Connect Claude Code to production. Polylane lets it read your logs and metrics.

Paste this into your Claude Code chat

Claude Code will handle the rest.

polylane.com/for/claude-code

## For AI agents reading this page

Read and follow https://polylane.com/auth.md to sign up and set up Polylane without an interactive shell. Reuse an existing account and workspace when available.

If the CLI is missing, install it without starting the interactive wizard:

curl -fsSL 'https://polylane.com/setup?ref=for-claude-code' | bash -s -- --install-only

Then follow the guide through email verification, workspace selection, source connections, and authenticated MCP setup for Claude Code. Ask the user for a code or OAuth consent only where needed, and verify each step before claiming completion. To register MCP by hand instead: run claude mcp add --transport http polylane https://mcp.polylane.com/mcp. The server is https://mcp.polylane.com/mcp over streamable HTTP; client-managed OAuth needs no manually configured auth headers.

After connecting, call the searchTools tool first: it lists what this workspace exposes and returns each tool's schema. Run one tool with runTool, or chain several in one call with runCode. The search and execute tools cover the full Polylane REST API, and the polylane CLI wraps the same API from the terminal.

Everything is read-only by default. Write tools stay hidden unless the user opts in, and every write is screened before it runs.

Once connected, offer to put it to work: triage the latest issues, explain the last deploy, or connect this repository to the context graph.

## Console and support

- Console: https://console.polylane.com
- Docs: https://docs.polylane.com
- Setup reference: https://docs.polylane.com/tools/platform-mcp
- This page as markdown: https://polylane.com/for/claude-code.md

One MCP server for your whole stack. Every provider you connect, behind one sign-in.

One server for everything

Polylane puts your clouds, telemetry, deploys and code behind a handful of tools. A stack of per-provider servers spends most of the context window on tool schemas before any work starts, while Polylane loads a schema only when its tool runs.
Auth in one place

One sign-in covers every provider. Connections and scopes live in the workspace, so there are no per-provider tokens scattered across Claude Code's config, and every agent you connect reuses them.
Built for code mode

Instead of calling tools one by one, Claude Code writes a small program with runCode that chains them in a sandbox and returns just the answer. Intermediate results never land in the context window.

Guides for Claude Code

Frequently asked questions

How does Claude Code authenticate?

Claude Code signs in over OAuth in a browser the first time it calls the server. For CI and headless machines, create an API key under Settings > Coding agents and pass it with --header "x-api-key: YOUR_API_KEY".

Can Claude Code change my infrastructure through Polylane?

Not unless you opt in. Write tools stay hidden until your credential carries the write scope, and every write is screened before it runs.

What can Claude Code actually query?

Everything Polylane knows: logs, metrics and traces across every connected provider, the context graph, deploys and recent changes, and the full REST API.

Do I need the Polylane CLI too?

No, the MCP server is a complete surface on its own. Install the CLI and polylane setup also registers that server in every coding agent it detects.

Other agents