Model Context Protocol (MCP) server for Nextcloud integration - enables AI assistants to interact with Nextcloud data
Server has only 2 tools, both authentication-focused. Tool naming follows verb_noun pattern (nc_auth_provision_access, nc_auth_check_status), which is good. However, descriptions are minimal (under 150 chars each), and critically, NO input schemas are visible in the provided source code. The first tool accepts a 'scopes' parameter (array of strings) but the schema definition is not shown. The second tool has empty input ({}). Without visible schema definitions, parameter types, and constraints, LLMs cannot validate inputs or understand what values are acceptable. Descriptions exist but lack actionable detail about prerequisites, return values, or error conditions. No output schemas documented. Risk annotations present (WRITE, READ_ONLY) but insufficient for production use.
Check if Nextcloud access has been provisioned. If a Login Flow is pending, this will poll for completion. Recommended polling interval: 5 seconds.
Start Nextcloud Login Flow v2 to obtain an app password. This is required before using any Nextcloud tools. You will be given a URL to open in your browser to log in.
No input schemas visible for either tool. Tool 1 accepts 'scopes' array but schema definition not shown in source. Tool 2 has empty input. Without JSON Schema definitions, LLMs cannot validate parameter types, enums, or constraints.
No output schemas documented. Descriptions do not specify what fields are returned, their types, or structure. LLMs cannot plan downstream tool calls or extract required data.
Descriptions lack actionable detail. Tool 1 says 'You will be given a URL' but does not explain the response structure, polling behavior, or error cases. Tool 2 mentions '5 second polling interval' but does not document what status values are possible or what to do on timeout.
Inferred effective spec: 2026-07-28+.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 50 | 2026-07-28+ | v2 |
No error handling guidance. Descriptions do not explain what errors can occur (invalid scopes, network failure, timeout) or how the LLM should recover. No recovery hints provided.
Tool 1 description mentions 'scopes' parameter but does not document valid scope values, format, or what happens if invalid scopes are requested. LLMs will hallucinate scope names.