Changelogs for apps, games and operating systems. Ask what shipped since the version you run.
Scored across 5 tools
Each tool targets a distinct action: listing products, searching releases, fetching newest releases, analyzing outdated dependencies, and providing upgrade notes. Even though search_releases and whats_new both deal with releases, their purposes are clearly separated by search vs. product-specific retrieval.
All tool names use lowercase snake_case and follow a noun-oriented pattern (list_products, missing_changes, search_releases, upgrade_notes, whats_new). While not strictly verb_noun (e.g., missing_changes is adjective_noun, whats_new is noun_adjective), the style is consistent and predictable.
With 5 tools, the server is well-scoped and each tool covers a distinct aspect of release tracking and dependency updates. No tool feels redundant or missing, and the count is within the ideal range for a focused MCP server.
The tool surface covers the core workflows: discovering products, searching releases, getting recent updates, identifying outdated dependencies, and retrieving upgrade details. There are no obvious dead ends—users can go from listing products to checking specific release notes or planning upgrades.
The products What's New tracks release notes for, with slugs, categories and platforms. Filter by category and/or a name query.
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | "popular" ranks by current audience popularity — outside signals (stars, downloads, players) blended with this site's own readers — and answers "what are the most popular software right now?". Default is the curated catalog order (or search relevance when query is set, which ignores sort). | |
| query | No | Filter by name, e.g. "terminal" or "jetbrains". | |
| category | No | Limit results to one product category. |
| Name | Required | Description |
|---|---|---|
| total | Yes | Matches before the cap. |
| products | Yes | |
| returned | Yes | |
| truncated | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds the return shape and filter behavior, but sort semantics and result details are left to the schema and output schema. This is a modest addition, not a contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences convey scope, returned fields, and filtering behavior with no filler. The most important information is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a list tool with zero required parameters, fully documented parameters, an output schema, and safety annotations, the description is sufficient for correct invocation. Only minor improvement would be explicit guidance on choosing this over search_releases or whats_new, but that is not essential here.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the schema gives detailed descriptions for sort and category. The description adds the useful summary that filters can be combined, but it does not materially extend what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb ('List') and a specific resource ('products What's New tracks release notes for'), and identifies the returned fields ('slugs, categories and platforms'). It is clearly distinct from siblings like search_releases and whats_new, which target release searching and news rather than the product catalog.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description frames this as the catalog of tracked products and mentions the available filters ('category and/or a name query'), giving clear context for when to call it. It does not explicitly contrast with search_releases or whats_new, but the resource distinction is implied strongly enough to select correctly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
For a whole project's outdated report — npm/pnpm outdated --json (current → from, wanted, latest), ncu --format installedVersion, pip or uv pip list --outdated --format json (version → from, latest_version → latest), go list -m -u -json all (Version → from, Update.Version → latest), cargo outdated, dotnet list package --outdated, a Gradle versions report — pass each package with the version installed and, where the tool gives them, wanted and latest. Answers what the project is missing, most exposed first: per package, the security releases, CVE ids and fixes it does not have, split into toWanted (from → wanted: reachable by an update within the declared range, no manifest edit) and toLatest (→ latest: needs the range changed), with the cost of moving beside them (major bump, breaking mentions, removed/deprecated) and a few of the fixes themselves. Counts are deterministic over every tracked release; no model judged anything. Up to 100 packages a call. Pass repository (from the package's own package.json) for scoped or renamed packages; a Maven, Go or NuGet package goes by its purl. For the vendor's own breaking-change and migration sections, call upgrade_notes on the packages worth moving. A Maven, Go or NuGet package this server does not track is checked against deps.dev after the answer and counted; pass recordMisses: false for private packages.
