Loading ToolBench
MCP server for accessing FilamentPHP v5.x documentation - enables AI agents to search, browse, and read FilamentPHP docs, component references, and code examples
Server provides 5 read-only tools with consistent naming (verb_noun pattern: list_, search_, get_) and reasonable descriptions (100-200 chars). All tools have input schemas with type definitions and parameter descriptions. However, output schemas are not documented in the source code, and error handling guidance is absent. Parameter descriptions lack format constraints and validation rules. No tool annotations (readOnlyHint) despite all being read-only. Descriptions are functional but generic, they lack dependency hints and discovery guidance that would optimize LLM tool selection.
Health check for the FilamentPHP MCP server. Returns server status, version, and index statistics.
Read the full content of a specific documentation file by its relative path. Use list_docs_in_section to find available paths. Returns the complete pre-processed markdown content.
List all documentation files within a specific section. Use list_docs_sections first to get the section IDs.
List all documentation sections with their IDs, names, and file counts. Use this to discover what documentation is available before searching or reading specific docs.
Search the full FilamentPHP documentation using keyword search. Returns ranked results with relevant snippets and source file paths. Great for finding specific components, configuration options, code examples, or explanations.
Output schemas not documented. Tool descriptions state what is returned (e.g., 'Returns ranked results with relevant snippets') but do not specify the JSON structure, field types, or pagination details. LLMs cannot plan downstream calls or extract data reliably without knowing response shape.
No tool annotations despite all tools being read-only. Missing readOnlyHint in tool definitions. This prevents clients from optimizing caching, retry logic, and safety checks for idempotent operations.
Parameter descriptions lack format constraints and validation rules. 'sectionId' description mentions examples but does not specify the format pattern (e.g., '\d{2}-[a-z-]+') or character restrictions. 'limit' parameter lacks min/max bounds. LLMs cannot self-validate inputs without explicit constraints.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 54 | 2026-07-28+ | v2 |
No error handling guidance. Tool descriptions do not explain what happens on invalid input (e.g., non-existent sectionId, malformed path). No recovery hints like 'Call list_docs_sections first to validate the ID.' Agents cannot self-correct on failures.
STDIO transport only. Server is not remotely accessible and cannot be used by hosted MCP clients. This is a hard architectural limitation, not a code quality issue, but it severely restricts deployment scenarios.