$ show upstash/context7
Context7 is a platform that delivers up-to-date, version-specific library documentation directly into AI coding assistant prompts. It operates as an MCP (Model Context Protocol) server exposing two core tools—`resolve-library-id` (converts a library name to a Context7 ID) and `query-docs` (retrieves documentation snippets for a given concept)—alongside a CLI (`ctx7`) for setup and querying, a TypeScript SDK for programmatic access, and plugins for Cursor, Claude Code, VS Code, Copilot CLI, OpenCode, and more. The architecture is client-server: the MCP server communicates with a private backend API that indexes documentation from public and private source repositories, websites, OpenAPI specs, and Confluence spaces. The CLI configures MCP servers for multiple AI coding agents by writing JSON/TOML config files and skill definitions. The SDK provides a typed client with retry, abort, and rate-limit handling. All components share a common workflow: resolve a library ID, then query documentation for a specific concept. The repository is a pnpm monorepo with packages for the MCP server (`@upstash/context7-mcp`), CLI (`ctx7`), SDK (`@upstash/context7-sdk`), Vercel AI SDK tools (`@upstash/context7-tools-ai-sdk`), and thin extensions for pi.dev and OpenCode. It includes comprehensive documentation, enterprise deployment guides (Docker, Kubernetes, on-premise), and integrations with GitHub Actions, Okta, Entra ID, and Vercel Marketplace. The codebase demonstrates strong engineering practices: command pattern in the SDK, declarative agent configuration, OpenTelemetry instrumentation with lazy loading, and secure authentication flows (OAuth, JWT, API keys). External dependencies include the Context7 backend API, Clerk for OAuth, Vercel Marketplace OIDC, and various AI coding agent platforms.
The LLM identified 4 files worth highlighting for reuse:
A reusable HTTP client with exponential backoff retry (GET only), configurable timeouts, abort signal composition, rate-limit header parsing, and per-request auth token refresh. It supports custom fetch implementations and is designed for API consumption patterns common in SDKs. The retry logic respects Retry-After headers and uses jittered backoff. This component is self-contained and could be extracted into any TypeScript project needing a resilient HTTP client.
A declarative agent configuration module that maps each supported AI coding agent (Cursor, Claude Code, VS Code, Devin, Copilot, OpenCode, Codex, Antigravity, Gemini) to its config file paths, config keys, and buildEntry functions. It centralizes all agent-specific paths and MCP server configuration logic, making it easy to add new agents by adding an entry to the map. This pattern is reusable for any CLI tool that needs to configure multiple external tools.
An OpenTelemetry instrumentation module that uses dynamic imports and lazy loading to avoid dependency overhead when telemetry is disabled. It provides a no-op fallback when OTEL_SDK_DISABLED is set, and wraps MCP server operations and sessions with spans and metrics. The design allows the MCP server to be used without any telemetry dependencies if not needed, making it a reusable pattern for any Node.js service that wants optional observability.
A unified configuration writer that reads, merges, and writes MCP server configurations in JSON, JSONC, and TOML formats. It handles partial updates (e.g., rotating API keys without corrupting unrelated config), supports removal of specific entries, and preserves file formatting. This component is self-contained and could be reused in any project that needs to programmatically manage MCP client configurations across multiple tools.