| Name | Required | Description | Default |
|---|---|---|---|
| dependencies | Yes | Up to 100 per call; split a larger project. | |
| recordMisses | No | Default true. A Maven, Go or NuGet package this server does not track is checked against deps.dev after the answer and counted per day, with nothing about the caller, to decide what to track next. Pass false for private packages. |
| Name | Required | Description |
|---|---|---|
| notes | No | |
| summary | Yes | |
| dependencies | Yes | Most exposed first — CVEs, then security releases, then fixes, then releases behind; untracked last, in the order given. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate readOnlyHint, openWorldHint, idempotentHint, so the tool is safe and deterministic. The description adds behavior beyond annotations: it states determinism and no model judgment, which is useful. It also discloses that unmatched Maven/Go/NuGet packages are checked against deps.dev after the answer and counted, which is a side-effect not obvious from annotations. However, it doesn't detail the exact output structure (though output schema exists) or potential rate limits. Given annotations cover major behavioral traits, the extra specifics earn a 3.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but packed with necessary context. It front-loads the core purpose and output decomposition, then details input formats, limits, and special cases. Each sentence carries operational value, but it is verbose; could be trimmed without losing meaning. Still, the efficiency is high given the complexity of the tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (multiple ecosystems, many parameters, and an output schema that likely defines return structure), the description is thorough. It covers input format, edge cases (scoped packages, private packages), limits, and when to delegate to the sibling. A slight gap: it doesn't explicitly describe the exact output schema structure, but since the output schema is provided, that's not necessary. The description effectively covers everything an agent needs to call it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema thoroughly documents each parameter. The description adds context beyond the schema by explaining version fields (current → from, wanted, latest) and the meaning of toWanted/toLatest split, but most parameter semantics are already in the schema. It adds value in clarifying the distinction between wanted/latest and the repository field, but not substantially beyond the schema, so a baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states what the tool does: it takes outdated package reports and computes what the project is missing in terms of security updates, CVEs, and fixes, split into toWanted and toLatest. It distinguishes from siblings like upgrade_notes (which is for vendor breaking-change sections) and what's_new/list_products by focusing on missing updates from outdated reports.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly describes when to use the tool (for any ecosystem's outdated report, to find missing security patches) and when not (for vendor's own breaking-change/migration sections, call upgrade_notes). It also specifies conditions such as passing repository for scoped packages and recordMisses: false for private packages, and notes up to 100 packages per call with splitting for larger projects.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Full-catalog search across product names and release history. Returns matching products and releases with permalinks.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search products and release notes. At least 2 characters. | |
| category | No | Limit results to one product category. |
| Name | Required | Description |
|---|---|---|
| note | No | Present when nothing matched. |
| query | Yes | The query as searched — trimmed and capped. |
| category | No | Limit results to one product category. |
| products | Yes | |
| releases | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already communicate readOnlyHint, idempotentHint, and openWorldHint=false, so the safety profile is covered. The description adds the 'full-catalog' scope and the fact that results include permalinks, which is useful context. It does not disclose behavior like pagination, result limits, ordering, or match semantics, but given the annotations, the additional burden is modest.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence conveys scope, action, and return value with no filler. The key differentiator (full-catalog coverage) is front-loaded, and every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of a complete input schema, an output schema, and informative annotations, the description is nearly sufficient on its own. The main gap is the lack of any note about result size, sorting, or how matching works, but for a simple read-only search these are minor and largely inferable from the schema and output contract.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents both parameters. The description adds no parameter-specific semantics beyond what is in the schema; it does not clarify the format or behavior of the query beyond 'search products and release notes', nor does it elaborate on the category filter. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('search') and names its resource precisely: 'full-catalog search across product names and release history.' It also states what is returned (matching products and releases with permalinks), making its scope clear even without inspecting the schema. This distinguishes it from sibling tools like list_products or whats_new.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context: it is a search tool for finding specific products or releases across the full catalog. However, it does not explicitly say when to prefer this over list_products or whats_new, nor does it mention any exclusions or scenarios where an alternative should be used.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Before or after upgrading dependencies — package.json / lockfile / requirements changes, npm update, pip install -U, a Gradle version catalog, go.mod, a workflow's actions — pass each package with the version you run and the version you are moving to. Returns every tracked release in between with the vendor's own breaking-change, deprecation, migration and security sections verbatim, the categorized change list, CVE ids and deterministic signals (major bump, removed/deprecated items, breaking mentions) — including breaking changes shipped in minor or patch versions. Pass repository (from the package's own package.json) for scoped or renamed packages; it makes the match exact. A Maven/Gradle, Go, NuGet or GitHub Actions package goes by its purl (e.g. pkg:maven/com.squareup.okhttp3/okhttp), or by its own coordinate as the name (group:artifact, a module path, owner/repo@ref), and is matched exactly or not at all. A Maven, Go or NuGet package this server does not track is checked against deps.dev after the answer and counted, to decide what to track next; pass recordMisses: false for private packages.
