Skip to main content
Glama
Nextcloud MCP Server

Nextcloud MCP Server

by stack74

Nextcloud unified search

nextcloud_unified_search
Read-onlyIdempotent

Search across all installed Nextcloud apps at once—files, calendar, contacts, Talk, Deck, notes, and mail—and narrow results by provider to find what you need.

Instructions

Nextcloud's own search box: one term across the installed apps — file names, and depending on the server also calendar events, contacts, Talk messages, Deck cards, notes, mail, and file CONTENTS when the full-text search app is installed (provider 'fulltextsearch').

Without 'providers' all apps are searched and the result lists the provider IDs; pass 'providers' (e.g. ['files']) to narrow a follow-up search.

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": {
      "term": "<term>"
    },
    "name": "nextcloud_unified_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
termYesSearch term.
limitNoResults per provider (default 5).
providersNoProvider IDs to search, e.g. ['files', 'calendar']. Default: all.
response_formatNo'markdown' for readable output, 'json' for structured datamarkdown

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.2

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: coverage depends on which apps the server has installed, content search only works with the fulltextsearch app, and the response enumerates provider IDs when no filter is given. It does not mention permissions or result ordering, but the server-variance disclosure is the important non-obvious trait.

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?

Two short paragraphs, front-loaded with the capability and then the provider workflow; nothing is redundant with the schema. The long mid-sentence app enumeration is somewhat dense but each item carries information about coverage.

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?

With no output schema, the description usefully indicates that results are grouped and labeled by provider ID. Combined with the server-dependence caveat and the schema's own limit/response_format docs, an agent has enough to call this correctly; only permissions behavior and result ordering are left unaddressed.

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 100%, so the baseline is 3, but the description goes further by explaining the semantics of omitting 'providers' (all apps searched, provider IDs returned) and why the parameter exists (to narrow a follow-up search). That functional explanation of the 'providers' array adds meaning the enum-less schema description does not convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Nextcloud's own search box: one term across the installed apps') and enumerates what is covered: file names, calendar events, contacts, Talk, Deck, notes, mail, and contents when the fulltextsearch app is present. It distinguishes itself reasonably from the file-specific siblings by naming the 'files' provider example, though it never explicitly says 'use nextcloud_search_files for filename-only lookups'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear operating context: omitting 'providers' searches everything and returns the provider list, while passing 'providers' narrows a follow-up search. That is genuinely useful two-step guidance. It stops short of saying when to prefer this over the dedicated siblings like nextcloud_search_files or nextcloud_search_file_contents, so the agent must infer the boundary.

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