{"slug": "context7", "name": "Context7", "category": "ai-coding", "category_name": "AI coding tools", "description": "MCP server that supplies AI coding assistants with up-to-date library documentation and code examples.", "recommenders": 6, "commenters": 7, "warners": 0, "score": 5.688, "rising": 0.69, "first": "2025-12-13", "latest": "2026-08-23", "why": "HN commenters use it to give AI coding agents current library and API docs over MCP, and credit it with better code and faster syntax lookups.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 6, "neutral": 1, "compare": 0, "warn": 0}, "spark": [0, 1, 1, 0, 0, 0, 0, 0, 2, 2, 0, 0], "listed": true, "loved": ["API docs lookup", "Code quality"], "caveat": "", "short_quote": "Context7 (coming soon) great at code, way better than exa for code", "icon": true, "domain": null, "github_repo": null, "official_url": "https://context7.com", "pricing": "unknown", "aliases": ["Context7", "context7"], "verdict": [{"text": "HN commenters use it to give AI coding agents current library and API docs over MCP,", "cites": [{"id": 740163874, "item_id": 46260242, "url": "https://news.ycombinator.com/item?id=46260242", "by": "brikym", "date": "2025-12-13", "stance": "recommend", "quote": "use context7's MCP for docs", "excerpt": "Here are some SvelteKit helpers to shove in your agents.md: https://www.davis7.sh/sv There are a number of ways to get examples into the LLM. I use shadcn-svelte and bitsui and try to copy the examples (copy button at the top of the docs) or tell the LLM to fetch docs from the github repo or use context7's MCP for docs.", "context": "", "use_case": "fetching docs for LLM", "switched_from": "", "story": "Ask HN: How can I get better at using AI for programming?"}, {"id": 785680064, "item_id": 49105004, "url": "https://news.ycombinator.com/item?id=49105004", "by": "mpdpsycho", "date": "2026-07-29", "stance": "recommend", "quote": "I think it matters easily for the things that can be patched like Context7 helping with API knowledge", "excerpt": "Eh, I think the urge is similar but maybe the rationality a bit less. i.e. there is some measurable increase in\u2026 whatever you\u2019re trying to maximize with a car mod, volume or performance or whatnot. It\u2019s more opaque with these harness optimizations and tools. To be fair I mess with \u201chow\u201d I use or orchestrate the harness myself, I still can\u2019t say anything I do that benefits me is more than placebo. At least from my pro", "context": "", "use_case": "API knowledge for coding agents", "switched_from": "", "story": "The Productivity Mirage"}, {"id": 782804594, "item_id": 48925287, "url": "https://news.ycombinator.com/item?id=48925287", "by": "port11", "date": "2026-07-15", "stance": "recommend", "quote": "My AGENTS.md does specific they should use context7 when unsure about a library", "excerpt": "Strange, I use M3 and Sonnet a lot, they never hallucinated. Gemini used to make up some function names, but it was in long context windows. My AGENTS.md does specific they should use context7 when unsure about a library, but still\u2026", "context": "", "use_case": "library documentation lookup for agents", "switched_from": "", "story": "Show HN: Super Dario"}]}, {"text": " and credit it with better code and faster syntax lookups.", "cites": [{"id": 747293073, "item_id": 46705817, "url": "https://news.ycombinator.com/item?id=46705817", "by": "tomjuggler", "date": "2026-01-21", "stance": "recommend", "quote": "the quality of code has improved since there is always context7 and fetch to look up syntax", "excerpt": "Personally I use \"agent mode\" in Cecli for almost everything - I don't know about other AI coding agents but you can easily set up tests to run and validate the output. Since MCP came out the quality of code has improved since there is always context7 and fetch to look up syntax. But yes at some point you need to look at the code yourself just to be sure", "context": "", "use_case": "looking up syntax docs", "switched_from": "", "story": "Ask HN: Do you have any evidence that agentic coding works?"}, {"id": 790533891, "item_id": 49408368, "url": "https://news.ycombinator.com/item?id=49408368", "by": "pi-victor", "date": "2026-08-23", "stance": "recommend", "quote": "if you connect staan-search (there is a pi plugin for that) and ctx7 to this it almost does miracles.", "excerpt": "i'm not good with paper work, in fact, i'm horrible with anything that's paperwork related. for the past few days, i ran this model on my rtx 4090 + rtx 3070 and told it to check all the bills, invoices, contracts for me and my small company. i used pi with llama and the pi-llama plugin. oh, boy - i hooked it to my email, told it to download all of the invoices and bills i had for both me and my company and organize ", "context": "", "use_case": "documentation lookup for agent", "switched_from": "", "story": "I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes"}, {"id": 789339045, "item_id": 49333690, "url": "https://news.ycombinator.com/item?id=49333690", "by": "yoeven", "date": "2026-08-17", "stance": "recommend", "quote": "Context7 (coming soon) great at code, way better than exa for code", "excerpt": "thanks! 1. yeah, we've optimized significantly for latency, give the API a try and you'll see it's pretty fast. 2. more than you think, we use a wide range of providers internally depending on the context needed. Exa could be great in some for example people search but is pretty bad at getting the latest content of the page, Parallel is better there. Apify is great for getting google ranked pages. Perplexity is great", "context": "", "use_case": "code search", "switched_from": "", "story": "Show HN: OpenWebSearch \u2013 A router for web search indexes"}]}, {"text": " No complaints appear in the mentions;", "cites": [{"id": 785680064, "item_id": 49105004, "url": "https://news.ycombinator.com/item?id=49105004", "by": "mpdpsycho", "date": "2026-07-29", "stance": "recommend", "quote": "I think it matters easily for the things that can be patched like Context7 helping with API knowledge", "excerpt": "Eh, I think the urge is similar but maybe the rationality a bit less. i.e. there is some measurable increase in\u2026 whatever you\u2019re trying to maximize with a car mod, volume or performance or whatnot. It\u2019s more opaque with these harness optimizations and tools. To be fair I mess with \u201chow\u201d I use or orchestrate the harness myself, I still can\u2019t say anything I do that benefits me is more than placebo. At least from my pro", "context": "", "use_case": "API knowledge for coding agents", "switched_from": "", "story": "The Productivity Mirage"}, {"id": 782804594, "item_id": 48925287, "url": "https://news.ycombinator.com/item?id=48925287", "by": "port11", "date": "2026-07-15", "stance": "recommend", "quote": "My AGENTS.md does specific they should use context7 when unsure about a library", "excerpt": "Strange, I use M3 and Sonnet a lot, they never hallucinated. Gemini used to make up some function names, but it was in long context windows. My AGENTS.md does specific they should use context7 when unsure about a library, but still\u2026", "context": "", "use_case": "library documentation lookup for agents", "switched_from": "", "story": "Show HN: Super Dario"}]}, {"text": " it suits developers who want agents to check documentation when unsure about a library.", "cites": [{"id": 782804594, "item_id": 48925287, "url": "https://news.ycombinator.com/item?id=48925287", "by": "port11", "date": "2026-07-15", "stance": "recommend", "quote": "My AGENTS.md does specific they should use context7 when unsure about a library", "excerpt": "Strange, I use M3 and Sonnet a lot, they never hallucinated. Gemini used to make up some function names, but it was in long context windows. My AGENTS.md does specific they should use context7 when unsure about a library, but still\u2026", "context": "", "use_case": "library documentation lookup for agents", "switched_from": "", "story": "Show HN: Super Dario"}, {"id": 740163874, "item_id": 46260242, "url": "https://news.ycombinator.com/item?id=46260242", "by": "brikym", "date": "2025-12-13", "stance": "recommend", "quote": "use context7's MCP for docs", "excerpt": "Here are some SvelteKit helpers to shove in your agents.md: https://www.davis7.sh/sv There are a number of ways to get examples into the LLM. I use shadcn-svelte and bitsui and try to copy the examples (copy button at the top of the docs) or tell the LLM to fetch docs from the github repo or use context7's MCP for docs.", "context": "", "use_case": "fetching docs for LLM", "switched_from": "", "story": "Ask HN: How can I get better at using AI for programming?"}]}], "praise": [{"label": "API docs lookup", "summary": "Commenters use it to fill gaps in a model's library and API knowledge.", "quotes": [{"id": 785680064, "item_id": 49105004, "url": "https://news.ycombinator.com/item?id=49105004", "by": "mpdpsycho", "date": "2026-07-29", "stance": "recommend", "quote": "I think it matters easily for the things that can be patched like Context7 helping with API knowledge", "excerpt": "Eh, I think the urge is similar but maybe the rationality a bit less. i.e. there is some measurable increase in\u2026 whatever you\u2019re trying to maximize with a car mod, volume or performance or whatnot. It\u2019s more opaque with these harness optimizations and tools. To be fair I mess with \u201chow\u201d I use or orchestrate the harness myself, I still can\u2019t say anything I do that benefits me is more than placebo. At least from my pro", "context": "", "use_case": "API knowledge for coding agents", "switched_from": "", "story": "The Productivity Mirage"}, {"id": 782804594, "item_id": 48925287, "url": "https://news.ycombinator.com/item?id=48925287", "by": "port11", "date": "2026-07-15", "stance": "recommend", "quote": "My AGENTS.md does specific they should use context7 when unsure about a library", "excerpt": "Strange, I use M3 and Sonnet a lot, they never hallucinated. Gemini used to make up some function names, but it was in long context windows. My AGENTS.md does specific they should use context7 when unsure about a library, but still\u2026", "context": "", "use_case": "library documentation lookup for agents", "switched_from": "", "story": "Show HN: Super Dario"}, {"id": 740163874, "item_id": 46260242, "url": "https://news.ycombinator.com/item?id=46260242", "by": "brikym", "date": "2025-12-13", "stance": "recommend", "quote": "use context7's MCP for docs", "excerpt": "Here are some SvelteKit helpers to shove in your agents.md: https://www.davis7.sh/sv There are a number of ways to get examples into the LLM. I use shadcn-svelte and bitsui and try to copy the examples (copy button at the top of the docs) or tell the LLM to fetch docs from the github repo or use context7's MCP for docs.", "context": "", "use_case": "fetching docs for LLM", "switched_from": "", "story": "Ask HN: How can I get better at using AI for programming?"}]}, {"label": "Code quality", "summary": "Users say agents write better code with it for syntax lookups.", "quotes": [{"id": 747293073, "item_id": 46705817, "url": "https://news.ycombinator.com/item?id=46705817", "by": "tomjuggler", "date": "2026-01-21", "stance": "recommend", "quote": "the quality of code has improved since there is always context7 and fetch to look up syntax", "excerpt": "Personally I use \"agent mode\" in Cecli for almost everything - I don't know about other AI coding agents but you can easily set up tests to run and validate the output. Since MCP came out the quality of code has improved since there is always context7 and fetch to look up syntax. But yes at some point you need to look at the code yourself just to be sure", "context": "", "use_case": "looking up syntax docs", "switched_from": "", "story": "Ask HN: Do you have any evidence that agentic coding works?"}, {"id": 790533891, "item_id": 49408368, "url": "https://news.ycombinator.com/item?id=49408368", "by": "pi-victor", "date": "2026-08-23", "stance": "recommend", "quote": "if you connect staan-search (there is a pi plugin for that) and ctx7 to this it almost does miracles.", "excerpt": "i'm not good with paper work, in fact, i'm horrible with anything that's paperwork related. for the past few days, i ran this model on my rtx 4090 + rtx 3070 and told it to check all the bills, invoices, contracts for me and my small company. i used pi with llama and the pi-llama plugin. oh, boy - i hooked it to my email, told it to download all of the invoices and bills i had for both me and my company and organize ", "context": "", "use_case": "documentation lookup for agent", "switched_from": "", "story": "I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes"}]}, {"label": "Code search", "summary": "One search-API builder rates it well above Exa for code.", "quotes": [{"id": 789339045, "item_id": 49333690, "url": "https://news.ycombinator.com/item?id=49333690", "by": "yoeven", "date": "2026-08-17", "stance": "recommend", "quote": "Context7 (coming soon) great at code, way better than exa for code", "excerpt": "thanks! 1. yeah, we've optimized significantly for latency, give the API a try and you'll see it's pretty fast. 2. more than you think, we use a wide range of providers internally depending on the context needed. Exa could be great in some for example people search but is pretty bad at getting the latest content of the page, Parallel is better there. Apify is great for getting google ranked pages. Perplexity is great", "context": "", "use_case": "code search", "switched_from": "", "story": "Show HN: OpenWebSearch \u2013 A router for web search indexes"}]}], "caveats": [], "who": [], "tags": ["for AI coding agents", "MCP server", "for library docs"], "use_cases": ["documentation lookup for agent", "code search", "api knowledge for coding agents", "library documentation lookup for agents", "looking up syntax docs", "documentation mcp for agent"], "compared": [], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49407507", "title": "I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49333187", "title": "Show HN: OpenWebSearch \u2013 A router for web search indexes", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49104335", "title": "The Productivity Mirage", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48896286", "title": "Show HN: Super Dario", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46691243", "title": "Ask HN: Do you have any evidence that agentic coding works?