Skip to main content

Context7 integration for AI chat

A model's knowledge stops at its training date, and libraries keep changing. Turn on Context7 in Endless and the agent reads the current documentation for the library you name before it writes code.

Book a demo

What the agent can do with Context7

  1. 01

    Find the right library

    Match a package or product name to its Context7 entry, so the agent reads the docs for the exact project you mean.

  2. 02

    Read current docs and examples

    Pull documentation and code examples for that library as they are today.

  3. 03

    Write code that matches the API

    Get code written against the documented API, which matters most for libraries that change between versions.

Things to ask

  • “Use Context7 to show how to add middleware in the current version of Next.js.”
  • “Check the Tailwind CSS docs on Context7 and explain how to define a custom color.”
  • “Using Context7, write a Prisma query that paginates with a cursor.”

How to set it up

  1. 01

    Open connectors

    In Endless, open Settings and go to Connectors.

  2. 02

    Turn on Context7

    Context7 is a public server, so there is nothing to sign in to. Turn it on in your list of connectors.

  3. 03

    Ask in chat

    Start a chat and ask for what you need. The agent uses Context7 when your request calls for it.

Every Context7 tool the agent gets

2 tools, as Context7's MCP server lists them. The agent picks the one that fits your request.

ToolWhat it does, in Context7's words
resolve-library-idResolves a package/product name to a Context7-compatible library ID and returns matching libraries.
query-docsRetrieves and queries up-to-date documentation and code examples from Context7 for any programming library or framework.

Frequently asked questions

  • Why use Context7 instead of asking the model directly?

    A model answers from what it learned in training, which can be several versions old. Context7 gives the agent the documentation as it is now, so the code it writes uses the current API.

  • Which libraries does Context7 cover?

    The libraries and frameworks Context7 has indexed, which include most popular open-source projects. The agent searches Context7 for the name you give and tells you when it finds nothing.

  • Do I need an account or an API key?

    No. Context7 is a public MCP server. There is no account to connect and no key to paste.

  • Can a workspace admin turn Context7 off?

    Yes. An admin can turn a connector off for the whole workspace in the Workspace tab of the connectors settings. Members choose for themselves among the connectors left on.

  • Can a scheduled task use Context7?

    Yes. A scheduled task can use the connectors that are on for its creator, so a weekly report can read Context7 the same way a chat does.

  • Which chat models can use Context7?

    The chat model you pick in Endless gets the Context7 tools, so you can switch models in a conversation and keep the connection.

Related integrations

Give your next idea a place to grow.

Start free, create a project, and bring your brand’s references together. Or book a demo to explore Endless with your team.

Book a demo