MCP Server

Use Releases as an AI agent tool server via the Model Context Protocol.

Remote server (recommended)

Connect to the hosted MCP server at https://mcp.releases.sh/mcp. No installation or API keys required — all tools are read-only and public.

Setup instructions

General

The hosted MCP server supports Streamable HTTP at:

https://mcp.releases.sh/mcp

Use that URL directly in clients with native remote MCP support. For clients that only support stdio MCP servers, use mcp-remote as a compatibility bridge.

One-click install

Click to install in a supported editor. The deeplink opens the app and prompts you to confirm before adding the server.

Add to Cursor Add to VS Code VS Code Insiders

Claude Code

claude mcp add --transport http releases https://mcp.releases.sh/mcp

Codex

codex mcp add releases --url https://mcp.releases.sh/mcp

VS Code, Windsurf, Zed, and others

For clients without native remote MCP support, use mcp-remote:

{
  "mcpServers": {
    "releases": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.releases.sh/mcp"]
    }
  }
}

Available tools

Read tools

Read-only tools available on the remote server with no authentication.

Tool	Description
`search_releases`	Hybrid search across releases and heading-aligned CHANGELOG chunks. Accepts `mode: "lexical" \| "semantic" \| "hybrid"` (default `hybrid`) and filters by product slug, organization, or release `type`. Every hit carries a `kind: "release" \| "changelog_chunk"` discriminator; chunk hits include `chunkOffset` and `chunkLength` so you can chain into `get_source_changelog` for surrounding context.
`search_registry`	Vector-backed search across orgs, products, and sources. Use this for entity lookup instead of `search_releases` when you want organization or product matches.
`get_latest_releases`	Get the most recent releases, optionally filtered by product, organization, or release `type`.
`get_release`	Fetch the full content of a single release by id. Accepts a `rel_` prefix or a bare nanoid.
`list_sources`	List all indexed changelog sources, optionally filtered to one organization.
`get_source`	Detail for a single source with org/product linkage, release count, last-fetched timestamp, and whether a CHANGELOG file is stored.
`get_source_changelog`	Read the canonical `CHANGELOG.md` tracked for a GitHub source, refreshed on every fetch. Supports heading-aligned slicing by chars (`offset` + `limit`) or by tokens (`tokens`, cl100k_base). Every response includes `totalTokens` for budget planning; token-mode responses also include `sliceTokens` for the returned chunk. Chain successive calls via `nextOffset` to page through large files (e.g. Apollo Client's 700KB CHANGELOG) without blowing out the context window. Recommended token brackets: 2000/5000/10000/20000.
`list_organizations`	List all organizations, searchable by name, slug, domain, or account handle.
`get_organization`	Detailed view of a single organization including accounts, tags, sources, products, and domain aliases.
`list_products`	List products, optionally scoped to one organization.
`get_product`	Detail for a single product with its organization, category, tags, and the sources grouped under it.

Analysis tools

AI-generated summaries and comparisons. Available on the remote server with no authentication.

Tool	Description
`summarize_changes`	AI-generated summary of recent releases for a product. Supports custom lookback window and additional instructions.
`compare_products`	Head-to-head AI comparison of releases between two products.

Example usage with Claude

Once configured, you can ask Claude to interact with the release index directly:

"What did Vercel ship last week?"
"Search for breaking changes in the Prisma changelog"
"Compare Next.js and Remix releases from the last 30 days"
"Summarize Cloudflare's recent releases, focusing on Workers"