data-aggregator-mcp

Overview Schema Source Related Servers Discussions Admin

fetch

Download selected resource files to local disk, verify checksums where published, and return file paths for analysis.

Instructions

Download a resource's files to local disk and return the PATHS (never the file contents). 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. Fetchable backends: Zenodo (md5-verified); SRA via ENA FASTQ (md5-verified); GEO supplementary files (unverified); DataCite sub-repos — Figshare/Dataverse/OSF (md5-verified), OpenNeuro (snapshot manifest, unverified), Dryad is manifest-only (resolve lists files, fetch fails loud), Mendeley + other DataCite repos fail loud; PubMed/OpenAIRE open-access full text (EuropePMC XML / Unpaywall PDF, unverified); HuggingFace Hub (unverified); DataONE Member-Node objects (md5/SHA-256-verified); OmicsDI — PRIDE (unverified) + MetaboLights (sha-256-verified) only, MassIVE/jPOST/iProX/PeptideAtlas/Panorama Public/GNPS/Metabolomics Workbench fail loud; DANDI dandisets (302→S3, sha-256-verified); CZ CELLxGENE H5AD/RDS assets (unverified); OpenML ARFF (md5-verified); RCSB PDB .cif/.pdb structure files (unverified); UniProtKB FASTA (unverified); BioStudies study files (unverified); GBIF Darwin Core Archives (unverified); data.gov dataset distributions (unverified). Fails loud if selected files exceed max_bytes unless force=true. Verifies md5/SHA-256 where the source publishes one; files marked unverified get no integrity check. Writes a .dataresource.json sidecar.

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": {
      "id": "<id>"
    },
    "name": "fetch"
  }
}

Input Schema

Name	Required	Description
`id`	Yes	Source-prefixed id or bare Zenodo id
`dest`	No	Destination dir (default managed cache)
`files`	No	Glob over file names (default all)
`force`	No	Override max_bytes
`extract`	No	Unpack downloaded zip/tar archives into the destination (default false). Path-traversal-guarded; counts against max_bytes.
`max_bytes`	No	Byte ceiling before failing loud

Output Schema

Name	Required	Description	Default
`bytes`	No
`paths`	No
`resumed`	No
`skipped`	No
`unverified`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.54.1Sep 30, 2026
- addedInput schema / additionalProperties
```
Added value: +false
```

Changed1 schema field changedv0.45.3Jul 29, 2026

addedOutput schema / properties / unverified

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "title": "Unverified",
+  "type": "array"
+}

Changed1 schema field changedv0.16.0May 31, 2026

addedOutput schema / properties / resumed

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "title": "Resumed",
+  "type": "array"
+}

First observedv0.11.0May 30, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Goes well beyond the annotations: discloses integrity verification per source (md5/SHA-256 vs unverified), that it fails loud when max_bytes is exceeded unless force=true, that extract is path-traversal-guarded and counts against max_bytes, that it writes a .dataresource.json sidecar, and that it returns paths rather than contents. Annotations only say readOnly=false and non-idempotent, so this added context is substantial.

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 opening sentences are well front-loaded with the core behavior and return-value contract. However, the backend enumeration is a very long run-on sentence dense with provider names and verification status; it earns its content but is hard to scan and would read better as a structured list.

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 an output schema exists, return values need not be explained, yet the description still clarifies that paths (not contents) are returned. It covers failure modes, integrity guarantees, side effects (sidecar file), and per-source support, which is complete for a 6-parameter download tool.

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 description coverage is 100%, so the baseline is 3, but the description adds cross-parameter meaning: force exists specifically to override max_bytes, and extract counts against the byte ceiling. This interaction between force/max_bytes/extract is not obvious from the schema fields alone.

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 ('Download a resource's files to local disk') and explicitly scopes the return value ('return the PATHS (never the file contents)'). This clearly distinguishes it from siblings like resolve and search, which are about discovery rather than retrieval.

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?

Usage is strongly implied by the per-backend breakdown of what is fetchable, md5-verified, manifest-only, or fails loud, plus the note that Dryad is 'manifest-only (resolve lists files, fetch fails loud)' which routes the agent to resolve first in that case. It lacks an explicit 'use fetch when X, use resolve when Y' statement for other scenarios, so it stops short of 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