| Name | Required | Description | Default |
|---|---|---|---|
| dependencies | Yes | Up to 20 per call; split a larger upgrade. | |
| recordMisses | No | Default true. A Maven, Go or NuGet package this server does not track is checked against deps.dev after the answer and counted per day, with nothing about the caller, to decide what to track next. Pass false for private packages. |
| Name | Required | Description |
|---|---|---|
| notes | No | |
| dependencies | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnly/openWorld/idempotent annotations, the description discloses rich behavioral details: returns verbatim vendor sections, categorized changes, CVE IDs, deterministic signals, and breaking changes even in minor/patch releases. It also explains exact-match behavior for non-npm ecosystems and the deps.dev fallback tracking, including the recordMisses privacy option. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a dense single paragraph, but every sentence contributes unique information about usage, matching rules, or behavior. It front-loads the primary use case and then adds identifier and privacy details. It is longer than ideal, but the complexity of the tool justifies the length.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the full calling context: when to use it, what to pass, how identifiers work across ecosystems, return contents, exact-match semantics, and the deps.dev fallback. An output schema exists and the description does not need to restate return structure. Nothing essential for correct invocation is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although schema coverage is 100%, the description adds substantial meaning: repository disambiguates scoped/renamed packages, purl takes precedence and is the right identifier for Maven/Go/NuGet/Actions, and recordMisses should be false for private packages. These are usage insights beyond the schema field descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: pass a package with current and target versions to get release notes and breaking-change signals. It is specific about the resource (dependency upgrades) and the output. However, it does not explicitly differentiate itself from siblings like whats_new or search_releases, though the upgrade-focused scope implies a distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit usage context: before or after upgrading dependencies, with concrete scenarios like npm update, pip install -U, Gradle version catalogs, go.mod, and workflow actions. It does not mention when not to use it or name alternative tools, but the context is clear enough for an agent to select it appropriately.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
A product's newest releases with notes. Pass since_version (the version you run) to get only what shipped after it, with per-category change counts.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Releases to return, default 10. | |
| product | Yes | Product slug or name, e.g. "next-js" or "Next.js". | |
| since_version | No | The version you run. Returns only the releases above it in the history, matched exactly or as the same version spelled with fewer trailing zeros. A version we do not hold is reported as a miss rather than guessed into an ordering. |
| Name | Required | Description |
|---|---|---|
| notes | No | How the product or the version was resolved. |
| product | Yes | |
| releases | Yes | |
| returned | Yes | |
| truncated | No | |
| newerCount | No | Releases above the pinned version, before the limit. |
| changeCounts | No | Change items across the whole span, even when truncated. |
| sinceVersion | No | The version you passed. |
