Release notes and changelogs from across the web, indexed for agents. Also via CLI and REST API.
sh.releases/mcp (Model Context Protocol Server)
sh.releases/mcp provides an agent-friendly API for product changelogs. It acts as a unified registry of release notes pulled from vendor changelogs, normalized into a single schema, summarized, and made queryable from the terminal, code, or an MCP client.
π οΈ Key Features
Unified registry of release notes
Pulls changelogs from vendor sources
Normalizes release data into one schema
Summarizes and indexes results for query
Accessible via CLI, API, or MCP
π Use Cases
Querying the latest product releases from an MCP client
Using release notes for agent workflows
Terminal or code-based release-note retrieval
Roadmap planning based on changelog summaries
β‘ Developer Benefits
One normalized schema for changelog data
Consistent access methods via CLI, API, and MCP
Queryable, agent-readable release notes
β οΈ Limitations
The provided description does not specify authentication, rate limits, or update frequency.
Unified search across the registry and release content. Returns up to four sections β organizations, catalog entries (products + standalone sources folded into one list), curated collections (cross-org playlists), and releases with CHANGELOG chunks interleaved by relevance.
Use `type` to narrow the surfaces you want and skip the expensive paths. For example, pass `type: ['catalog']` to look up a known entity by name (fast, registry-only); pass `type: ['releases']` when you only care about release content and want to avoid entity lookups. Omit `type` to search all four.
Collections surface via two paths: a direct match on the collection's name/description (lexical in every mode, plus a vector match in hybrid/semantic mode) and a member rollup that includes every collection containing one of the matched orgs. Member rollups carry a list of result-set org slugs that triggered the rollup so a UI can render an "includes X" hint.
Use `entity` (product slug / prod_ id OR source slug / src_ id) to scope release results to one catalog entry. Product identifiers expand to every source under the product. Use `organization` to scope to a whole org. Release retrieval defaults to hybrid (FTS5 + semantic vectors fused via RRF); it silently degrades to lexical when vector infra is unavailable and flags the result.
Parameters13
query
string
required
Search query
type
array
optional
Which sections to return. Omit to return all four. Use to skip expensive paths β e.g. ['catalog'] for registry-only lookups, ['releases'] for pure release search, ['collections'] for a quick playlist lookup.
organization
string
optional
Scope release results to sources belonging to this organization. Accepts an org_ id, slug, or registered domain.
domain
string
optional
Scope to the org owning this domain. Input is normalized (scheme/path/www stripped, lowercased), so `https://vercel.com/` and `vercel.com` both work. Falls back to a 'no match' message when the domain isn't owned by anything indexed. Use this instead of `organization` when you have a URL-shaped input.
entity
string
optional
Scope release results to one catalog entry. Accepts a prod_ id (expands to every source under the product), a src_ id, or an org-scoped coordinate in the form orgSlug/slug (e.g. 'vercel/nextjs'). Bare slugs without an org prefix are not accepted.
product
string
optional
Scope release results to a specific product's sources. Accepts a prod_ id or an org-scoped coordinate in the form orgSlug/productSlug (e.g. 'vercel/next-js'). Bare slugs without an org prefix are not accepted. When both `entity` and `product` are supplied, `entity` takes precedence. The resolved product coordinate is echoed on `_meta.search.product`.
limit
number
optional
Max results per section (default 20)
mode
string
optional
Release-retrieval strategy. 'hybrid' (default) fuses FTS + vector results. 'lexical' is legacy FTS only. 'semantic' is vectors only. Falls back to lexical if vector infra is unavailable.
include_coverage
boolean
optional
Include releases grouped as coverage of another (e.g. marketing posts that re-announce a platform release). Defaults to false so each underlying launch appears once.
include_empty
boolean
optional
Include orgs with zero indexed releases in the `orgs` section. Default false β empty orgs are stubs and surface as noise. Scoping by `domain` ignores this and always returns the resolved org.
kind
string
optional
Filter to a specific source/product kind. Release hits resolve through `source.kind ?? product.kind`; catalog hits filter on the row's own kind. The orgs and collections sections are unaffected; changelog chunk hits are unaffected.
since
string
optional
Keep only release hits published at or after this bound. Accepts an ISO date/datetime (`2026-01-01`) or relative shorthand (`90d`, `4w`, `6m`, `2y`). Filters `published_at`; undated releases are dropped. Only the releases section is affected β great for capability-discovery queries like 'who added X in the last 90 days'.
until
string
optional
Keep only release hits published at or before this bound. Same input formats as `since`.
