Skip to content
Local AI Picks logo

Local AI Picks MCP server

Which MCP servers are Local AI Picks'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 2026-10-29

← Back to Local AI Picks

Whose server it is
  • Registry namecom.localaipicks/localaipicksverified in the MCP registry

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

When we asked itchecked 2026-10-29
  • Stateanswerschecked 2026-10-29
  • Tools4
  • Server calls itselflocalaipicks
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-29 the server answered initialize and tools/list without a sign-in. First answer in 54 ms.

Should an agent connect itNot proven either way yet
  • Its tools do check which open models fit your device's memory; compare local speech-to-text models by memory needs, but not run coding agents on your own machine.
  • Checked on 4 of the 7 days it takes to judge reliability.

Once connected

  • For "check which open models fit your device's memory", the likely first call is find_models.
  • For "compare local speech-to-text models by memory needs", the likely first call is find_models.
  • Parameters are untyped or undescribed in 2 of 4 tools: check arguments before calling.

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: 4, the first on 2026-10-29
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
  • What an agent can do with it2 of 3 use cases
  • Answeredmeasuring4 of the 7 daily checks it takes to print a share
  • Median first answer176 ms
  • Space in an agent's context≈ 446 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsA · 92 of 100
  • Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 2 of 4

What an agent can do with it

  • can do · check which open models fit your device's memory
  • can do · compare local speech-to-text models by memory needs
  • cannot · run coding agents on your own machine

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 offers4 tools · read 2026-10-29
  • list_tasks

    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.

  • find_models

    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…

  • get_model

    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.

  • compare_models

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

How to connect

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

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

Add it

Claude Code, in a terminal

claude mcp add --transport http localaipicks https://localaipicks.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://localaipicks.com/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.