Koskamo

Local AI Prices MCP

Provides tools to search for local AI hardware, retrieve machine details, find devices suitable for specific models, and track price changes. It enables agents to answer questions about hardware costs, stock availability, and performance metrics like tokens per second for various open models.

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.

Local AI Prices MCP logo, by localaiprices.comVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-07Operated by localaiprices.com
MCP endpoint (Streamable HTTP)
https://localaiprices.com/mcp
Vendor documentation

What its tools do

5 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (5)

5 of 5 have a description · 5 of 5 declare behavior hints · 4 of 4 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to localaiprices.com ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Find the cheapest machine that runs a specific model
  • Search for high-performance boxes under a budget
  • Compare prices for a specific machine across stores
  • Track price drops and restocks for target hardware

Source and maintenance

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

Protocol and capabilities

Server
localaiprices 1.0.0
MCP protocol negotiated in check
2025-11-25
Tools
5 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

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

Prices, stock and measured LLM speeds (tokens per second) for local AI computers and graphics cards, from localaiprices.com. Prices are checked once a day. Show the page link and the check time with any price. Speeds are public results by others; keep the source link. Read-only: nothing here can buy anything.

Tools

5 advertised

search_machines — Search machines
Advertised by the server during the last successful anonymous check.
Advertised read-only

Find local AI computers and graphics cards by budget, memory and type. Returns price, measured tok/s, value (tok/s per 1,000 of currency), when the price was checked, and the page URL. Prices are checked once a day.

search_machines input schema
{
  "type": "object",
  "properties": {
    "kind": {
      "enum": [
        "machine",
        "gpu-card",
        "any"
      ],
      "type": "string",
      "description": "machine = complete computer, gpu-card = graphics card only (needs a PC). Default any."
    },
    "sort": {
      "enum": [
        "value",
        "price",
        "speed"
      ],
      "type": "string",
      "description": "value = tok/s per 1,000 (default), price = cheapest first, speed = fastest first."
    },
    "limit": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1,
      "description": "Default 10."
    },
    "region": {
      "enum": [
        "us",
        "eu"
      ],
      "type": "string",
      "description": "us = prices in USD, eu = prices in EUR. Default us."
    },
    "benchmark": {
      "enum": [
        "small",
        "large"
      ],
      "type": "string",
      "description": "Speed to use: small = Llama-2 7B Q4_0 (default, most results), large = gpt-oss-120b (needs 64GB+)."
    },
    "max_price": {
      "type": "number",
      "description": "Highest price in the region's currency."
    },
    "in_stock_only": {
      "type": "boolean",
      "description": "Leave out machines a store reports as out of stock."
    },
    "min_memory_gb": {
      "type": "number",
      "description": "Least memory (unified memory or VRAM) in GB, e.g. 128."
    }
  }
}
search_machines annotations
{
  "title": "Search machines",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_machine — Get one machine
Advertised by the server during the last successful anonymous check.
Advertised read-only

One machine in full by id (from search_machines) or page URL: price per store with stock and check time, price history summary, every published speed result with its source, and value.

get_machine input schema
{
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Machine id, e.g. framework-desktop-128, or its localaiprices.com/p/<id>/ URL."
    }
  }
}
get_machine annotations
{
  "title": "Get one machine",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
find_for_model — Machines for a model
Advertised by the server during the last successful anonymous check.
Advertised read-only

Which tracked machines can run an open model (4-bit weights fit in memory), cheapest first, with measured tok/s where someone has published a result. Use list_models for ids.

find_for_model input schema
{
  "type": "object",
  "required": [
    "model"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1,
      "description": "Default 20."
    },
    "model": {
      "type": "string",
      "description": "Model id or name, e.g. gpt-oss-120b or Qwen3 Coder 30B A3B."
    },
    "region": {
      "enum": [
        "us",
        "eu"
      ],
      "type": "string",
      "description": "us = prices in USD, eu = prices in EUR. Default us."
    },
    "max_price": {
      "type": "number",
      "description": "Highest price in the region's currency."
    },
    "measured_only": {
      "type": "boolean",
      "description": "Only machines with a published speed for this model."
    }
  }
}
find_for_model annotations
{
  "title": "Machines for a model",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
list_changes — What changed
Advertised by the server during the last successful anonymous check.
Advertised read-only

Price drops, price rises, restocks and newly tracked machines, newest first. Set since to a timestamp and only later changes come back; reuse next_since from the reply for the next call. Prices are checked once a day.

list_changes input schema
{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 500,
      "minimum": 1,
      "description": "Default 50."
    },
    "since": {
      "type": "string",
      "description": "ISO date or time; only changes after it. Omit for all."
    },
    "types": {
      "type": "array",
      "items": {
        "enum": [
          "price_drop",
          "price_rise",
          "back_in_stock",
          "out_of_stock",
          "new_machine"
        ],
        "type": "string"
      },
      "description": "Only these kinds of change."
    },
    "machine": {
      "type": "string",
      "description": "Only changes for this machine id."
    }
  }
}
list_changes annotations
{
  "title": "What changed",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
list_models — List models
Advertised by the server during the last successful anonymous check.
Advertised read-only

The open models we track: id, size, memory needed at 4-bit and 8-bit, how many machines fit each and how many have a measured speed, and the page URL.

list_models input schema
{
  "type": "object",
  "properties": {}
}
list_models annotations
{
  "title": "List models",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

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
276 ms
95th percentile latency
276 ms

Maintenance history

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

  • · probe · passed · 276 ms · metadata changed · 5 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 local-ai-prices-mcp https://localaiprices.com/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 local-ai-prices-mcp --url https://localaiprices.com/mcp

Cursor

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

Cline

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

VS Code

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

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://localaiprices.com/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": {
    "local-ai-prices-mcp": {
      "serverUrl": "https://localaiprices.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Local AI Prices 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 6,972

Do you run Local AI Prices 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