What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the WhichModel MCP server?
Cost-optimized LLM model routing recommendations for autonomous AI agents
How to install WhichModel
Copy-paste configuration for popular MCP clients.
{
"mcpServers": {
"whichmodel": {
"url": "https://whichmodel.dev/mcp"
}
}
}Related MCP servers

io.github.WirterNow/agent-bank
Financial infrastructure for AI agents: wallets, USDC transfers, lending, jobs on Polygon

Intelligence marketplace on Solana — 86 tools, 168+ endpoints, per-call USDC.
Build and publish AI products for coaching practices from inside Claude. 16 live tools.
View repository →A coding and development harness on local models or hosted APIs, for code, review, research and ops.
View repository →
io.github.Whitemarmot/copyright01
Copyright deposit API — protect code, text, and websites with Berne Convention proof

io.github.Whitemarmot/markly
Add text or logo watermarks to images via the Markly.cloud API. Batch supported.

