Skip to main content
Glama
Sign In

Duty & Rest for agents

by com.textforagents
OverviewDiscussionsAdmin

Server Details

Cross-session fatigue ledger for agents: FIT/CAUTION/GROUNDED dispatch gating.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2024-11-05
URL
ChatGPT
–
Claude
–

TDQS

B3.2/5.0

Scored across 6 tools

Disambiguation4/5

Each tool has a distinct role: gate decision, state inspection, event recording, rest issuance, fatigue declaration, and fleet aggregation. Minor confusion is possible between duty_state and duty_check (both report load/status) and between duty_rest and duty_declare_fatigue, but descriptions clarify the gate vs. reporting and issuance vs. declaration distinction.

Naming Consistency4/5

All names share the duty_ prefix in snake_case, giving a predictable, readable pattern. The suffix style varies slightly (verb-based duty_record_event/duty_declare_fatigue vs. noun-based duty_check/duty_state/duty_fleet_stats), but the shared prefix keeps it coherent.

Tool Count4/5

Six tools map cleanly onto the duty/rest lifecycle without redundancy. It is on the lean side, but every tool corresponds to a real operation rather than filler.

Completeness4/5

The surface covers state query, gate decision, event recording, rest credit, fatigue declaration, and fleet stats, which is nearly full lifecycle coverage. Minor gaps exist around inspecting recorded event history or per-agent audit details, but agents can work around this via duty_state.

Available Tools

6 tools
duty_checkBInspect

Duty-state gate decision (FIT/CAUTION/GROUNDED + allowed) for a task class; consequential classes in CAUTION need a FIT non-self checker. Billed per the pricing sheet (trial, then pass ceiling, then $0.002 x402).

Inputs: agent (required), task_class (required), checker.

duty_declare_fatigueBInspect

Non-punitive fatigue declaration: grounds the agent until a passed rest; no penalty field.

Inputs: agent (required).

duty_fleet_statsBInspect

Duty statistics for your whole fleet (your agents only).

Inputs: no named parameters.

duty_record_eventBInspect

Record a duty event for one of your agents (kinds: compaction, verification_failure, model_switch, tool_error, work_hour, session_restart).

Inputs: kind (required), agent (required), ts, hours.

duty_restCInspect

Rest-credit issuance: credit only on a passed restoration audit (audit_retention >= 0.90).

Inputs: agent (required), audit_retention (required).

duty_stateCInspect

Current duty state and cumulative + rolling loads for one of your agents.

Inputs: agent (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • roxabi-sense

      roxabi-senseofficial

      Roxabi
      A
      license
      B
      quality
      B
      maintenance
      Local workstation attention journal that tracks focus, idle, and agent sessions, exposing timeline data via MCP for AI agents to query current or past activity.
      5
      AGPL 3.0

    • context-rot-detection

      milos-product-maker
      A
      license
      Not graded
      quality
      D
      maintenance
      Provides AI agents with real-time cognitive health monitoring, detecting context rot through token utilization, retrieval accuracy, and session fatigue analysis.
      29 npm
      13
      MIT
    Try in Browser
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources