Coding agents

Your coding agent can see what Polylane sees. Once connected, it can query telemetry across every connected provider, traverse the topology, search code and change records, read issues and their investigations, and save memories. It answers questions like "what errored in production for the service this branch deploys, in the last hour?" without you leaving the editor.

Three surfaces

Supported coding agents

Any coding agent that speaks the Model Context Protocol can connect to the MCP server. Platform MCP has per-client install steps.

The CLI works from any agent that can run shell commands, and it ships with a skill that teaches your agent when and how to reach for it. See CLI and Scripting.

Reads by default, writes behind a gate

Agent tools are read-only by default on both the MCP server and the CLI. Telemetry queries, topology traversal, and code search always work. Write tools, the ones that mutate provider resources, stay hidden and denied until you opt in:

• On the MCP server, send the x-polylane-allow-writes: true header with a credential that carries the agent_tools:write scope.
• On the CLI, pass --write to polylane tools run or polylane tools code with a credential that carries the same scope.

Even with writes enabled, a safety model screens every write call and refuses egregious ones. On the MCP server, clients that support confirmation prompts also ask you to approve each write before it runs.

Which surface to pick

• An agent living in your editor: use Platform MCP.
• Scripts, continuous integration, or terminal agents: use the CLI. Start with Authentication.
• Questions about a page you are looking at: use the browser extension.

Once connected, try a prompt like this:

Use Polylane to show me the error rate for the service this branch deploys, over the last hour, and list what changed in production for it today.