For coding agents
A Cobalt review is built to be read by an AI coding agent — the notes, the annotations, and the screenshots, in a form it can act on. Two ways to connect.
1 · MCP server
Connect the Cobalt MCP server and your agent can pull any review — the reviewer's notes as text plus each annotated screenshot as a real image. This is the highest-fidelity path: the agent sees the arrows, boxes, and labels, not just a link.
claude mcp add --transport http cobalt https://cobaltcapture.com/mcpClaude Code shown. Cursor, Codex, and other MCP clients use the same endpoint — https://cobaltcapture.com/mcp — over the Streamable HTTP transport.
Tool: get_review
One tool. Give it a review URL (/r/<slug> or /s/<slug>) or a bare slug, and it returns the review markdown followed by each composed screenshot (annotations burned in) as an image/png block. Then just ask your agent: "Read the Cobalt review <url> and make the changes it asks for."
Machine-readable manifest: /.well-known/mcp.json. Public reviews only — no auth, the same access as opening the link in a browser.
2 · Or just paste the link
No setup required. When an AI fetcher opens a review URL, Cobalt serves the markdown export instead of the HTML page — with the reviewer's annotations described in text and a note telling the agent to fetch and view each screenshot. Works in any agent that can browse the web.
You can also grab the same markdown yourself from any review's share section (Copy as markdown), or append /markdown to a review URL.
There's no separate REST API — a review's shareable URL, its markdown, and the MCP server above are the whole agent-facing surface.