Koskamo

readygpu MCP

A read-only MCP server that provides live pricing and hardware specifications for GPUs and Macs suitable for running local AI models. It allows agents to search for models, find compatible hardware, retrieve hardware details, and compare different devices across multiple countries and currencies.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

readygpu MCP logo, by readygpuVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by readygpu
MCP endpoint (Streamable HTTP)
https://readygpu.com/api/mcp
Vendor documentation

What you can do with it

  • Search for hardware compatible with specific AI models
  • Find the best hardware for local AI within a budget
  • Compare specifications and prices of different GPUs
  • Retrieve detailed hardware information for AI workloads

Source and maintenance

Vendor evidenceRegistry 1.0.0
mcp-registry: com.readygpu/readygpu@1.0.0Project website

Protocol and capabilities

Server
readygpu 1.0.0
MCP protocol
2025-06-18
Tools
6 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

For any open AI model: which graphics cards (new and used), Macs and mini PCs sold in the UK, Germany, Canada and the US run it fully in memory, how much memory it needs at each context length, and an estimated speed. Every answer links the readygpu.com page that shows today's prices. Free and read-only, with no sign-up, account or API key. Start with search_models or find_hardware to get slugs, then hardware_for_model, hardware_details, compare_hardware or best_hardware. Speeds are estimates, so say so when you quote them, and link the page each answer gives. Prices are on readygpu.com's own pages only: follow the page link in each answer.

Tools

6 advertised

search_models — Search open models
Advertised by the server during the last successful anonymous check.
Advertised read-only

Find open-weight AI models by name or task (chat, coding, agentic, vision, reasoning). Returns each model's slug, size, context length and licence; use the slug with hardware_for_model.

search_models input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "task": {
      "enum": [
        "chat",
        "coding",
        "agentic",
        "vision",
        "reasoning"
      ],
      "type": "string"
    },
    "limit": {
      "type": "integer",
      "default": 20,
      "maximum": 50,
      "minimum": 1
    },
    "query": {
      "type": "string",
      "maxLength": 100,
      "description": "Part of a model's name, e.g. qwen"
    }
  }
}
search_models annotations
{
  "title": "Search open models",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true
}
find_hardware — Find graphics cards or machines
Advertised by the server during the last successful anonymous check.
Advertised read-only

List graphics cards or complete machines (Macs, mini PCs) sold in a market, with memory, bandwidth, the estimated speed on a model and a link to each one's page and prices. Filter by minimum memory and new or used; sort by speed or popularity.

find_hardware input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "kind": {
      "enum": [
        "gpu_card",
        "machine"
      ],
      "type": "string",
      "default": "gpu_card"
    },
    "sort": {
      "enum": [
        "speed",
        "popularity"
      ],
      "type": "string",
      "default": "speed"
    },
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 30,
      "minimum": 1
    },
    "model": {
      "type": "string",
      "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
      "maxLength": 120,
      "minLength": 1,
      "description": "A model slug (from search_models) for the speed column; a reference model by default"
    },
    "market": {
      "enum": [
        "us",
        "uk",
        "de",
        "ca"
      ],
      "type": "string",
      "default": "us",
      "description": "Which market's catalogue: us, uk, de (Germany and the rest of the EU) or ca (Canada)."
    },
    "context": {
      "anyOf": [
        {
          "type": "number",
          "const": 8192
        },
        {
          "type": "number",
          "const": 32768
        },
        {
          "type": "number",
          "const": 65536
        },
        {
          "type": "number",
          "const": 131072
        }
      ],
      "default": 32768,
      "description": "Context length in tokens: 8192, 32768, 65536 or 131072."
    },
    "condition": {
      "enum": [
        "any",
        "new",
        "used"
      ],
      "type": "string",
      "default": "any"
    },
    "min_memory_gb": {
      "type": "number",
      "exclusiveMinimum": 0
    }
  }
}
find_hardware annotations
{
  "title": "Find graphics cards or machines",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true
}
hardware_details — Hardware details
Advertised by the server during the last successful anonymous check.
Advertised read-only

One graphics card or machine in a market: its specifications, which models it runs fully in memory at a context length and how fast, and a link to its page and prices.

hardware_details input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
      "maxLength": 120,
      "minLength": 1,
      "description": "A card or machine slug, from find_hardware"
    },
    "market": {
      "enum": [
        "us",
        "uk",
        "de",
        "ca"
      ],
      "type": "string",
      "default": "us",
      "description": "Which market's catalogue: us, uk, de (Germany and the rest of the EU) or ca (Canada)."
    },
    "context": {
      "anyOf": [
        {
          "type": "number",
          "const": 8192
        },
        {
          "type": "number",
          "const": 32768
        },
        {
          "type": "number",
          "const": 65536
        },
        {
          "type": "number",
          "const": 131072
        }
      ],
      "default": 32768,
      "description": "Context length in tokens: 8192, 32768, 65536 or 131072."
    }
  }
}
hardware_details annotations
{
  "title": "Hardware details",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true
}
hardware_for_model — Hardware to run a model
Advertised by the server during the last successful anonymous check.
Advertised read-only

