Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 12 additions & 0 deletions release-notes.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -31,10 +31,22 @@ description: "New features, fixes, and improvements for the Runpod platform."

You can now request a GPU that's currently out of capacity and get notified by email when it becomes available. Runpod saves your pod configuration so you can deploy immediately when capacity returns.

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The "Sign in with Runpod" entry is based on PR #27, which added the hosted Streamable HTTP transport and the OAuth "Sign in with Runpod" flow (stateless token passthrough, no API key stored on disk) while leaving the existing local stdio + API key mode unchanged. This shipped in @runpod/mcp-server@1.3.0 (npm publish 2026-06-18), placing it in the June 2026 section.

Source: runpod/runpod-mcp#27


<h4><Badge color="green">New Release</Badge> Sign in with Runpod for the MCP server</h4>

You can now connect AI coding agents to a hosted [Runpod MCP server](/get-started/mcp-servers) over HTTP and authenticate with the "Sign in with Runpod" OAuth flow, so you no longer need to store a Runpod API key on disk. Local connections that use an API key continue to work as before.

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The "Expanded MCP server tools and REST API v2" entry draws on the @runpod/mcp-server@2.0.0 release (PR #50 changeset): defaulting REST to v2 (v2-rest.runpod.io/v2), the create-endpoint move from the v1 templateId model to the v2 inline-config imageName + gpuPoolIds model with RUNPOD_REST_VERSION=v1 as the opt-out, and the v2-only tags/billing/endpoint-workers/catalog tools. Serverless job tools and GPU/data-center discovery come from the earlier 1.2.0 release (npm publish 2026-06-05); 2.0.0 published 2026-06-29.

Source: runpod/runpod-mcp#50


<h4><Badge color="green">New Release</Badge> Expanded MCP server tools and REST API v2</h4>

The [Runpod MCP server](/get-started/mcp-servers) now covers more of the platform: you can run and manage Serverless jobs, discover GPU types and data centers, and manage tags, billing, and endpoint workers through natural language. List results are now paginated, and the server defaults to the Runpod REST API v2. Note that `create-endpoint` now takes an image name and GPU pool instead of a template ID; set `RUNPOD_REST_VERSION=v1` to keep the previous behavior.

<h4><Badge color="blue">Improvement</Badge> Hub navigation consolidated</h4>

Hub navigation items are now consolidated into a single unified entry, making it easier to find templates and repos.

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The "Guided install command" entry is based on the @runpod/mcp-server@1.4.0 changeset in PR #33, which added the npx @runpod/mcp-server@latest add wizard that detects installed agents (Claude Code, Claude Desktop, Cursor, Windsurf, VS Code) and writes MCP config for each selected one, with remove to undo. Published to npm 2026-06-26, so it belongs in the June 2026 section.

Source: runpod/runpod-mcp#33


<h4><Badge color="blue">Improvement</Badge> Guided install command for the MCP server</h4>

Running `npx @runpod/mcp-server add` now detects your installed agents — Claude Code, Claude Desktop, Cursor, Windsurf, and VS Code — and writes the [MCP configuration](/get-started/mcp-servers) for each one you select. Run `remove` to undo those changes.

<h4><Badge color="red">Bug Fix</Badge> Billing records now show correct data for deleted resources</h4>

SKU, region, and creation timestamps now appear correctly in [billing views and exports](/pods/pricing) for deleted Pods and network volumes.
Expand Down
Loading