Skip to content
Proxlai logo

Proxlai MCP server

Which MCP servers are Proxlai'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 2026-10-28

← Back to Proxlai

Whose server it is
  • Registry namecom.proxlai/proxlaiverified in the MCP registry

The registry name sits under proxlai.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-28
  • Stateanswerschecked 2026-10-28
  • Tools5
  • Server calls itselfproxlai
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 161 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.

Once connected

  • For "Let an AI agent check current AI API prices", the likely first call is list_markets.

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: 7, the first on 2026-10-28
  • INITE MCP score84 of 100answers 93 · definitions 100 · context 100 · use 0 · connects 100
  • Answered100% of days7 of 7 daily checks
  • Median first answer1695 ms
  • Space in an agent's context≈ 874 tokensthe definitions of all its tools (5), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • not sure · Compare LLM and embedding API prices side by side
  • not sure · Look up hourly GPU rental prices across providers
  • can do · Let an AI agent check current AI API prices

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

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 offers5 tools · read 2026-10-28
  • list_markets

    List every market (kind of AI API) that has prices, with its id and pricing unit. Start here to find the market id.

  • describe_market

    Explain one market: what it is, how its pricing works, and the attributes you can filter and compare on (with plain-language help).

  • search_offerings

    Rank the offerings in one market by price, quality and speed, with optional requirements and a maximum price. Returns prices with their verification date and source.

  • get_offering

    Full detail for one offering: description, capabilities, current price with its source, and price history.

  • compare_offerings

    Put 2 to 4 offerings from the same market side by side: prices, scores and every capability.

How to connect

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

{
  "mcpServers": {
    "proxlai": {
      "type": "http",
      "url": "https://proxlai.com/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http proxlai https://proxlai.com/api/mcp

Add to CursorAdd to VS Code

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

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.