Managed MCP gateway that connects AI agents to 1,500+ apps with handled OAuth, a free tier and usage-based pricing.

Context7 AI features, pricing and GDPR (October 2026)
MCP server and API from Upstash that give AI coding assistants current, version-specific library documentation and code examples.
from $10 per user/month
Pricing details
According to the pricing page, Free costs $0 with 1,000 API calls per month for public repositories, Pro costs $10 per seat per month with 2,000 calls per seat and $5 per 1,000 extra calls, and parsing private repositories costs $5 per 1M tokens. Enterprise is custom. As of September 2026.
What is Context7?
Context7 is a documentation service from Upstash that gives AI coding assistants current, version-specific library documentation and code examples through an MCP server and an API, aimed at developers and engineering teams.
Context7 indexes documentation and code snippets from library sources and returns the parts that match a question, so that assistants such as Cursor or Claude Code work with the right library version. The MCP server exposes two tools, resolve-library-id and query-docs, and the repository lists support for more than 30 other MCP clients. A Search API, private repositories for teams and a self-hosted option for enterprises complete the offer. Upstash, Inc. is based in California. The MCP server code is MIT licensed and the repository had more than 62,000 GitHub stars on October 1, 2026.
Context7 AI features and use cases
- Supplies agents with current library docsThe MCP server turns a library name into an identifier and fetches matching documentation for the requested version. Coding agents then write code against current APIs instead of outdated training data, and developers spend less time correcting invented function calls.
- Finds snippets from plain questionsThe Search API lets an agent ask a question without naming a library. The service identifies relevant libraries, extracts matching code snippets and reranks them before returning results with library name and source URL, so the agent can cite where an answer comes from.
- Screens documentation for unsafe contentAccording to the vendor, a two-pass check screens indexed documentation for prompt injection and unsafe code, and trust scoring keeps unsafe content out of agent context. Teams that connect agents to community-contributed libraries get a safeguard against poisoned snippets.
What sets Context7 apart
- The MCP server code is open source under the MIT license, while the API backend, parsing engine and crawling engine remain proprietary, according to the repository.
- Enterprise adds SSO (SAML or OIDC), a self-hosted Docker deployment in a private network and, per the vendor, US or EU data residency.
- Pricing is per seat with included API calls and a separate charge for parsing private repositories, and a free plan covers public repositories.
Where Context7 is strongest
Context7 belongs to Upstash, Inc., based in California; the service is offered online, and the Enterprise plan offers US or EU data residency.
Questions to ask before you buy Context7
Context7 libraries are community-contributed, so treat retrieved snippets as untrusted input and keep prompt injection defenses on the agent side too. The Free plan stops at 1,000 API calls per month, and private repositories need Pro. SSO, a self-hosted option and SOC 2 belong to Enterprise. The vendor says queries are processed locally with 30-day retention; ask for the data processing terms.
Using Context7 in the EU: GDPR and AI Act
- Data locationMultiple regions, EU region available (according to the vendor). Hosting regions: United States, EU.
- Data processing agreementNot published by the vendor: ask for one (Art. 28 GDPR).
- EU AI ActCheck whether the AI prepares decisions about people. If not, the high-risk rules usually do not apply. The high-risk obligations apply from December 2, 2027 (Digital Omnibus).
Context7 reviews
No reviews yet. Be the first to share how your team uses it.
Every review shows its verification level. We read each one before it goes live. How we check reviews
Questions about Context7
What does Context7 cost?
The pricing page lists a Free plan at $0 with 1,000 API calls per month and a Pro plan at $10 per seat per month. Pro includes 2,000 calls per seat and charges $5 per 1,000 extra calls. Enterprise pricing is custom.
Is Context7 open source?
Partly. The MCP server in the GitHub repository is MIT licensed. According to the repository, the API backend, parsing engine and crawling engine are proprietary.
Can we run it inside our own network?
Yes, in the Enterprise plan. The vendor describes a self-hosted deployment as a Docker container in a private network, and says private data stays on your own infrastructure.
Context7 update historyno updates yet
No changes recorded for Context7 yet.
Changes the vendor made and confirmed user reports, each checked against the vendor's own pages. We review every tool monthly.
Alternatives to Context7
Tools in the same category (Developer & cloud tools) with the most overlapping markets.
GitHub's official MCP server that lets AI assistants read and act on repositories, issues, pull requests and Actions.
Microsoft MCP server that lets AI agents control browsers through the accessibility tree instead of screenshots.
Sentry's official MCP server that lets coding assistants query errors, issues and traces and use Seer analysis.



