Per-model retirement rows from the record: which model dies when, with runway and migration target. Default shows scheduled (upcoming) retirements sorted by shutdown date.
AI agents call list_deprecations to retrieve information from Modelmeter without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | integer | — | Max rows. Default 100. |
status | string | — | Default scheduled. |
provider | string | — | Filter to one provider id. |
Parameters from the server's own tool schema.
This tool retrieves and displays historical or scheduled deprecation information about models. It has no side effects—it does not create, modify, delete, or execute anything. It simply queries and returns existing deprecation records from a changelog. The blast radius of misuse is minimal; an agent could only retrieve information that should typically be available to stakeholders anyway.
From the tool's definition Tool name 'list_deprecations' and description 'Per-model retirement rows from the record' indicate data retrieval. The description states it 'shows scheduled (upcoming) retirements' with no mention of modifying, deleting, or executing operations.
Attacks that exploit this kind of access
Per-model retirement rows from the record: which model dies when, with runway and migration target. Default shows scheduled (upcoming) retirements sorted by shutdown date. It is categorised as a Read tool in the Modelmeter MCP Server, which means it retrieves data without modifying state.
list_deprecations accepts 3 parameters: limit, status, provider. The full parameter table on this page comes from the server's own tool schema.
Register the Modelmeter MCP server in PolicyLayer and add a rule for list_deprecations: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Modelmeter. Nothing to install.
list_deprecations is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_deprecations rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for list_deprecations. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
list_deprecations is provided by the Modelmeter MCP server (https://modelmeter.xyz/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
list_deprecations is one line of Modelmeter's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →