Skip to main content
Glama
Nextcloud MCP Server

Nextcloud MCP Server

by stack74

Download file

nextcloud_download_file
Read-onlyIdempotent

Download a file from Nextcloud and stream it directly to a local path, so large files save without loading into the conversation. Returns the saved path and size.

Instructions

Download a file from Nextcloud.

The file is streamed to 'output_path' on this computer; its content is NOT loaded into the conversation, so this works for large files. Returns the saved path and size.

To just read a document's text, nextcloud_read_file is the better choice.

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": {
      "path": "<path>",
      "output_path": "<output_path>"
    },
    "name": "nextcloud_download_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesFile path, relative to the user's Nextcloud root, e.g. '/Documents/Offers/offer-4711.pdf'
output_pathYesAbsolute local path to save to, e.g. '/Users/me/Downloads/report.pdf'. If it is an existing folder, the file keeps its Nextcloud name inside it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.2

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false for the remote side, but the description adds the crucial local-side behavior: content is streamed to disk and NOT loaded into the conversation, which is why it handles large files. It also states the return shape (saved path and size). The only gap is silence on overwrite semantics when output_path is an existing file rather than a folder.

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

Conciseness5/5

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

Four short sentences, front-loaded with the core action, then mechanism, then return value, then alternative. Every sentence carries distinct information with no repetition of the title.

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?

For a two-parameter download tool with no output schema, the description covers what it does, where the bytes go, why it suits large files, what it returns, and which sibling to prefer for text reading. Nothing an agent needs to invoke it correctly 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 coverage is 100%, and the schema itself documents both path and output_path with examples and the existing-folder rule. The description reinforces that output_path is where content lands but adds no syntax or edge-case detail beyond the schema, so the 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 states a specific verb and resource ('Download a file from Nextcloud') and immediately clarifies the mechanism ('streamed to output_path on this computer'). It is plainly distinguishable from the sibling nextcloud_read_file, which it names explicitly.

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 an explicit routing rule: to just read a document's text, use nextcloud_read_file instead. That is a concrete when-not condition paired with a named alternative, plus an implied when-to-use for large files that shouldn't enter the conversation.

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