The changelog of record for the model layer: deprecations, price changes, launches, and the market events around them. Filter by severity to find what demands action: 'breaking' (model going away, ID changing), 'action_required' (price/rate-limit/context changes), 'informational' (releases, fundi...
AI agents call list_events 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 |
|---|---|---|---|
type | string | — | Event type, e.g. model_deprecation, pricing_change, model_launch. |
limit | integer | — | Max events. Default 50. |
since | string | — | ISO date (YYYY-MM-DD); events announced on/after. |
until | string | — | ISO date (YYYY-MM-DD); events announced on/before. |
status | string | — | Verification status. Default 'verified' (human-confirmed). 'all' = verified + unverified. |
provider | string | — | Filter to events touching this provider. |
severity | string | — | Filter by what the event demands of consumers of the affected models. |
Parameters from the server's own tool schema.
This tool queries historical event data (deprecations, price changes, launches, market events) and returns filtered results. It has no capability to modify, delete, or execute external operations. Even though the events described (deprecations, price changes) may require user action, the tool itself only reads and presents information.
From the tool's definition Tool description states it retrieves 'the changelog of record' and allows filtering—these are query/read operations with no side effects. The name 'list_events' and verbs like 'find' indicate data retrieval only.
Attacks that exploit this kind of access
The changelog of record for the model layer: deprecations, price changes, launches, and the market events around them. Filter by severity to find what demands action: 'breaking' (model going away, ID changing), 'action_required' (price/rate-limit/context changes), 'informational' (releases, funding). It is categorised as a Read tool in the Modelmeter MCP Server, which means it retrieves data without modifying state.
list_events accepts 7 parameters: type, limit, since, until, status, provider, severity. 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_events: 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_events 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_events 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_events. 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_events 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_events 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 →