MCP server for Remnus workspace management, providing tools for reading and writing pages, databases, and workspace data with context-aware preparation and bulk operations
Critical failures across all dimensions. No input schemas are visible in the provided source code. Descriptions exist but are extremely generic (10-50 chars), providing minimal LLM guidance. No parameter descriptions, no output schemas, no error handling patterns. The server appears to be a Next.js web app with MCP endpoints, but the actual tool implementation code is not provided, making verification impossible.
Add a comment to a page or item
Create multiple pages in the workspace
Delete multiple pages in bulk
Move multiple workspace items in bulk
Update multiple pages in bulk
Create a new database in the workspace
Create a new view in a database
No input schemas visible in source code. All 25 tools have schema score of 0. Cannot verify parameter types, constraints, or descriptions.
Tool definitions inferred from React component file (LandingTools.tsx), not from explicit MCP server registration code. Actual tool implementation, handler logic, and schema definitions not provided.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 39 | <=2025-11-25 | v2 |
Create a new page in the workspace
Delete a database view
Delete a page from the workspace
Get changes to workspace items since a given timestamp
Get the schema of a database
Get a single page by ID
Get multiple pages by ID
Get pages related to a given page
List workspace members
List all items in the workspace
Move a workspace item to a different location
Prepares context for an agent task by selecting relevant workspace items within a token budget and applying access policies
Query the workspace audit log
Query a database with filters and sorting
Search for items in the workspace
Update the schema of a database
Update an existing database view
Update an existing page
Descriptions are extremely generic and under 20 characters for most tools (e.g., 'Search for items in the workspace', 'List all items in the workspace'). No guidance on WHEN to use each tool or what it returns.
No parameter descriptions visible. 'prepare_context' has parameters 'task', 'budget', 'policy' with no descriptions explaining what values are valid, what format is expected, or what happens if omitted.
No output schemas documented. LLMs cannot plan downstream tool calls or extract required fields (e.g., page_id, database_id) from responses. Breaks tool composition patterns.