Skip to content
Whizi logo

Whizi MCP server

Which MCP servers are Whizi's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-09

← Back to Whizi

Whose server it is
  • Addresshttps://whizi.io/mcpnot in the official registry: answered when asked

No entry in the official MCP registry names this server. It answered on whizi.io when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.

When we asked itchecked 2026-10-27
  • Stateanswerschecked 2026-10-27
  • Tools2
  • Server calls itselfwhizi-model-finder
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 59 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 1 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 1, the first on 2026-10-27
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer212 ms
  • Space in an agent's context≈ 640 tokensthe definitions of all its tools (2), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 2 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers2 tools · read 2026-10-27
  • recommend_model

    Recommends which AI model (LLM) to use for one kind of task, as three picks: best quality, best value and lowest cost, each with list price, context window and a one line reason. Use when the user asks which AI model, chatbot or LLM to…

  • compare_models

    Compares two to four named AI models side by side: list price per million tokens, context window, image input, multilingual benchmark score where measured, and the tasks each is recommended for. Use when the user names specific models and…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "whizi": {
      "type": "http",
      "url": "https://whizi.io/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http whizi https://whizi.io/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://whizi.io/mcp as a custom connector in the settings.

OpenAPI spec

5 paths, read 2026-10-09. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.