| sinceVersionFound | No | Whether that version was found in the history. False means the releases below are the latest, not the ones after yours. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, and the description adds useful behavior beyond that: filtering by since_version and returning per-category change counts. It also indirectly conveys that omitting since_version returns the newest releases without filtering, which is helpful.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no filler: the first states the tool's core function, the second explains the key optional parameter and output characteristic. It is compact, front-loaded, and every sentence contributes value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the output schema exists and annotations cover safety/idempotence, the description covers the essential behavioral detail (since_version filtering and per-category counts) plus the notion of newest releases. Nothing critical for calling the tool correctly is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description essentially restates the since_version semantics already present in the schema (the version you run, only what shipped after it) without adding new parameter-level meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the tool as returning a product's newest releases with notes, which is a specific verb-resource combination. It does not explicitly differentiate from sibling tools like search_releases, so the distinctiveness is somewhat implicit rather than stated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives a clear usage condition for the since_version parameter: pass the version you run to get only what shipped after it. However, it gives no explicit guidance on when to choose this tool over list_products or search_releases, leaving the choice to be inferred from context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
missing_changesupgrade_notes1 field changedInput schema / properties / dependencies / items / properties / purl / descriptionPrevious value: -"The package as a purl (package URL), e.g. \"pkg:maven/com.squareup.okhttp3/okhttp\", \"pkg:golang/github.com/spf13/cobra\" or \"pkg:nuget/Newtonsoft.Json\" — what an SBOM, OSV or Renovate already names it by. Takes precedence over name and registry; a version inside it is ignored in favour of from/to."New value: +"The package as a purl (package URL), e.g. \"pkg:maven/com.squareup.okhttp3/okhttp\", \"pkg:golang/github.com/spf13/cobra\" or \"pkg:nuget/Newtonsoft.Json\" — what an SBOM, OSV or Renovate already names it by. Takes precedence over name and registry; a version inside it is ignored in favour of the versions passed beside it."upgrade_notes1 field changedInput schema / properties / recordMissesAdded value: +{
+ "description": "Default true. A Maven, Go or NuGet package this server does not track is checked against deps.dev after the answer and counted per day, with nothing about the caller, to decide what to track next. Pass false for private packages.",
+ "type": "boolean"
+}upgrade_notes9 fields changedInput schema / properties / dependencies / items / properties / name / descriptionPrevious value: -"The package name as its registry spells it, e.g. \"better-auth\" or \"@tanstack/react-query\"."New value: +"The package as its ecosystem spells it: \"better-auth\", \"@tanstack/react-query\", a Maven \"group:artifact\", a Go module path, or an Action's \"owner/repo@ref\"."Input schema / properties / dependencies / items / properties / purlAdded value: +{
+ "description": "The package as a purl (package URL), e.g. \"pkg:maven/com.squareup.okhttp3/okhttp\", \"pkg:golang/github.com/spf13/cobra\" or \"pkg:nuget/Newtonsoft.Json\" — what an SBOM, OSV or Renovate already names it by. Takes precedence over name and registry; a version inside it is ignored in favour of from/to.",
+ "maxLength": 300,
+ "pattern": "^[Pp][Kk][Gg]:",
+ "type": "string"
+}Input schema / properties / dependencies / items / properties / registry / descriptionPrevious value: -"Default npm."New value: +"Default npm — unless purl, or the name's own shape (group:artifact, a Go module path), says otherwise."Input schema / properties / dependencies / items / properties / repository / descriptionPrevious value: -"The package's source repository — its package.json `repository` (any GitHub URL, github:owner/repo or owner/repo). Resolves scoped and renamed packages the name alone cannot, and makes the match exact."New value: +"The package's source repository — its package.json `repository`, or the repo a Maven or NuGet package is built from (any GitHub URL, github:owner/repo or owner/repo). Resolves scoped and renamed packages the name alone cannot, and makes the match exact."Output schema / properties / dependencies / items / properties / match / properties / tier / descriptionPrevious value: -"identifier: a registry id or repository the catalog tracks. name: a name-only guess — check the product before trusting it, and pass repository to make it exact."New value: +"identifier: a registry id, a purl or a repository the catalog tracks. namespace: the package sits under a namespace the product claims (a Maven group, say) — the notes are the family's. name: a name-only guess — check the product before trusting it, and pass purl or repository to make it exact."Output schema / properties / dependencies / items / properties / match / properties / tier / enumPrevious value: -[
- "identifier",
- "name"
-]New value: +[
+ "identifier",
+ "namespace",
+ "name"
+]Output schema / properties / dependencies / items / properties / purlAdded value: +{
+ "description": "The package as a versionless purl, as it was matched.",
+ "type": "string"
+}Output schema / properties / dependencies / items / properties / registry / descriptionAdded value: +"The registry, when the package is in one of these four; absent for a Maven, Go, NuGet or Actions package."Output schema / properties / dependencies / items / requiredPrevious value: -[
- "name",
- "registry",
- "from",
- "status"
-]New value: +[
+ "name",
+ "from",
+ "status"
+]upgrade_noteslist_products3 fields changedOutput schema / properties / products / items / properties / archivedAdded value: +{
+ "description": "Whether the upstream repository is archived; absent when unknown.",
+ "type": "boolean"
+}Output schema / properties / products / items / properties / languageAdded value: +{
+ "type": "string"
+}Output schema / properties / products / items / properties / licenseAdded value: +{
+ "description": "SPDX expression as the product's own source states it, e.g. MIT or LicenseRef-proprietary; absent when unknown.",
+ "type": "string"
+}search_releases3 fields changedOutput schema / properties / products / items / properties / archivedAdded value: +{
+ "description": "Whether the upstream repository is archived; absent when unknown.",
+ "type": "boolean"
+}Output schema / properties / products / items / properties / languageAdded value: +{
+ "type": "string"
+}Output schema / properties / products / items / properties / licenseAdded value: +{
+ "description": "SPDX expression as the product's own source states it, e.g. MIT or LicenseRef-proprietary; absent when unknown.",
+ "type": "string"
+}whats_new3 fields changedOutput schema / properties / product / properties / archivedAdded value: +{
+ "description": "Whether the upstream repository is archived; absent when unknown.",
+ "type": "boolean"
+}Output schema / properties / product / properties / languageAdded value: +{
+ "type": "string"
+}Output schema / properties / product / properties / licenseAdded value: +{
+ "description": "SPDX expression as the product's own source states it, e.g. MIT or LicenseRef-proprietary; absent when unknown.",
+ "type": "string"
+}list_products2 fields changedInput schema / properties / category / enumPrevious value: -[
- "Developer Tools",
- "Frameworks & Libraries",
- "Languages & Runtimes",
- "Games",
- "Operating Systems",
- "Browsers",
- "Communication",
- "Media",
- "AI",
- "Design Tools",
- "Productivity",
- "Firmware",
- "Drivers"
-]New value: +[
+ "Developer Tools",
+ "Frameworks & Libraries",
+ "Languages & Runtimes",
+ "Infrastructure & DevOps",
+ "Databases & Data",
+ "Security & Privacy",
+ "Games",
+ "Gaming Tools",
+ "Operating Systems",
