Skip to main content

Best Practices

Get the most out of Context7 with these best practices
2 min read

Add a Rule#

To avoid typing use context7 in every prompt, add a rule to your MCP client to automatically invoke Context7 for code-related questions:

  • Cursor: Cursor Settings > Rules
  • Claude Code: CLAUDE.md
  • Or the equivalent in your MCP client

Example rule:

Use Library ID#

If you already know exactly which library you want to use, add its Context7 ID to your prompt. That way, Context7 MCP server can skip the library-matching step and directly continue with retrieving docs.

The slash syntax tells the MCP tool exactly which library to load docs for.

Specify a Version#

To get documentation for a specific library version, just mention the version in your prompt:

Context7 will automatically match the appropriate version.

Query Strategy#

Context7 grounds your assistant with up-to-date docs, but the quality of what it retrieves depends on how the retrieval is scoped. These habits keep the retrieved context minimal and relevant:

  • Retrieve only when needed — Context7 is for library, framework, SDK, API, and CLI-tool questions. Skip it for refactoring, writing scripts from scratch, debugging business logic, code review, or general programming concepts.
  • One concept per query — scope each query to a single topic. Split multi-topic questions (e.g. "routing and auth and caching") into a separate query per concept, unless the question is about how the concepts interact. Combined queries dilute ranking and return shallow results for each topic.
  • Be specific, not vague — a query like "How to set up authentication with JWT in Express.js" returns far better results than "auth" or "hooks".
  • Keep the context relevant — don't include sensitive or confidential information in queries, and use the best-matching library ID (and version-specific ID when a version matters) so you don't pull docs for the wrong package.