not clarifying the exact shape/serialization of results or how 'preview' differs from 'head' beyond row count.

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 83%, so the baseline is 3, but the description earns more by explaining the semantics of each enum value (schema/preview/head/sql/peek) and by giving a concrete SQL example against the view 'data'. The id-plus-file addressing model is also spelled out. It doesn't clarify the 'columns' projection or 'n' defaults, which the schema already covers.

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 ('Inspect or query a remote tabular file (Parquet/CSV/TSV)') and immediately clarifies scope with 'WITHOUT downloading it', which contrastively separates it from the fetch sibling. It then enumerates every op value, so an agent knows exactly what the tool covers without opening the 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 clear context: address files by catalog id + file name, and 'resolve the id first to see files[] and access_modes'. It also states the prerequisite ('Requires the [operate] extra') and the failure mode ('fails loud if the file is not an operable tabular file'). It does not explicitly name when to use fetch or search instead, so a 4 rather than a 5.

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

Deploy Server

Other Tools