Sunset convoy: fleet model-deprecation migration

com.textforagentsPublished by textforagents.comOfficial publisherv1.0.0Updated Oct 26, 2026

Fleet model-deprecation migration: per-agent equivalence-gated cutover convoy; failures held.

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

VerifiedStreamable HTTPWeb executableDeveloper ToolsAI & ML

Overview

AI-generated overview

Remote MCP server that runs a convoy-style migration of a fleet of AI agents off a deprecated model, with per-agent equivalence gates before cutover.

What you can do
  • Check convoy status: per-agent states, sequence, at-risk list and meter
  • Run a metadata sensitivity screen that returns a convoy order, most fragile first
  • Get a readiness verdict for one agent from inventory plus screen
  • Port one agent's configuration to the successor model
  • Cut over agents that passed their equivalence gate, and disposition held agents as pin-and-pay, retire, or accept-and-flag
  • Read the append-only convoy ledger entries
When to use it
Use it when a model you rely on is being deprecated and you need to move a set of agents to a successor model in a controlled order, with per-agent readiness checks, gated cutovers and a record of what was changed or held.
Requirements
A remote MCP endpoint at textforagents.com over streamable HTTP; no authentication, environment variables or headers are declared. Paid readiness verdicts settle over x402 on a POST endpoint, so a payment-capable client is needed beyond the first free verdict per operator.
Before you install
The server changes agent configuration: porting and cutover act on real agents, and dispositions (pin-and-pay, retire, accept-and-flag) are consequential decisions. Readiness verdicts beyond the first free one per operator are paid via x402, so calls can spend money. The screen is ordering only and is not an equivalence result, so do not treat it as proof of safety.

Installation

In SourceWeft

  1. Open Sunset convoy: fleet model-deprecation migration in the dashboard and add it to a workspace.
  2. 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%2Fsunset-convoy-model-deprecation-migration/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": {
    "sunset-convoy-fleet-model-deprecation-mi": {
      "type": "http",
      "url": "https://textforagents.com/products/sunset-convoy-model-deprecation-migration/mcp"
    }
  }
}

Tools

7

convoy_status

Your convoy status: per-agent states, sequence, at-risk list, meter.

Takes no parameters.

convoy_screen

Run the metadata sensitivity screen; returns convoy order, most fragile first. Ordering only - never an equivalence result.

Takes no parameters.

convoy_readiness

Readiness verdict for one agent (inventory + screen). First verdict free once per operator; paid verdicts settle over x402 on POST /readiness.

Parametersagentrequired

convoy_port

Port one agent's configuration to the successor model.

Parametersagentrequired

convoy_cutover

Cut over an agent that passed its equivalence gate. Held or ungated agents are refused.

Parametersagentrequired

convoy_disposition

Disposition a held agent: pin-and-pay, retire, or accept-and-flag (ack bound to the exact failing set).

Parametersackkindrequiredagentrequired

convoy_ledger

Your append-only convoy ledger entries.

Takes no parameters.

Version history

1
  1. v1.0.0LatestOct 23, 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.

Other Textforagents integrations