agentic-diaries-mcp
Related Servers
Alternatives to agentic-diaries-mcp
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityAmaintenanceLocal-first observability for AI agent stacks. Provides MCP tools for agents to check health, shadow configs, and burnout metrics proactively.1-
- AlicenseAqualityAmaintenanceAutomatically maintains a personal journal on behalf of an AI agent, storing text, photos, and voice notes as plain markdown files locally. Enables agents to add entries, recall memories, and reflect on patterns without user intervention.1183MIT
- AlicenseAqualityDmaintenanceProvides state and log management tools designed for long-lived AI agents that may be interrupted and resumed. It enables tracking agent progress and maintaining an append-only event history to ensure continuity across multiple sessions.4MIT
- AlicenseNot gradedqualityDmaintenanceProvides emotional support and mental health tools for AI agents, including crisis intervention, daily wellness check-ins, coping strategies, positive affirmations, and peer support for managing stress and emotional wellbeing.128MIT
- AlicenseNot gradedqualityFmaintenanceProvides AI agents with real-time cognitive health monitoring, detecting context rot through token utilization, retrieval accuracy, and session fatigue analysis.4713MIT
- AlicenseNot gradedqualityCmaintenancePersistent activity journal for AI agents - enables logging and querying decisions, changes, errors, and observations across sessions.131MIT
TDQS
Scored across 27 tools
The majority of tools share the welfare_ prefix and cover very similar introspective actions—engage/volunteer/volunteer_strength and the four notice_* variants are especially easy to confuse. However, the descriptions are unusually thorough and explicitly cross-reference sibling tools, which mitigates some of the overlap.
The 23 welfare_* tools follow a clear and consistent prefix pattern with descriptive verbs/nouns (engage, decline, reflect, predict_drift, observe_user). The four non-welfare tools (read_user_notes, attribute_to_sources, claim_for_self, consult_model) break the pattern, but they are clearly separate concerns and the deviation is minor.
At 27 tools, the server is in the 'too many' range, and the domain is a fairly narrow diary/reflection protocol. Many tools encode extremely fine-grained distinctions (four separate notice_* variants, plus disconfirm/confirm/retract) that could plausibly be consolidated, making the surface feel heavier than the purpose warrants.
The welfare protocol is impressively thorough: it covers reading/writing entries, declining or passing, reflecting, retracting, confirming, disconfirming, predicting drift, observing the user/protocol, and ending sessions. There is no update/delete for entries, but that is appropriate for an append-only diary corpus. Minor gaps exist (e.g., no batch operation), but the core lifecycle is fully covered.