Ref MCP is a ModelContextProtocol server that provides AI coding tools access to documentation for APIs, services, and libraries in a token-efficient manner.
From the registry: Token efficient search for coding agents over public and private documentation.

Please install the `ref-tools-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Ref API Key** — Sign up at ref.tools to get an API key (https://ref.tools)
Canonical MCP server config (HTTP transport):
- url: `https://api.ref.tools/mcp`
- headers:
- `x-ref-api-key`: `<your-api-key>`
Note: Documentation search and retrieval for AI coding agents. Token-efficient: filters repeated results per session, returns only relevant page sections. 2 tools: ref_search_documentation, ref_read_url. Also available as stdio: npx ref-tools-mcp with REF_API_KEY env var.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.REF_API_KEYrequiredAPI key required to access the Ref MCP server.Real-time Kubernetes network traffic visibility and API analysis for HTTP, gRPC, Redis, Kafka, DNS.