Context7
Verified Oct 2, 2026 ActiveDocumentation service and MCP server that feeds version-specific library docs and code examples into AI coding assistants.
Listed on EffectHub Β·
Pricing
- Pricing model
- Freemium
- Paid options from
- $10/seat/mo
- Billing
- Per seat, monthly
Free plan covers public repositories with 1,000 API calls a month. Pro is $10 per seat a month with 2,000 calls per seat, then $5 per 1,000 extra calls, and private repository parsing costs $5 per million tokens. Enterprise adds SOC 2, SSO and self-hosting by quote.
Use tool βAbout Context7
Context7 indexes the documentation of open-source libraries and returns current, version-specific passages and code samples on request, so coding assistants stop guessing at outdated APIs. It works through an MCP server or through a CLI plus an agent skill, and adding "use context7" to a prompt triggers a lookup; a library ID or a version number can be named to narrow it. A free API key raises rate limits, and teams can index private repositories on paid plans. It is built and run by Upstash, and the main code is MIT-licensed on GitHub.
- Platforms
- Web Β· API
- API
- Yes
- Last verified
- Oct 2, 2026
Verified sources
- What Context7 does and who builds it: Upstash project, free for personal usecontext7.com β
- Free, Pro and Enterprise plans with call limits and overage ratescontext7.com β
- Open-source repository under MIT, setup via MCP or CLI plus skills, created March 2025github.com β
- Upstash, Inc., a Delaware corporation based in Californiaupstash.com β
Is Context7 legit?
We donβt label tools safe or unsafe. Below are the records we checked ourselves, each with the date we read it.
- Last checked
- Oct 2, 2026The site answered
- On the market since
- 2025The vendor's own material, read by us
- Operated by
- Upstash, Inc., United StatesOur research, card verified Oct 2, 2026
Pros & cons of Context7
Context7 fixes a narrow but common annoyance: AI coding assistants quoting last year's API for a fast-moving library. It is quick to wire into Cursor, Claude Code and similar tools, and the free tier is enough for an individual developer. It only helps for libraries that are indexed and documented well, and it adds prompt tokens on every lookup.
Pros
- Version-specific docs pulled from source rather than model training data
- Works over MCP or via a CLI and skill, with one-command setup
- Free tier plus a $10 per-seat Pro plan
- Open-source code under MIT, built by Upstash
Cons
- Free plan stops at 1,000 calls a month, with a small daily bonus allowance after that
- Quality depends on how well each library's docs are indexed and ranked
- Retrieved snippets consume context window space on every call
Best for
- Developers using AI editors with frameworks that change often, such as Next.js or Supabase
- Teams that want agents to read their own private library docs
- Anyone tired of hallucinated or deprecated API calls in generated code
Not for
- Teams that need answers about proprietary systems that are not documented in a library repository
- People who do not use an AI coding assistant
Watch out: Free users are blocked after 1,000 calls in a month and then get only 20 bonus calls a day; Pro overage is billed at $5 per 1,000 calls, and each seat has its own allowance rather than a shared pool.
Top alternatives to Context7
Context7 head-to-head
Side-by-side fact sheets against the competitors our research or their makers name β pricing, platforms, API and both verdicts on one page.