MCP server that provides cost-optimised model recommendations for autonomous agents
Connect Whichmodel MCP to Claude, Cursor or any other MCP client and it stops being a tab you switch to. MCP server that provides cost-optimised model recommendations for autonomous agents. The whichmodel mcp mcp server is what makes that connection.
For MCP clients that use stdio transport (Claude Desktop, Cursor, etc.):
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
recommend_model — Get a cost-optimised model recommendation for a specific task type, complexity, and budgetcompare_models — Head-to-head comparison of 2–5 models with optional volume cost projectionsget_pricing — Raw pricing data lookup with filters by model, provider, price ceiling, and capabilitiescheck_price_changes — Returns: price increases, decreases, new models, and deprecationsSetup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.
This sits in the planning and project tracking group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Whichmodel MCP's toolset — recommend_model, compare_models, get_pricing and 1 more — is a fair guide to whether it matches your workflow. It is maintained by which-model; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Whichmodel MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| recommend_model | Get a cost-optimised model recommendation for a specific task type, complexity, and budget. |
| compare_models | Head-to-head comparison of 2–5 models with optional volume cost projections. |
| get_pricing | Raw pricing data lookup with filters by model, provider, price ceiling, and capabilities. |
| check_price_changes | Returns: price increases, decreases, new models, and deprecations. |
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Your assistant inside the workspace — read channels, search history, post messages and tame the noise.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.