AI coding agents need more than file search. This repo gives them semantic code context.
This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
AI coding agents need more than file search. This repo gives them semantic code context. mcpls is an MCP-to-LSP bridge for builders who want AI coding assistants to work through language servers. It helps you give an agent code-aware context by exposing LSP capabilities—including type information, cross-reference analysis, and semantic navigation—through MCP. Key features: • Type-aware context – retrieve hover information and inferred types at a position • Definition and implementation jumps – navigate to where a symbol or implementation is defined • Workspace-wide references – find every
Posted by Dan Kornas (99.3k followers) 1 h ago · 2 likes · 529 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- Claude推出云端session — @mylifcc
- Agent work gets messy when every task lives in a terminal tab. — @DanKornas
- under-rated use of @OpenAIDevs Codex: — @theaaron
- 有时候，我会先让 Claude 把方案想清楚，再交给 Codex 去写，两个 Agent 工具之间来回复制上下文，挺麻烦的。 — @GitHub_Daily
- introducing https://agently.dev — @omarships
- 🚨 Android devs: AI agents can now generate native Jetpack Compose UI with A2UI. — @akshay81844
- I made a Jev competitor called Jev-Huyev: https://www.chapterpal.com/jev-huyev — @burkov
- prime agent v0.9.6 is out: — @kevinjosethomas
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 23.2k posts from 5k X accounts over the last 21 days, 2.7k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-24 04:51 UTC. Full method.