MCP Rating

io.mcpratingv0.2.0Updated Sep 29, 2026

Search MCP servers, with our own start-test results, required keys, tools and token cost.

VerifiedStreamable HTTPWeb executableDeveloper Tools

Overview

AI-generated overview

Lets an assistant search a directory of MCP servers and see start-test results, required keys, tools, and token cost.

What it does
This remote MCP server exposes a search capability over a catalog of MCP servers. According to its description, results include the provider's own start-test results, the keys a server requires, the tools it offers, and its token cost. It is a lookup and comparison service rather than a tool that acts on your own systems.
When to use it
Useful when you are choosing which MCP server to add and want to compare candidates by whether they start successfully, what credentials they need, what tools they expose, and how much context they consume. It is a discovery aid, not a runtime dependency for other work.
Requirements
It runs as a remote endpoint at mcprating.io over streamable HTTP; no packages, environment variables, or headers are declared, and no authentication is declared. Network access to that endpoint is required.
Before you install
The catalog content is third-party data, so treat listed start-test results, required keys, and token costs as claims to verify rather than guarantees. No credentials are requested by the manifest, but do not paste secrets into search queries.

Installation

In SourceWeft

  1. Open MCP Rating in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

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

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v0.2.0LatestSep 29, 2026