+ "System Utilities",
+ "Browsers",
+ "Communication",
+ "Media",
+ "Creative Tools",
+ "AI",
+ "Productivity",
+ "Lifestyle & Apps",
+ "Firmware",
+ "Drivers"
+]Output schema / properties / products / items / properties / category / enumPrevious value: -[
- "Developer Tools",
- "Frameworks & Libraries",
- "Languages & Runtimes",
- "Games",
- "Operating Systems",
- "Browsers",
- "Communication",
- "Media",
- "AI",
- "Design Tools",
- "Productivity",
- "Firmware",
- "Drivers"
-]New value: +[
+ "Developer Tools",
+ "Frameworks & Libraries",
+ "Languages & Runtimes",
+ "Infrastructure & DevOps",
+ "Databases & Data",
+ "Security & Privacy",
+ "Games",
+ "Gaming Tools",
+ "Operating Systems",
+ "System Utilities",
+ "Browsers",
+ "Communication",
+ "Media",
+ "Creative Tools",
+ "AI",
+ "Productivity",
+ "Lifestyle & Apps",
+ "Firmware",
+ "Drivers"
+]search_releases3 fields changedInput schema / properties / category / enumPrevious value: -[
- "Developer Tools",
- "Frameworks & Libraries",
- "Languages & Runtimes",
- "Games",
- "Operating Systems",
- "Browsers",
- "Communication",
- "Media",
- "AI",
- "Design Tools",
- "Productivity",
- "Firmware",
- "Drivers"
-]New value: +[
+ "Developer Tools",
+ "Frameworks & Libraries",
+ "Languages & Runtimes",
+ "Infrastructure & DevOps",
+ "Databases & Data",
+ "Security & Privacy",
+ "Games",
+ "Gaming Tools",
+ "Operating Systems",
+ "System Utilities",
+ "Browsers",
+ "Communication",
+ "Media",
+ "Creative Tools",
+ "AI",
+ "Productivity",
+ "Lifestyle & Apps",
+ "Firmware",
+ "Drivers"
+]Output schema / properties / category / enumPrevious value: -[
- "Developer Tools",
- "Frameworks & Libraries",
- "Languages & Runtimes",
- "Games",
- "Operating Systems",
- "Browsers",
- "Communication",
- "Media",
- "AI",
- "Design Tools",
- "Productivity",
- "Firmware",
- "Drivers"
-]New value: +[
+ "Developer Tools",
+ "Frameworks & Libraries",
+ "Languages & Runtimes",
+ "Infrastructure & DevOps",
+ "Databases & Data",
+ "Security & Privacy",
+ "Games",
+ "Gaming Tools",
+ "Operating Systems",
+ "System Utilities",
+ "Browsers",
+ "Communication",
+ "Media",
+ "Creative Tools",
+ "AI",
+ "Productivity",
+ "Lifestyle & Apps",
+ "Firmware",
+ "Drivers"
+]Output schema / properties / products / items / properties / category / enumPrevious value: -[
- "Developer Tools",
- "Frameworks & Libraries",
- "Languages & Runtimes",
- "Games",
- "Operating Systems",
- "Browsers",
- "Communication",
- "Media",
- "AI",
- "Design Tools",
- "Productivity",
- "Firmware",
- "Drivers"
-]New value: +[
+ "Developer Tools",
+ "Frameworks & Libraries",
+ "Languages & Runtimes",
+ "Infrastructure & DevOps",
+ "Databases & Data",
+ "Security & Privacy",
+ "Games",
+ "Gaming Tools",
+ "Operating Systems",
+ "System Utilities",
+ "Browsers",
+ "Communication",
+ "Media",
+ "Creative Tools",
+ "AI",
+ "Productivity",
+ "Lifestyle & Apps",
+ "Firmware",
+ "Drivers"
+]whats_new1 field changedOutput schema / properties / product / properties / category / enumPrevious value: -[
- "Developer Tools",
- "Frameworks & Libraries",
- "Languages & Runtimes",
- "Games",
- "Operating Systems",
- "Browsers",
- "Communication",
- "Media",
- "AI",
- "Design Tools",
- "Productivity",
- "Firmware",
- "Drivers"
-]New value: +[
+ "Developer Tools",
+ "Frameworks & Libraries",
+ "Languages & Runtimes",
+ "Infrastructure & DevOps",
+ "Databases & Data",
+ "Security & Privacy",
+ "Games",
+ "Gaming Tools",
+ "Operating Systems",
+ "System Utilities",
+ "Browsers",
+ "Communication",
+ "Media",
+ "Creative Tools",
+ "AI",
+ "Productivity",
+ "Lifestyle & Apps",
+ "Firmware",
+ "Drivers"
+]list_products1 field changedInput schema / properties / sortAdded value: +{
+ "description": "\"popular\" ranks by current audience popularity — outside signals (stars, downloads, players) blended with this site's own readers — and answers \"what are the most popular software right now?\". Default is the curated catalog order (or search relevance when query is set, which ignores sort).",
