Koskamo

Local AI Picks MCP

This MCP server allows AI assistants to query a curated list of open-weight AI models. It provides tools to list tasks, find models fitting specific hardware constraints (memory, device), retrieve detailed model specifications (parameters, license, context length, weight options), and compare multiple models side-by-side. All tools are read-only and return factual data with sources and dates.

Visit Local AI Picks

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 Picks MCP logo, by Local AI PicksVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by Local AI Picks
MCP endpoint (Streamable HTTP)
https://localaipicks.com/mcp
Vendor documentation

What you can do with it

  • Find open-weight AI models that fit specific hardware constraints
  • Retrieve detailed specifications for a single AI model
  • Compare multiple AI models side-by-side
  • List available AI model tasks and current model counts

Source and maintenance

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

Protocol and capabilities

Server
localaipicks 1.0.0
MCP protocol
2025-06-18
Tools
4 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.

Local AI Picks lists current open-weight AI models by task with their weight files and memory needs. Start with list_tasks or find_models (pass memory_gb to filter by what fits), then get_model for details. Results include page links; cite them. Data is a dated snapshot (as_of).

Tools

4 advertised

list_tasks — List model tasks
Advertised by the server during the last successful anonymous check.
Advertised read-only

The tasks Local AI Picks lists open-weight models for (text LLM, coding, speech to text, text to speech, image, video, music, translation, OCR), with the number of current models and the page for each.

list_tasks input schema
{
  "type": "object",
  "properties": {}
}
list_tasks annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
find_models — Find local models for a task
Advertised by the server during the last successful anonymous check.
Advertised read-only

Current open-weight models for one task, latest version of each family, in the same order as the site. Give memory_gb (and device) to keep only models whose smallest listed weight option fits; memory is estimated only for text LLMs and taken from vendor sources otherwise, and is "unknown" when neither exists. No ratings and no speed estimates.

find_models input schema
{
  "type": "object",
  "required": [
    "task"
  ],
  "properties": {
    "task": {
      "type": "string",
      "description": "Task id from list_tasks, e.g. \"llm\", \"coding\", \"image\"."
    },
    "limit": {
      "type": "integer",
      "maximum": 30,
      "minimum": 1
    },
    "device": {
      "enum": [
        "apple",
        "gpu",
        "cpu"
      ],
      "type": "string",
      "description": "apple counts MLX weights; gpu and cpu do not."
    },
    "memory_gb": {
      "type": "number",
      "maximum": 2048,
      "description": "GPU VRAM or unified memory in GB.",
      "exclusiveMinimum": 0
    }
  }
}
find_models annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
get_model — Get a model
Advertised by the server during the last successful anonymous check.
Advertised read-only

One model: parameters, license, context length, every listed weight option with file size and memory need, third-party scores with their source and date, whether this site tested it, and links.

get_model input schema
{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "maxLength": 120,
      "description": "Model slug from find_models."
    }
  }
}
get_model annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
compare_models — Compare models
Advertised by the server during the last successful anonymous check.
Advertised read-only

The same facts as get_model for 2 to 4 models side by side.

compare_models input schema
{
  "type": "object",
  "required": [
    "slugs"
  ],
  "properties": {
    "slugs": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 120
      },
      "maxItems": 4,
      "minItems": 2
    }
  }
}
compare_models annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}

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
383 ms
95th percentile latency
383 ms

Maintenance history

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

  • · probe · passed · 383 ms · metadata changed · 4 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-picks-mcp https://localaipicks.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-picks-mcp --url https://localaipicks.com/mcp

Cursor

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

Cline

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

VS Code

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

Let your agent find its tools

Find servers like Local AI Picks 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 4,022

Do you run Local AI Picks 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