Urgent.News

What's breaking now, across thousands of outlets.

Tech

How to find LM Studio plugins and MCP servers

Originally published on sahansera.dev . You have a model running in LM Studio. Now you want it to search the web, work with files, or trim a video. Where do you find the tool that makes that possible? I've built Local AI Tools to help with that step. It's a free, open-source directory where you can browse native LM Studio plugins and MCP servers, search by capability, and inspect their setup…

Local AI Tools is an open-source marketplace designed to help users discover and utilize LM Studio plugins and MCP servers. It offers a searchable catalogue of native LM Studio plugins and MCP servers, allowing users to browse by capability and inspect their setup information.

To use Local AI Tools, simply navigate to the marketplace and explore the available options. If you know the specific plugin or server you want, a direct link can be used. Otherwise, you can search for the desired capability, such as video processing, memory management, or web search.

Local AI Tools distinguishes between native LM Studio plugins and MCP servers, helping users understand the integration type and setup requirements. For example, the Local Video Tools plugin, which I also maintain, allows for video inspection, trimming, conversion, and FFmpeg job management within LM Studio. This tool enables local video processing with hardware acceleration and without holding AI tool calls open during video encoding.

By providing a centralized directory of plugins and servers, Local AI Tools simplifies the process of finding and integrating the desired tools into LM Studio, making it easier for users to enhance their local AI setup.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in Tech

Stop Returning “Access Denied”

Security teams spend a lot of time deciding whether a request should be allowed. The person making that request experiences the decision through a much smaller interface: usually a status code and a…

  • 403 Forbidden status code provides enforcement effect but lacks reason for denial
  • Unique decision identifier links user-facing error to diagnostic records
  • Reason catalog offers defined owners and tested remediation procedures for common denials

I Moved Everything to Kubernetes, Then Moved It Back

Over two weeks I moved six self-hosted services from Docker Compose onto Kubernetes — ArgoCD, supply-chain policy, the whole GitOps loop.

  • Reporter migrated six self-hosted services to Kubernetes and then back to Docker Compose
  • Six services maintained same external domains and ports during migration
  • Reporter questioned necessity of Kubernetes for third-party software

Why Most Medicine Reminders Fail (And How We Built One That Refuses to Be Ignored)

It usually happens around 8:30 in the morning. A notification pings on a smartphone: "Time for your morning BP medication." The son glances at the screen, swipes it away, and thinks to himself, "I'll…

  • Most reminder apps assume lack of alarm is the main issue
  • Parhezo addresses messy health management and emotional exhaustion
  • Uses persistent siren alerts and local data storage

Your Cache Is Part of the Security Model

Caching is usually introduced as a performance decision. Once cached data participates in an authorization result, it also determines how long an old security fact remains usable.

  • Caching can prolong outdated security facts by maintaining old permissions even after revocation.
  • Different attributes require different cache lifetimes based on risk and source system behavior.
  • Implementing soft and hard expiry for cached values mitigates risks of stale hits.

More from Monday 14 September →