Raw schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Search query"
},
"type": {
"description": "Which sections to return. Omit to return all four. Use to skip expensive paths β e.g. ['catalog'] for registry-only lookups, ['releases'] for pure release search, ['collections'] for a quick playlist lookup.",
"type": "array",
"items": {
"type": "string",
"enum": [
"orgs",
"catalog",
"releases",
"collections"
]
}
},
"organization": {
"description": "Scope release results to sources belonging to this organization. Accepts an org_ id, slug, or registered domain.",
"type": "string"
},
"domain": {
"description": "Scope to the org owning this domain. Input is normalized (scheme/path/www stripped, lowercased), so `https://vercel.com/` and `vercel.com` both work. Falls back to a 'no match' message when the domain isn't owned by anything indexed. Use this instead of `organization` when you have a URL-shaped input.",
"type": "string"
},
"entity": {
"description": "Scope release results to one catalog entry. Accepts a prod_ id (expands to every source under the product), a src_ id, or an org-scoped coordinate in the form orgSlug/slug (e.g. 'vercel/nextjs'). Bare slugs without an org prefix are not accepted.",
"type": "string"
},
"product": {
"description": "Scope release results to a specific product's sources. Accepts a prod_ id or an org-scoped coordinate in the form orgSlug/productSlug (e.g. 'vercel/next-js'). Bare slugs without an org prefix are not accepted. When both `entity` and `product` are supplied, `entity` takes precedence. The resolved product coordinate is echoed on `_meta.search.product`.",
"type": "string"
},
"limit": {
"description": "Max results per section (default 20)",
"type": "number"
},
"mode": {
"description": "Release-retrieval strategy. 'hybrid' (default) fuses FTS + vector results. 'lexical' is legacy FTS only. 'semantic' is vectors only. Falls back to lexical if vector infra is unavailable.",
"type": "string",
"enum": [
"lexical",
"semantic",
"hybrid"
]
},
"include_coverage": {
"description": "Include releases grouped as coverage of another (e.g. marketing posts that re-announce a platform release). Defaults to false so each underlying launch appears once.",
"type": "boolean"
},
"include_empty": {
"description": "Include orgs with zero indexed releases in the `orgs` section. Default false β empty orgs are stubs and surface as noise. Scoping by `domain` ignores this and always returns the resolved org.",
"type": "boolean"
},
"kind": {
"description": "Filter to a specific source/product kind. Release hits resolve through `source.kind ?? product.kind`; catalog hits filter on the row's own kind. The orgs and collections sections are unaffected; changelog chunk hits are unaffected.",
"type": "string",
"enum": [
"platform",
"sdk",
"mobile",
"desktop",
"docs",
"integration",
"tool"
]
},
"since": {
"description": "Keep only release hits published at or after this bound. Accepts an ISO date/datetime (`2026-01-01`) or relative shorthand (`90d`, `4w`, `6m`, `2y`). Filters `published_at`; undated releases are dropped. Only the releases section is affected β great for capability-discovery queries like 'who added X in the last 90 days'.",
"type": "string"
},
"until": {
"description": "Keep only release hits published at or before this bound. Same input formats as `since`.",
"type": "string"
}
},
"required": [
"query"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}
get_latest_releases
Get the most recent releases, optionally filtered by product or organization. Excludes prereleases (canaries / alphas / betas / RCs) by default β pass `include_prereleases: true` to include them.
Cursor-paginated: pass `limit` for slice size (default 10), `cursor` to continue from a prior call. The result's `_meta.pagination` carries `kind: 'cursor'`, `hasMore`, and `nextCursor` when more rows exist; the response text echoes `nextCursor` so an LLM caller can chain without parsing `_meta`. Cursors are stable under inserts β a release added between calls won't shift the slice.
Parameters11
product
string
optional
Filter to a product's cross-source release feed. Accepts a prod_ id (expands to ALL sources under the product), a src_ id (single source), or an org-scoped coordinate in the form orgSlug/productSlug (e.g. 'vercel/next-js'). Bare slugs without an org prefix are not accepted. Mirrors the REST ?product= expansion β multi-source products (e.g. Next.js with GitHub releases + blog) return releases from all of their sources interleaved.
organization
string
optional
Filter to sources belonging to this organization. Accepts an org_ id, slug, or registered domain.
type
string
optional
Filter by release type: 'feature' for individual releases, 'rollup' for seasonal/quarterly catch-all posts. Omit to include both.
kind
string
optional
Filter to releases from sources of a specific kind. Resolves through `source.kind ?? product.kind`, so an SDK repo with no own kind still matches its product's kind. Omit to include all kinds.
