A comprehensive MCP server that provides Claude with private journaling, semantic search, resources, and guided prompts for reflection and learning
Server has 4 tools with complete input schemas and descriptions. Naming follows verb_noun convention (process_thoughts, search_journal, read_journal_entry, list_recent_entries). Descriptions are detailed and context-rich (150-300 chars), exceeding baseline averages. However, output schemas are not documented, LLMs cannot predict response structure for downstream chaining. Parameter descriptions are thorough but lack explicit constraints (e.g., no min/max for 'limit' or 'days'). Error handling is absent from tool definitions. No tool annotations (readOnlyHint/destructiveHint) despite clear risk profiles (process_thoughts is WRITE, others are READ_ONLY). Missing recovery guidance in descriptions.
Get recent journal entries in chronological order.
Your PRIVATE JOURNAL for learning and reflection. Write to any combination of these completely private spaces. Nobody but you will ever see this. Use it to clarify your thoughts and feelings and to record observations.
Read the full content of a specific journal entry by file path.
Search through your private journal entries using natural language queries. Returns semantically similar entries ranked by relevance.
Output schemas not documented. LLMs cannot predict response structure (fields, types, pagination) for process_thoughts, search_journal, read_journal_entry, or list_recent_entries. Breaks tool chaining and forces agents to guess field names.
No tool annotations (readOnlyHint/destructiveHint/idempotentHint). process_thoughts is destructive (WRITE), search_journal/read_journal_entry/list_recent_entries are read-only, but this is not declared in tool metadata. Agents cannot reason about safety or retry semantics.
Numeric parameters lack explicit bounds. 'limit' and 'days' have defaults but no min/max constraints. LLMs may pass absurd values (limit=999999, days=36500) causing performance issues or API timeouts.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 61 | 2026-07-28+ | v2 |
No error handling guidance in tool descriptions. If search_journal finds no results, or read_journal_entry receives an invalid path, descriptions do not explain what to do next. Agents lack recovery paths.
Enum constraint for search_journal 'type' parameter is present (project|user|both) but 'sections' array lacks enum definition. LLMs may pass invalid section names; should enumerate valid options (feelings, project_notes, user_context, technical_insights, world_knowledge).