{"slug": "serena", "name": "Serena", "category": "ai-coding", "category_name": "AI coding tools", "description": "", "recommenders": 3, "commenters": 4, "warners": 0, "score": 2.908, "rising": 0.35, "first": "2025-12-28", "latest": "2026-09-04", "why": "I use serena as an MCP for all LSPs and it works great.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 1, "compare": 0, "warn": 0}, "spark": [0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "I use serena as an MCP for all LSPs and it works great.", "icon": true, "domain": null, "github_repo": "github.com/oraios/serena", "official_url": "https://github.com/oraios/serena", "pricing": "", "aliases": ["Serena"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 793012640, "item_id": 49563290, "url": "https://news.ycombinator.com/item?id=49563290", "by": "ghthor", "date": "2026-09-04", "stance": "recommend", "quote": "I use serena as an MCP for all LSPs and it works great.", "excerpt": "I use serena as an MCP for all LSPs and it works great. She does installs hooks into Claude reminding to use LSP tools.", "context": "", "use_case": "LSP tools for coding agents", "switched_from": "", "story": "Grep beats LSP? Why coding agents ignore your fancier tools"}, {"id": 746055793, "item_id": 46628487, "url": "https://news.ycombinator.com/item?id=46628487", "by": "akshay326", "date": "2026-01-14", "stance": "recommend", "quote": "symbolic search (serena mcp)", "excerpt": "What would you cover not-continuous? Best methods I\u2019ve observed -progressive loading (claude skills) & symbolic search (serena mcp)", "context": "", "use_case": "symbolic code search", "switched_from": "", "story": "Ask HN: What is best way to provide continuous context to models?"}, {"id": 742559216, "item_id": 46409951, "url": "https://news.ycombinator.com/item?id=46409951", "by": "gutafoki", "date": "2025-12-28", "stance": "recommend", "quote": "If the code base is large enough, serena is a must have.", "excerpt": "I am surprised by all the answers saying 0 percent. I'd understand that if you use use it without any grounding or additional context. I am far faster with it, using one MCP server with docs and one for language specific features. If the code base is large enough, serena is a must have. I'd say about the same, groking an unknown code base is a lot faster, producing for something I am familiar with maybe 4-5x", "context": "", "use_case": "navigating large codebases with AI", "switched_from": "", "story": "Ask HN: By what percentage has AI changed your output as a software engineer?"}]}], "caveats": [], "who": [], "tags": [], "use_cases": ["lsp tools for coding agents", "language server wrapper for coding agents", "symbolic code search", "navigating large codebases with ai"], "compared": [], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49560260", "title": "Grep beats LSP? Why coding agents ignore your fancier tools", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49407493", "title": "What if coding agents didn't have to read code?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46626639", "title": "Ask HN: What is best way to provide continuous context to models?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46409375", "title": "Ask HN: By what percentage has AI changed your output as a software engineer?", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {"recommend": 1}, "2026-01": {"recommend": 1}, "2026-02": {}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {}, "2026-07": {}, "2026-08": {"neutral": 1}, "2026-09": {"recommend": 1}, "2026-10": {}}, "quotes": [{"id": 793012640, "item_id": 49563290, "url": "https://news.ycombinator.com/item?id=49563290", "by": "ghthor", "date": "2026-09-04", "stance": "recommend", "quote": "I use serena as an MCP for all LSPs and it works great.", "excerpt": "I use serena as an MCP for all LSPs and it works great. She does installs hooks into Claude reminding to use LSP tools.", "context": "", "use_case": "LSP tools for coding agents", "switched_from": "", "story": "Grep beats LSP? Why coding agents ignore your fancier tools"}, {"id": 790521280, "item_id": 49407580, "url": "https://news.ycombinator.com/item?id=49407580", "by": "killingtime74", "date": "2026-08-23", "stance": "neutral", "quote": "There's even wrappers for it like", "excerpt": "So just like a language server? https://en.wikipedia.org/wiki/Language_Server_Protocol. It's a good idea which is why it's already been invented. There's even wrappers for it like https://github.com/oraios/serena", "context": "", "use_case": "language server wrapper for coding agents", "switched_from": "", "story": "What if coding agents didn't have to read code?"}, {"id": 746055793, "item_id": 46628487, "url": "https://news.ycombinator.com/item?id=46628487", "by": "akshay326", "date": "2026-01-14", "stance": "recommend", "quote": "symbolic search (serena mcp)", "excerpt": "What would you cover not-continuous? Best methods I\u2019ve observed -progressive loading (claude skills) & symbolic search (serena mcp)", "context": "", "use_case": "symbolic code search", "switched_from": "", "story": "Ask HN: What is best way to provide continuous context to models?"}, {"id": 742559216, "item_id": 46409951, "url": "https://news.ycombinator.com/item?id=46409951", "by": "gutafoki", "date": "2025-12-28", "stance": "recommend", "quote": "If the code base is large enough, serena is a must have.", "excerpt": "I am surprised by all the answers saying 0 percent. I'd understand that if you use use it without any grounding or additional context. I am far faster with it, using one MCP server with docs and one for language specific features. If the code base is large enough, serena is a must have. I'd say about the same, groking an unknown code base is a lot faster, producing for something I am familiar with maybe 4-5x", "context": "", "use_case": "navigating large codebases with AI", "switched_from": "", "story": "Ask HN: By what percentage has AI changed your output as a software engineer?"}]}