limit
integer
optional
Slice size (1β200). Defaults to 10.
cursor
string
optional
Opaque continuation token from a prior call's `_meta.pagination.nextCursor`. Pass to fetch the next slice. Stale cursors are silently ignored β the call returns a fresh head of the feed.
include_coverage
boolean
optional
Include releases grouped as coverage of another (e.g. marketing posts that re-announce a platform release). Defaults to false so each underlying launch appears once.
include_prereleases
boolean
optional
Include prerelease tags (alphas, betas, RCs, canaries). Defaults to false so the feed matches the public web view.
since
string
optional
Keep only releases published at or after this bound. Accepts an ISO date/datetime (`2026-01-01`) or relative shorthand (`90d`, `4w`, `6m`, `2y`). Filters `published_at`; undated releases are dropped.
until
string
optional
Keep only releases published at or before this bound. Same input formats as `since`.
minImportance
integer
optional
Only include releases with an AI-scored `importance` >= this value (1-5; 5=landmark, 1=housekeeping). Releases with no score (unscored) are excluded when this is set. Mirrors the REST `?minImportance=` filter.
Raw schema
{
"type": "object",
"properties": {
"product": {
"description": "Filter to a product's cross-source release feed. Accepts a prod_ id (expands to ALL sources under the product), a src_ id (single source), or an org-scoped coordinate in the form orgSlug/productSlug (e.g. 'vercel/next-js'). Bare slugs without an org prefix are not accepted. Mirrors the REST ?product= expansion β multi-source products (e.g. Next.js with GitHub releases + blog) return releases from all of their sources interleaved.",
"type": "string"
},
"organization": {
"description": "Filter to sources belonging to this organization. Accepts an org_ id, slug, or registered domain.",
"type": "string"
},
"type": {
"description": "Filter by release type: 'feature' for individual releases, 'rollup' for seasonal/quarterly catch-all posts. Omit to include both.",
"type": "string",
"enum": [
"feature",
"rollup"
]
},
"kind": {
"description": "Filter to releases from sources of a specific kind. Resolves through `source.kind ?? product.kind`, so an SDK repo with no own kind still matches its product's kind. Omit to include all kinds.",
"type": "string",
"enum": [
"platform",
"sdk",
"mobile",
"desktop",
"docs",
"integration",
"tool"
]
},
"limit": {
"description": "Slice size (1β200). Defaults to 10.",
"type": "integer",
"minimum": 1,
"maximum": 200
},
"cursor": {
"description": "Opaque continuation token from a prior call's `_meta.pagination.nextCursor`. Pass to fetch the next slice. Stale cursors are silently ignored β the call returns a fresh head of the feed.",
"type": "string"
},
"include_coverage": {
"description": "Include releases grouped as coverage of another (e.g. marketing posts that re-announce a platform release). Defaults to false so each underlying launch appears once.",
"type": "boolean"
},
"include_prereleases": {
"description": "Include prerelease tags (alphas, betas, RCs, canaries). Defaults to false so the feed matches the public web view.",
"type": "boolean"
},
"since": {
"description": "Keep only releases published at or after this bound. Accepts an ISO date/datetime (`2026-01-01`) or relative shorthand (`90d`, `4w`, `6m`, `2y`). Filters `published_at`; undated releases are dropped.",
"type": "string"
},
"until": {
"description": "Keep only releases published at or before this bound. Same input formats as `since`.",
"type": "string"
},
"minImportance": {
"description": "Only include releases with an AI-scored `importance` >= this value (1-5; 5=landmark, 1=housekeeping). Releases with no score (unscored) are excluded when this is set. Mirrors the REST `?minImportance=` filter.",
"type": "integer",
"minimum": 1,
"maximum": 5
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}
list_catalog
List catalog entries β products and standalone sources combined into one list with an `entryType: 'product' | 'source'` discriminator per row.
Orgs that group multiple sources under a product (e.g. Vercel β Next.js, Turborepo) surface those products; orgs with a single source that isn't part of a product surface it directly as an `entryType: 'source'` entry. Either shape is a reasonable thing to pass to `search(entity: ...)`.
Paginated: defaults to 50 entries per page. Pass `page: 2` for the next slice. The footer surfaces the total when more pages exist.
