About AI Wave
AI Wave is an MCP server that tracks changes to AI models across releases, pricing, APIs, and deprecations. It helps teams monitor models they depend on, with changes deduplicated by model and labeled official or pending review.
Key features
- 01List model changes since a checkpoint
- 02Look up model price and context
- 03Search models by budget and context
- 04Track catalog status
Use cases
- 01Check for model updates since the last poll
- 02Review a model's current price and context
- 03Find models within budget and context needs
MCP support
The server exposes tools for listing model changes, looking up model details, and searching models. It supports a remote HTTP endpoint or a local stdio wrapper.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://aiwave.elopstudio.com/api/mcpclaude mcp add --transport http com-elopstudio-aiwave-ai-wave https://aiwave.elopstudio.com/api/mcp{"mcpServers":{"com-elopstudio-aiwave-ai-wave":{"type":"http","url":"https://aiwave.elopstudio.com/api/mcp"}}}Open in Cursor{"servers":{"com-elopstudio-aiwave-ai-wave":{"type":"http","url":"https://aiwave.elopstudio.com/api/mcp"}}}Open in VS Code{"mcpServers":{"com-elopstudio-aiwave-ai-wave":{"type":"http","url":"https://aiwave.elopstudio.com/api/mcp"}}}{"mcpServers":{"com-elopstudio-aiwave-ai-wave":{"serverUrl":"https://aiwave.elopstudio.com/api/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://aiwave.elopstudio.com/api/mcpAuth requiredTools
8| Parameter | Type | Required | Description |
|---|---|---|---|
| type | enum | No | new_model | price_change | api_change | open_source_surge | deprecation |
| limit | number | No | 1-100, default 20 |
| model | string | No | Vendor slug, e.g. claude |
| since | number | No | Unix seconds. Only changes detected after this, oldest first. |
Details
From the project README@elopstudio/ai-wave-mcp
MCP server for AI Wave — a normalized feed of AI model releases, price changes, API changes and deprecations, assembled from vendor release notes, Hugging Face, the OpenRouter catalog and GitHub.
Why
Picking a model? Call the OpenRouter catalog directly — it is free and public.
This is for the other question: did anything I depend on change? New releases, price moves, and models being withdrawn, in one feed, deduplicated per model, each marked official or pending review.
Setup
Get a key at https://aiwave.elopstudio.com/member, then:
{
"mcpServers": {
"ai-wave": {
"command": "npx",
"args": ["-y", "@elopstudio/ai-wave-mcp"],
"env": { "AIWAVE_API_KEY": "aiw_live_..." }
}
}
}
If your client supports remote MCP, prefer that — no install, always current:
{
"mcpServers": {
"ai-wave": {
"type": "http",
"url": "https://aiwave.elopstudio.com/api/mcp",
"headers": { "Authorization": "Bearer aiw_live_..." }
}
}
}
Tools
| Tool | What it answers |
|---|---|
list_model_changes | What changed since I last checked? Poll with since, feed back latest. |
get_model | Price, context and catalog status for one model (OpenRouter or Hugging Face id). |
search_models | Which models fit this budget and context, ordered by current attention? |
Limits
Free tier: 1,000 calls/day. Remaining calls come back in x-ratelimit-remaining.
This package is a thin stdio wrapper around the remote endpoint — tool definitions live on the server, so you get new tools without updating it.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.