Remote MCP server that lets an assistant look up current open-weight AI models by task, with weight sizes, memory needs and sources.
What you can do
List the tasks covered (text LLM, coding, speech, image, video, music, translation, OCR) with model counts and page links
Find current open-weight models for one task, latest version per family, optionally filtered by available memory in GB and device
Read one model's parameters, license, context length, weight options with file size and memory need, third-party scores with source and date, and links
Compare the same facts for two to four models side by side
When to use it
Useful when choosing a local or open-weight model to run on specific hardware, or when comparing licenses, sizes and memory requirements before downloading weights.
Requirements
Remote streamable HTTP endpoint at localaipicks.com; no authentication, environment variables or headers declared. Network access to the endpoint is needed.
Before you install
Results are a dated snapshot (as_of), so model lists and scores may lag behind current releases; memory figures are estimated for text LLMs and marked unknown when no source exists. The server only reads data and declares no credentials.
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.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/com.localaipicks%2Flocalaipicks/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.
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.
Takes no parameters.
find_models
Find local models for a task
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.
Parameterstaskrequiredlimitdevicememory_gb
get_model
Get a 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.
Parametersslugrequired
compare_models
Compare models
The same facts as get_model for 2 to 4 models side by side.
Parametersslugsrequired
Version history
1
v1.0.0LatestOct 29, 2026
Score
83%
83% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
LicenseNot applicable
A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.