Parameters4
organization
string
optional
Organization to scope to. Accepts an org_ id, slug, domain, or name.
kind
string
optional
Filter to catalog entries of a specific kind. Matches each row's own kind (a product's kind, or a standalone source's kind) β no sourceβproduct inheritance on this catalog surface. Omit to include all kinds.
page
integer
optional
1-based page number. Defaults to 1.
limit
integer
optional
Entries per page (1β200). Defaults to 50.
Raw schema
{
"type": "object",
"properties": {
"organization": {
"description": "Organization to scope to. Accepts an org_ id, slug, domain, or name.",
"type": "string"
},
"kind": {
"description": "Filter to catalog entries of a specific kind. Matches each row's own kind (a product's kind, or a standalone source's kind) β no sourceβproduct inheritance on this catalog surface. Omit to include all kinds.",
"type": "string",
"enum": [
"platform",
"sdk",
"mobile",
"desktop",
"docs",
"integration",
"tool"
]
},
"page": {
"description": "1-based page number. Defaults to 1.",
"type": "integer",
"minimum": 1,
"maximum": 9007199254740991
},
"limit": {
"description": "Entries per page (1β200). Defaults to 50.",
"type": "integer",
"minimum": 1,
"maximum": 200
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}
get_catalog_entry
Detail for a single catalog entry β accepts a prod_ id, src_ id, or an org-scoped coordinate in the form orgSlug/slug (e.g. 'vercel/nextjs' or 'vercel/next-js'). Returns the union of product / source detail fields depending on the entry kind. Source entries list tracked CHANGELOG files by path and byte size. Pass `include_changelog: true` to inline the root CHANGELOG, or `changelog_path` / `changelog_offset` / `changelog_limit` / `changelog_tokens` to embed a specific file or slice β heading-aligned, supports per-package files in monorepos (e.g. `packages/next/CHANGELOG.md`), and emits `totalTokens` / `sliceTokens` for LLM context budgeting. Files over 1MB are flagged as truncated so you know the tail is missing.
Parameters6
identifier
string
required
Catalog entry identifier: prod_ id, src_ id, or org-scoped coordinate orgSlug/slug (e.g. 'vercel/nextjs'). Bare slugs without an org prefix are not accepted.
include_changelog
boolean
optional
When true, inline the root tracked CHANGELOG for a source-kind entry. Ignored for products.
changelog_path
string
optional
Specific CHANGELOG path for a source-kind entry (e.g. 'packages/next/CHANGELOG.md'). Passing this implies include_changelog.
changelog_offset
number
optional
Character offset into the selected CHANGELOG. Snapped forward to the next heading unless 0. Passing this implies include_changelog.
changelog_limit
number
optional
Target slice size in characters. Slice ends at a heading boundary. Defaults to 40000 when slicing without a token budget. Passing this implies include_changelog.
changelog_tokens
number
optional
Target slice size in tokens (cl100k_base). Takes precedence over changelog_limit. Recommended brackets: 2000, 5000, 10000, 20000. Passing this implies include_changelog.
Raw schema
{
"type": "object",
"properties": {
"identifier": {
"type": "string",
"description": "Catalog entry identifier: prod_ id, src_ id, or org-scoped coordinate orgSlug/slug (e.g. 'vercel/nextjs'). Bare slugs without an org prefix are not accepted."
},
"include_changelog": {
"description": "When true, inline the root tracked CHANGELOG for a source-kind entry. Ignored for products.",
"type": "boolean"
},
"changelog_path": {
"description": "Specific CHANGELOG path for a source-kind entry (e.g. 'packages/next/CHANGELOG.md'). Passing this implies include_changelog.",
"type": "string"
},
"changelog_offset": {
"description": "Character offset into the selected CHANGELOG. Snapped forward to the next heading unless 0. Passing this implies include_changelog.",
"type": "number"
},
"changelog_limit": {
"description": "Target slice size in characters. Slice ends at a heading boundary. Defaults to 40000 when slicing without a token budget. Passing this implies include_changelog.",
"type": "number"
},
"changelog_tokens": {
"description": "Target slice size in tokens (cl100k_base). Takes precedence over changelog_limit. Recommended brackets: 2000, 5000, 10000, 20000. Passing this implies include_changelog.",
"type": "number"
}
},
"required": [
"identifier"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}
list_organizations
List all indexed organizations, optionally filtered. Paginated: defaults to 50 entries per page; pass `page: 2` for the next slice. Orgs with zero indexed releases are hidden by default (curator-stub noise); set `include_empty: true` to see them.