For one model: how much memory it needs at each context length, and the fastest hardware (and the fastest Mac) that runs it fully in memory in a market, with their speeds. Links the model's page, which shows the cheapest and best-value picks with prices.

hardware_for_model input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "model"
  ],
  "properties": {
    "model": {
      "type": "string",
      "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
      "maxLength": 120,
      "minLength": 1,
      "description": "A model slug, from search_models"
    },
    "market": {
      "enum": [
        "us",
        "uk",
        "de",
        "ca"
      ],
      "type": "string",
      "default": "us",
      "description": "Which market's catalogue: us, uk, de (Germany and the rest of the EU) or ca (Canada)."
    },
    "context": {
      "anyOf": [
        {
          "type": "number",
          "const": 8192
        },
        {
          "type": "number",
          "const": 32768
        },
        {
          "type": "number",
          "const": 65536
        },
        {
          "type": "number",
          "const": 131072
        }
      ],
      "default": 32768,
      "description": "Context length in tokens: 8192, 32768, 65536 or 131072."
    }
  }
}
hardware_for_model annotations
{
  "title": "Hardware to run a model",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true
}
best_hardware — Best hardware lists
Advertised by the server during the last successful anonymous check.
Advertised read-only

The ranked 'best for local AI' lists of a market (all graphics cards, cards under a price, used cards, Macs and mini PCs): best first by the most capable model each runs fully in memory. Prices are on each list's page.

best_hardware input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "list": {
      "type": "string",
      "default": "gpus",
      "pattern": "^[a-z0-9-]{1,60}$",
      "description": "Which list: us: gpus, gpus-under-300, gpus-under-500, gpus-under-1000, gpus-under-2000, used-gpus, machines; uk: gpus, gpus-under-300, gpus-under-500, gpus-under-1000, gpus-under-2000, used-gpus, machines; de: gpus, gpus-under-300, gpus-under-500, gpus-under-1000, gpus-under-2000, used-gpus, machines; ca: gpus, gpus-under-400, gpus-under-700, gpus-under-1400, gpus-under-2800, used-gpus, machines. Lists with too few priced entries are not published."
    },
    "market": {
      "enum": [
        "us",
        "uk",
        "de",
        "ca"
      ],
      "type": "string",
      "default": "us",
      "description": "Which market's catalogue: us, uk, de (Germany and the rest of the EU) or ca (Canada)."
    }
  }
}
best_hardware annotations
{
  "title": "Best hardware lists",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true
}
compare_hardware — Compare two
Advertised by the server during the last successful anonymous check.
Advertised read-only

Two graphics cards or machines side by side in a market: memory, bandwidth, how many models each runs fully in memory, and the estimated speed of each on every model.

compare_hardware input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "a",
    "b"
  ],
  "properties": {
    "a": {
      "type": "string",
      "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
      "maxLength": 120,
      "minLength": 1,
      "description": "First card or machine slug"
    },
    "b": {
      "type": "string",
      "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
      "maxLength": 120,
      "minLength": 1,
      "description": "Second card or machine slug"
    },
    "market": {
      "enum": [
        "us",
        "uk",
        "de",
        "ca"
      ],
      "type": "string",
      "default": "us",
      "description": "Which market's catalogue: us, uk, de (Germany and the rest of the EU) or ca (Canada)."
    },
    "context": {
      "anyOf": [
        {
          "type": "number",
          "const": 8192
        },
        {
          "type": "number",
          "const": 32768
        },
        {
          "type": "number",
          "const": 65536
        },
        {
          "type": "number",
          "const": 131072
        }
      ],
      "default": 32768,
      "description": "Context length in tokens: 8192, 32768, 65536 or 131072."
    }
  }
}
compare_hardware annotations
{
  "title": "Compare two",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
1199 ms
95th percentile latency
1199 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 1199 ms · metadata changed · 6 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http readygpu-mcp https://readygpu.com/api/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add readygpu-mcp --url https://readygpu.com/api/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable readygpu-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "readygpu-mcp": {
      "url": "https://readygpu.com/api/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "readygpu-mcp": {
      "type": "streamableHttp",
      "url": "https://readygpu.com/api/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start readygpu-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "readygpu-mcp": {
      "type": "http",
      "url": "https://readygpu.com/api/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http readygpu-mcp https://readygpu.com/api/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "readygpu-mcp": {
      "url": "https://readygpu.com/api/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "readygpu-mcp": {
      "serverUrl": "https://readygpu.com/api/mcp"
    }
  }
}

Let your agent find its tools

Find servers like readygpu MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 6,904

Do you run readygpu MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing