# upstash/context7

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

Repository: https://github.com/upstash/context7
Canonical: https://ross.abutalabs.com/products/context7
Homepage: https://context7.com
Language: TypeScript
License: MIT
License Family: permissive
Topics: llm, mcp, mcp-server, vibe-coding
Last push: 2026-08-26T12:24:36+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 37
- inputs: {"age_days": 525, "days_push": 7, "days_rel": 6, "gap_med": 1.5, "n_releases_24m": 107}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 61268, forks 2953 (observed 2026-08-28T04:12:19.007124+00:00)

## What it is
Context7 is an MCP server and hosted platform by Upstash that pulls up-to-date, version-specific library documentation and code examples directly into LLM prompts and AI coding assistants. It integrates with tools like Cursor, Claude Code, Codex, and VS Code to ground AI-generated code in current, real APIs.

## Use cases
- get up-to-date library docs inside AI coding assistants
- stop LLMs from hallucinating nonexistent APIs
- inject version-specific code examples into prompts
- wire documentation retrieval into Cursor or Claude Code via MCP
- ground AI code generation in current framework APIs
- reduce outdated code examples from stale training data

## When to choose
- you use AI coding assistants and hit outdated or hallucinated API suggestions
- you want an MCP server that supplies current library documentation to LLMs
- you need version-specific docs for frameworks like Next.js, Supabase, or Cloudflare Workers in your prompts

## When to avoid
- you need fully offline documentation retrieval with no external service dependency
- you require self-hosting on the free tier (self-hosting is enterprise-only)
- your workflow doesn't involve LLMs or AI-assisted coding

## Facets
- artifact type: service
- maturity: active
- function: rag, mcp, documentation, llm-inference, developer-tools
- domain: large-language-models, developer-tools, documentation
- platform: cli, cross-platform
- tags: mcp-server, vibe-coding, ai-coding-assistants, code-documentation, context-injection, ai-agents, nodejs, web-server

## Member repositories
- upstash/context7 (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:19.007124+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:17:32.890747+00:00, confidence not recorded.
  - readme: https://github.com/upstash/context7 (fetched 2026-08-28T04:12:19.007124+00:00, sha fc49deab5580)
  - homepage: https://context7.com (fetched 2026-08-28T17:58:30.370783+00:00, sha a29f22d14fc6)
  - site_page: https://context7.com/about (fetched 2026-08-28T17:58:30.387996+00:00, sha afd0e9deceb1)
  - site_page: https://context7.com/docs (fetched 2026-08-28T17:58:30.379599+00:00, sha 4f060b199c88)
  - site_page: https://context7.com/install (fetched 2026-08-28T17:58:30.383704+00:00, sha 931c9e93265a)
  - site_page: https://context7.com/plans (fetched 2026-08-28T17:58:30.381553+00:00, sha d5ace2a40445)
  - site_page: https://context7.com/add-library (fetched 2026-08-28T17:58:30.385876+00:00, sha 31ceab09378d)
- Data as of 2026-08-30T08:39:29.467469+00:00.