Parameters6
query
string
optional
Search across org name, slug, domain, and account handles
platform
string
optional
Filter to orgs with an account on this platform
include_empty
boolean
optional
Include orgs with zero indexed releases. Default false β empty orgs are stubs from in-flight discovery or broken parsers and surface as noise on the public catalog.
category
string
optional
Filter to a single category slug (e.g. `ai`, `devops`). Aliases (e.g. `e-commerce`) resolve to their canonical category (`commerce`); unknown values are ignored (unfiltered).
page
integer
optional
1-based page number. Defaults to 1.
limit
integer
optional
Entries per page (1β200). Defaults to 50.
Raw schema
{
"type": "object",
"properties": {
"query": {
"description": "Search across org name, slug, domain, and account handles",
"type": "string"
},
"platform": {
"description": "Filter to orgs with an account on this platform",
"type": "string"
},
"include_empty": {
"description": "Include orgs with zero indexed releases. Default false β empty orgs are stubs from in-flight discovery or broken parsers and surface as noise on the public catalog.",
"type": "boolean"
},
"category": {
"description": "Filter to a single category slug (e.g. `ai`, `devops`). Aliases (e.g. `e-commerce`) resolve to their canonical category (`commerce`); unknown values are ignored (unfiltered).",
"type": "string"
},
"page": {
"description": "1-based page number. Defaults to 1.",
"type": "integer",
"minimum": 1,
"maximum": 9007199254740991
},
"limit": {
"description": "Entries per page (1β200). Defaults to 50.",
"type": "integer",
"minimum": 1,
"maximum": 200
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}
get_organization
Get detailed information about a single organization β accounts, tags, sources, products, aliases. When an AI-generated overview exists the response includes a short preview; pass `include_overview: true` to inline the full briefing (with a stale warning if the content is older than 30 days since last write).
Parameters2
identifier
string
required
Organization identifier. Accepts an org_ id, slug, domain, name, or account handle.
include_overview
boolean
optional
When true, inline the full AI-generated overview instead of the default first-paragraph preview.
Raw schema
{
"type": "object",
"properties": {
"identifier": {
"type": "string",
"description": "Organization identifier. Accepts an org_ id, slug, domain, name, or account handle."
},
"include_overview": {
"description": "When true, inline the full AI-generated overview instead of the default first-paragraph preview.",
"type": "boolean"
}
},
"required": [
"identifier"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}
lookup_domain
Resolve a domain to the org or product that owns it. The domain is normalized first (scheme, `www.`, path, and trailing slash stripped, lowercased), so `https://vercel.com/about` and `vercel.com` both look up the same row.
Returns the matching org (with primary-vs-alias distinction) and any products whose alias targets the same domain. Pure resolution β does not probe the domain or materialize anything; unknown domains surface a 'no match' message. Use `lookup_domain` when you have a URL-shaped input; use `get_organization` when you already have a slug or id.
Parameters1
domain
string
required
Domain to resolve. Any URL-shaped form is accepted; the server normalizes it.
Raw schema
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Domain to resolve. Any URL-shaped form is accepted; the server normalizes it."
}
},
"required": [
"domain"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}
list_collections
List curated collections β named cross-org playlists (e.g. 'Frontier AI Labs') independent of the fixed category taxonomy.
Use `get_collection` for a collection's full member list, or `get_collection_releases` for the interleaved cross-org release feed. Paginated: defaults to 50 entries per page; pass `page: 2` for the next slice.
Detail for a single collection β name, description, and the ordered list of member organizations. Hidden / on-demand orgs never leak through; only publicly visible orgs appear in the member list.
Interleaved cross-org release feed for a collection β same shape as `get_latest_releases` but scoped to the collection's member orgs.
Cursor-paginated: pass `limit` for slice size (default 20), `cursor` to continue from a prior call. The result's `_meta.pagination` carries `kind: 'cursor'`, `hasMore`, and `nextCursor` when more rows exist; the response text echoes `nextCursor` so an LLM caller can chain without parsing `_meta`. Cursors are stable under inserts.
Parameters4
slug
string
required
Collection slug (e.g. 'frontier-ai-labs').
limit
integer
optional
Slice size (1β200). Defaults to 20.
cursor
string
optional
Opaque continuation token from a prior call's `_meta.pagination.nextCursor`. Stale cursors are silently ignored β the call returns a fresh head of the feed.
include_prereleases
boolean
optional
Include prerelease tags (alphas, betas, RCs). Defaults to false so the feed matches the public web view.
Raw schema
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Collection slug (e.g. 'frontier-ai-labs')."