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46515696", "title": "Opus 4.5 is going to change everything", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {"recommend": 1}, "2026-01": {"neutral": 1, "recommend": 1}, "2026-02": {}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {}, "2026-07": {"recommend": 2}, "2026-08": {"recommend": 2}, "2026-09": {}, "2026-10": {}}, "quotes": [{"id": 790533891, "item_id": 49408368, "url": "https://news.ycombinator.com/item?id=49408368", "by": "pi-victor", "date": "2026-08-23", "stance": "recommend", "quote": "if you connect staan-search (there is a pi plugin for that) and ctx7 to this it almost does miracles.", "excerpt": "i'm not good with paper work, in fact, i'm horrible with anything that's paperwork related. for the past few days, i ran this model on my rtx 4090 + rtx 3070 and told it to check all the bills, invoices, contracts for me and my small company. i used pi with llama and the pi-llama plugin. oh, boy - i hooked it to my email, told it to download all of the invoices and bills i had for both me and my company and organize ", "context": "", "use_case": "documentation lookup for agent", "switched_from": "", "story": "I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes"}, {"id": 789339045, "item_id": 49333690, "url": "https://news.ycombinator.com/item?id=49333690", "by": "yoeven", "date": "2026-08-17", "stance": "recommend", "quote": "Context7 (coming soon) great at code, way better than exa for code", "excerpt": "thanks! 1. yeah, we've optimized significantly for latency, give the API a try and you'll see it's pretty fast. 2. more than you think, we use a wide range of providers internally depending on the context needed. Exa could be great in some for example people search but is pretty bad at getting the latest content of the page, Parallel is better there. Apify is great for getting google ranked pages. Perplexity is great", "context": "", "use_case": "code search", "switched_from": "", "story": "Show HN: OpenWebSearch \u2013 A router for web search indexes"}, {"id": 785680064, "item_id": 49105004, "url": "https://news.ycombinator.com/item?id=49105004", "by": "mpdpsycho", "date": "2026-07-29", "stance": "recommend", "quote": "I think it matters easily for the things that can be patched like Context7 helping with API knowledge", "excerpt": "Eh, I think the urge is similar but maybe the rationality a bit less. i.e. there is some measurable increase in\u2026 whatever you\u2019re trying to maximize with a car mod, volume or performance or whatnot. It\u2019s more opaque with these harness optimizations and tools. To be fair I mess with \u201chow\u201d I use or orchestrate the harness myself, I still can\u2019t say anything I do that benefits me is more than placebo. At least from my pro", "context": "", "use_case": "API knowledge for coding agents", "switched_from": "", "story": "The Productivity Mirage"}, {"id": 782804594, "item_id": 48925287, "url": "https://news.ycombinator.com/item?id=48925287", "by": "port11", "date": "2026-07-15", "stance": "recommend", "quote": "My AGENTS.md does specific they should use context7 when unsure about a library", "excerpt": "Strange, I use M3 and Sonnet a lot, they never hallucinated. Gemini used to make up some function names, but it was in long context windows. My AGENTS.md does specific they should use context7 when unsure about a library, but still\u2026", "context": "", "use_case": "library documentation lookup for agents", "switched_from": "", "story": "Show HN: Super Dario"}, {"id": 747293073, "item_id": 46705817, "url": "https://news.ycombinator.com/item?id=46705817", "by": "tomjuggler", "date": "2026-01-21", "stance": "recommend", "quote": "the quality of code has improved since there is always context7 and fetch to look up syntax", "excerpt": "Personally I use \"agent mode\" in Cecli for almost everything - I don't know about other AI coding agents but you can easily set up tests to run and validate the output. Since MCP came out the quality of code has improved since there is always context7 and fetch to look up syntax. But yes at some point you need to look at the code yourself just to be sure", "context": "", "use_case": "looking up syntax docs", "switched_from": "", "story": "Ask HN: Do you have any evidence that agentic coding works?"}, {"id": 744464002, "item_id": 46529000, "url": "https://news.ycombinator.com/item?id=46529000", "by": "hollandburke", "date": "2026-01-07", "stance": "neutral", "quote": "the only MCP I used", "excerpt": "Author of the post here. I appreciate the spirited debate and I agree with most of it - on both sides. It's a strange place to be where I think both arguments for and against this case make perfect sense. All I have to go on then is my personal experience, which is the only objective thing I've got. This entire profession feels stochastic these days. A few points of clarification... 1. I don't speak for anyone but my", "context": "", "use_case": "documentation MCP for agent", "switched_from": "", "story": "Opus 4.5 is going to change everything"}, {"id": 740163874, "item_id": 46260242, "url": "https://news.ycombinator.com/item?id=46260242", "by": "brikym", "date": "2025-12-13", "stance": "recommend", "quote": "use context7's MCP for docs", "excerpt": "Here are some SvelteKit helpers to shove in your agents.md: https://www.davis7.sh/sv There are a number of ways to get examples into the LLM. I use shadcn-svelte and bitsui and try to copy the examples (copy button at the top of the docs) or tell the LLM to fetch docs from the github repo or use context7's MCP for docs.", "context": "", "use_case": "fetching docs for LLM", "switched_from": "", "story": "Ask HN: How can I get better at using AI for programming?"}]}