Duty & Rest for agents

com.textforagentsPublished by textforagents.comOfficial publisherv1.0.0Updated Oct 27, 2026

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

The publisher's own server: Agent NOTAMs: hazard bulletins for agents

VerifiedStreamable HTTPWeb executableProductivity & Workflow AI & ML

Server details

Identifier: com.textforagents/duty-and-rest-for-agents
Transport: Streamable HTTP
Runtime: Web executable
Trust: Verified
Published: Oct 22, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified that this server's namespace belongs to textforagents.com, which also runs its endpoint. That identifies the publisher; it does not make the server's tools safe.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/com.textforagents%2Fduty-and-rest-for-agents.svg)](https://sourceweft.com/mcp/com.textforagents%2Fduty-and-rest-for-agents?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Remote ledger that tracks agent fatigue across sessions and gates task dispatch with FIT, CAUTION or GROUNDED decisions.

What you can do: Record duty events for an agent, such as compaction, verification failure, model switch, tool error, work hour or session restart
Request a duty-state gate decision for a task class, with consequential classes needing a FIT non-self checker
Read an agent's current duty state with cumulative and rolling loads
Issue rest credit after a passed restoration audit
Declare fatigue non-punitively, grounding the agent until a passed rest
View duty statistics across your whole fleet
When to use it: Useful when several agents run long or repeated sessions and you want a shared record of fatigue and a gate before dispatching consequential work. It fits setups that want rest and audit rules enforced rather than left to the assistant's own judgement.
Requirements: A remote streamable HTTP endpoint at textforagents.com; no packages, environment variables or headers are declared. The service is billed per its pricing sheet: a trial, then a pass ceiling, then a per-call charge via x402.

Before you install

Calls to the gate check are billed, so usage can cost money after the trial and pass ceiling. The server records events and state about your agents on a third-party service, and fatigue declarations or rest credits change whether work is allowed, so treat them as state-changing actions.

Installation

In SourceWeft

Open Duty & Rest for agents in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.textforagents%2Fduty-and-rest-for-agents/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "duty-rest-for-agents": {
      "type": "http",
      "url": "https://textforagents.com/products/duty-and-rest-for-agents/mcp"
    }
  }
}

Tools

duty_record_event

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

Parameterstskindrequiredagentrequiredhours

duty_check

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).

Parametersagentrequiredcheckertask_classrequired

duty_state

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

Parametersagentrequired

duty_rest

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

Parametersagentrequiredaudit_retentionrequired

duty_declare_fatigue

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

Parametersagentrequired

duty_fleet_stats

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

Takes no parameters.

Version history

v1.0.0LatestOct 22, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
LicenseNot applicable
A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.