},
"limit": {
"description": "Slice size (1β200). Defaults to 20.",
"type": "integer",
"minimum": 1,
"maximum": 200
},
"cursor": {
"description": "Opaque continuation token from a prior call's `_meta.pagination.nextCursor`. Stale cursors are silently ignored β the call returns a fresh head of the feed.",
"type": "string"
},
"include_prereleases": {
"description": "Include prerelease tags (alphas, betas, RCs). Defaults to false so the feed matches the public web view.",
"type": "boolean"
}
},
"required": [
"slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}
get_release
Fetch the full content of a single release by id. Release ids are returned by search or get_latest_releases β pass them here to read the whole entry (e.g. to quote a specific Next.js release note). Accepts the full rel_<nanoid> form or the bare 21-char nanoid.
Parameters1
id
string
required
Release id β 'rel_<nanoid>' or a bare 21-char nanoid
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Release id β 'rel_<nanoid>' or a bare 21-char nanoid"
}
},
"required": [
"id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}
follow
Follow an organization or a product so it appears in your personalized feed (`get_personalized_feed`). Following an organization implicitly includes all of its products.
Requires a signed-in user (a `relu_` user key or an OAuth token). `entity` is a typed id β an `org_β¦` id or a `prod_β¦` id β as returned by `search`, `get_organization`, or `get_catalog_entry`. Idempotent: following something you already follow is a no-op.
Parameters1
entity
string
required
Entity to follow β an `org_β¦` or `prod_β¦` id (from search / get_* results).
Raw schema
{
"type": "object",
"properties": {
"entity": {
"type": "string",
"description": "Entity to follow β an `org_β¦` or `prod_β¦` id (from search / get_* results)."
}
},
"required": [
"entity"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}
unfollow
Stop following an organization or product. Requires a signed-in user. `entity` is an `org_β¦` or `prod_β¦` id. Idempotent: unfollowing something you don't follow is a no-op.
Parameters1
entity
string
required
Entity to unfollow β an `org_β¦` or `prod_β¦` id.
Raw schema
{
"type": "object",
"properties": {
"entity": {
"type": "string",
"description": "Entity to unfollow β an `org_β¦` or `prod_β¦` id."
}
},
"required": [
"entity"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}
list_follows
List the organizations and products you follow (newest first). Requires a signed-in user.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {}
}
get_personalized_feed
Your personalized release feed β recent releases from the organizations and products you follow, newest first. Requires a signed-in user. Same item shape as `get_latest_releases`, scoped to your follows.
Cursor-paginated: pass `cursor` from a prior response's `_meta.pagination.nextCursor` and optional `limit` (1β100, default 30).
Parameters2
cursor
string
optional
Opaque cursor from a previous page's `_meta.pagination.nextCursor`.
limit
integer
optional
Entries per page (1β100). Defaults to 30.
Raw schema
{
"type": "object",
"properties": {
"cursor": {
"description": "Opaque cursor from a previous page's `_meta.pagination.nextCursor`.",
"type": "string"
},
"limit": {
"description": "Entries per page (1β100). Defaults to 30.",
"type": "integer",
"minimum": 1,
"maximum": 100
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}
list_webhooks
List your outbound release webhooks, personal or workspace. Requires a signed-in user (a `relu_` user key or an OAuth token).
With no `workspace`, lists your personal webhooks (`GET /v1/me/webhooks`) and includes a short list of your workspaces (id, slug, role) so you can target one next. Pass `workspace` (an id or a slug) to list that workspace's webhooks instead. Pass `id` to see one webhook plus its 10 most recent deliveries. Pass `enabled` to filter by enabled/disabled state.
Parameters3
workspace
string
optional
Workspace id or slug. Omit for your personal webhooks.
id
string
optional
Show one webhook (with recent deliveries) instead of the full list.
enabled
boolean
optional
Filter to enabled or disabled webhooks.
Raw schema
{
"type": "object",
"properties": {
"workspace": {
"description": "Workspace id or slug. Omit for your personal webhooks.",
"type": "string"
},
"id": {
"description": "Show one webhook (with recent deliveries) instead of the full list.",
"type": "string"
},
"enabled": {
"description": "Filter to enabled or disabled webhooks.",
"type": "boolean"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}
manage_webhook
Create, update, delete, test, or rotate the signing key of an outbound release webhook β personal or workspace. Requires a signed-in user. This tool sends requests to an external URL you supply and can delete or disable delivery, so treat it as a write.
Pass `workspace` (an id or slug) to act on a workspace's webhooks instead of your personal ones; workspace webhooks are always org-scoped (`scope: "follows"` is personal-only and is rejected up front). Only workspace owners and admins can create, update, delete, or rotate a workspace webhook β any member can test one.
`action: "create"` needs `url` and `format` (`json`, `slack`, or `discord`), plus either `scope: "follows"` (personal only β everything you follow) or an org-scoped target: `org` (an org slug or `org_β¦` id), optionally narrowed by `product` (slug or `prod_β¦` id) or `source` (slug or `src_β¦` id). `action: "update"` needs `id` plus any fields to change; pass `source: null` or `product: null` to clear a filter. `action: "delete"`, `action: "test"`, and `action: "rotate_secret"` need only `id`.
`create` and `rotate_secret` return a one-time `signingKey` for `json`-format webhooks β store it now, it will not be shown again. `slack` and `discord` deliveries aren't signed, so those formats never return one.
Parameters12
action
string
required
workspace
string
optional
Workspace id or slug. Omit to act on your personal webhooks.
id
string
optional
Webhook id β required for update, delete, test, and rotate_secret.
url
string
optional
Delivery URL. Required for create.
scope
string
optional
Create only. "follows" is personal-only and defaults org-scoped when omitted.
org
string
optional
Org slug or org_β¦ id. Required for an org-scoped create.
product
any
optional
Product slug or prod_β¦ id to narrow an org-scoped webhook. null clears it on update.
source
any
optional
Source slug or src_β¦ id to narrow an org-scoped webhook. null clears it on update.
releaseType
string
optional
Optional filter on release taxonomy type.
format
string
optional
Delivery format.
description
string
optional
Freeform label for the webhook.
enabled
boolean
optional
Update only. Enable or disable delivery.
Raw schema
{
"type": "object",
"properties": {
"action": {
"type": "string",
"enum": [
"create",
"update",
"delete",
"test",
"rotate_secret"
]
},
"workspace": {
"description": "Workspace id or slug. Omit to act on your personal webhooks.",
"type": "string"
},
"id": {
"description": "Webhook id β required for update, delete, test, and rotate_secret.",
"type": "string"
},
"url": {
"description": "Delivery URL. Required for create.",
"type": "string"
},
"scope": {
"description": "Create only. \"follows\" is personal-only and defaults org-scoped when omitted.",
"type": "string",
"enum": [
"org",
"follows"
]
},
"org": {
"description": "Org slug or org_β¦ id. Required for an org-scoped create.",
"type": "string"
},
"product": {
"description": "Product slug or prod_β¦ id to narrow an org-scoped webhook. null clears it on update.",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"source": {
"description": "Source slug or src_β¦ id to narrow an org-scoped webhook. null clears it on update.",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"releaseType": {
"description": "Optional filter on release taxonomy type.",
"type": "string",
"enum": [
"feature",
"rollup"
]
},
"format": {
"description": "Delivery format.",
"type": "string",
"enum": [
"json",
"slack",
"discord"
]
},
"description": {
"description": "Freeform label for the webhook.",
"type": "string"
},
"enabled": {
"description": "Update only. Enable or disable delivery.",
"type": "boolean"
}
},
"required": [
"action"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}
whats_changed
Given a package and a `from`/`to` version, return the changelog entries between them β `(from, to]`, from exclusive, to inclusive β with summaries and breaking-change verdicts. One call instead of reading N changelog pages to plan an upgrade.
`package` is a tracked source slug or a GitHub `owner/repo` coordinate (set `ecosystem: "github"` for a bare coordinate). Reads already-indexed releases only. If the package isn't in the catalog you'll get a clear 'not tracked' answer (npm/PyPI names may not be mapped to a source yet).
Parameters5
package
string
required
Package identifier β a source slug or a GitHub "owner/repo" coordinate.
from
string
required
Version you're upgrading FROM (exclusive).
to
string
required
Version you're upgrading TO (inclusive).
ecosystem
string
optional
Optional resolution hint; "github" enables matching a bare owner/repo.
minImportance
integer
optional
Only include entries with an AI-scored `importance` >= this value (1-5; 5=landmark, 1=housekeeping). Entries with no score (unscored) are excluded when this is set.
Raw schema
{
"type": "object",
"properties": {
"package": {
"type": "string",
"description": "Package identifier β a source slug or a GitHub \"owner/repo\" coordinate."
},
"from": {
"type": "string",
"description": "Version you're upgrading FROM (exclusive)."
},
"to": {
"type": "string",
"description": "Version you're upgrading TO (inclusive)."
},
"ecosystem": {
"description": "Optional resolution hint; \"github\" enables matching a bare owner/repo.",
"type": "string",
"enum": [
"npm",
"pypi",
"github"
]
},
"minImportance": {
"description": "Only include entries with an AI-scored `importance` >= this value (1-5; 5=landmark, 1=housekeeping). Entries with no score (unscored) are excluded when this is set.",
"type": "integer",
"minimum": 1,
"maximum": 5
}
},
"required": [
"package",
"from",
"to"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}
A registry of release notes from across the web β pulled from vendor changelogs,
normalized into one schema, summarized, and queryable from your terminal, your
code, or any MCP client. Readable by you and your agent.
"What changed?" is a question agents and developers ask constantly β before an
upgrade, after an incident, when a tool suddenly behaves differently. The answer
is scattered across GitHub releases, RSS feeds, changelog pages, and blog posts
in a hundred different formats.
Release Notes Index collects those into one registry. It watches hundreds of sources
across the vendors developers actually depend on, and for every release stores
the original content plus an AI-generated title, summary, and breaking-change
classification. Each organization gets a maintained overview of what it shipped
recently. The web page a human reads and the JSON an agent fetches are the same
content.
This repo is the source of the canonical deployment at
releases.sh: the API worker (the authoritative data
plane), the MCP server, the web frontend, and the ingest pipeline + agent
harness that keep the registry fresh. The user-facing CLI lives in apps/cli/ and
ships from this repo (npm + Homebrew).
Use it
No account or API key needed for reads β all four surfaces are public.
MCP β hosted at agents.releases.sh/mcp (mcp.releases.sh/mcp still
works), listed in the
MCP Registry
as sh.releases/mcp, and in the
Claude connector directory for Claude on the web, desktop, and mobile:
Agent skills β auto-triggering playbooks, installable into any agent (Claude
Code / Codex / Cursor / OpenCode) without checking out anything. Start with the
reader skills β search, MCP lookups, and release analysis β which is what almost
everyone wants:
bash
npx skills add buildinternet/releases # reader skills β search, MCP, release analysis# just the skill that writes a releases.json manifest for your own product
npx skills add buildinternet/releases --skill creating-releases-json
On Claude Code, the CLI repo also installs as a plugin β the reader skills plus
a bundled MCP connection and a /releases command:
Running or maintaining the registry itself? This repo also ships
operator skills (source onboarding, parsing, bulk maintenance) β most need
an admin key: npx skills add buildinternet/releases. See
releases.sh/docs/skills.
Storage β Cloudflare D1 (FTS5 + Vectorize). The API worker is the sole data plane.
Ingest β adapters for GitHub Releases, RSS/Atom/JSON feeds, and a browser-rendering fallback for feed-less pages (packages/adapters/). The crawler signs outbound fetches (RFC 9421) as a Cloudflare Verified Bot.
AI β changelog parsing, summarization, grouping, and org overviews run in the API worker as direct Anthropic SDK calls.
Contributor mental model
This repo has four kinds of code:
Area
Paths
What to know
Product surfaces
apps/api/, apps/mcp/, apps/webhooks/, apps/web/
The API worker is the data plane. Web, MCP, CLI, and webhooks read from or route through it.
Architecture docs are maintained references. Plans and specs are point-in-time design history.
For normal contributions, start with bun run bootstrap, bun run check, and
bun run test. You do not need production Cloudflare, Anthropic, Vercel, email, or
Firecrawl access to work on the core loop. If you are trying to fork or
self-host the full service, read
deploy-coupling.md.
Per-package detail and project conventions live in AGENTS.md β the
agent entry point for working in this repo. Architecture deep-dives are in
docs/architecture/, with a reader's guide at
docs/README.md.
Local development
Prerequisites:Bun. No external accounts needed for the
core loop:
bash
bun run bootstrap # one-command setup: tooling, deps, env files, local D1
bun run doctor # diagnose the setup β reports what's missing and how to fix it
bun run check # lint + type-check + format (the CI gate)
bun run test# full test suite, secret-free
bun run dev:api # API worker on local D1
bun run dev:web # Next.js frontend
bootstrap is idempotent (safe to re-run; never overwrites your env files or
wipes the local DB) and doctor is read-only. Prefer the manual steps? They're
bun install, copy each *.example env file, then bun run db:reset:local.
AI passes, scrape fetches, and semantic search take your own keys
(ANTHROPIC_API_KEY, Cloudflare Browser Rendering, VOYAGE_API_KEY) and
degrade gracefully without them. Setup detail, environment variables, testing,
deployment, and the full no-accounts / bring-your-own-keys / hosted-only
breakdown live in CONTRIBUTING.md.