+ "enum": [
+ "curated",
+ "popular"
+ ],
+ "type": "string"
+}list_products1 field changedOutput schema / (root)Previous value: -nullNew value: +{
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
+ "additionalProperties": false,
+ "properties": {
+ "products": {
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "category": {
+ "enum": [
+ "Developer Tools",
+ "Frameworks & Libraries",
+ "Languages & Runtimes",
+ "Games",
+ "Operating Systems",
+ "Browsers",
+ "Communication",
+ "Media",
+ "AI",
+ "Design Tools",
+ "Productivity",
+ "Firmware",
+ "Drivers"
+ ],
+ "type": "string"
+ },
+ "description": {
+ "type": "string"
+ },
+ "homepage": {
+ "description": "The vendor's own site.",
+ "type": "string"
+ },
+ "labels": {
+ "description": "Provenance to keep with any quote, e.g. “Sample data”.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "name": {
+ "type": "string"
+ },
+ "platforms": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "slug": {
+ "type": "string"
+ },
+ "url": {
+ "description": "This product's page on What's New.",
+ "type": "string"
+ },
+ "vendor": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "slug",
+ "name",
+ "vendor",
+ "category",
+ "description",
+ "url",
+ "homepage"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "returned": {
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+ },
+ "total": {
+ "description": "Matches before the cap.",
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+ },
+ "truncated": {
+ "const": true,
+ "type": "boolean"
+ }
+ },
+ "required": [
+ "total",
+ "returned",
+ "products"
+ ],
+ "type": "object"
+}search_releases1 field changedOutput schema / (root)Previous value: -nullNew value: +{
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
+ "additionalProperties": false,
+ "properties": {
+ "category": {
+ "description": "Limit results to one product category.",
+ "enum": [
+ "Developer Tools",
+ "Frameworks & Libraries",
+ "Languages & Runtimes",
+ "Games",
+ "Operating Systems",
+ "Browsers",
+ "Communication",
+ "Media",
+ "AI",
+ "Design Tools",
+ "Productivity",
+ "Firmware",
+ "Drivers"
+ ],
+ "type": "string"
+ },
+ "note": {
+ "description": "Present when nothing matched.",
+ "type": "string"
+ },
+ "products": {
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "category": {
+ "enum": [
+ "Developer Tools",
+ "Frameworks & Libraries",
+ "Languages & Runtimes",
+ "Games",
+ "Operating Systems",
+ "Browsers",
+ "Communication",
+ "Media",
+ "AI",
+ "Design Tools",
+ "Productivity",
+ "Firmware",
+ "Drivers"
+ ],
+ "type": "string"
+ },
+ "description": {
+ "type": "string"
+ },
+ "homepage": {
+ "description": "The vendor's own site.",
+ "type": "string"
+ },
+ "labels": {
+ "description": "Provenance to keep with any quote, e.g. “Sample data”.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "name": {
+ "type": "string"
+ },
+ "platforms": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "slug": {
+ "type": "string"
+ },
+ "url": {
+ "description": "This product's page on What's New.",
+ "type": "string"
+ },
+ "vendor": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "slug",
+ "name",
+ "vendor",
+ "category",
+ "description",
+ "url",
+ "homepage"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "query": {
+ "description": "The query as searched — trimmed and capped.",
+ "type": "string"
+ },
+ "releases": {
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "changes": {
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "category": {
+ "enum": [
+ "added",
+ "changed",
+ "fixed",
+ "removed",
+ "deprecated",
+ "security"
+ ],
+ "type": "string"
+ },
+ "text": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "category",
+ "text"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "channel": {
+ "description": "The source's own classification, e.g. “longterm”.",
+ "type": "string"
+ },
+ "date": {
+ "description": "ISO 8601 timestamp.",
+ "type": "string"
+ },
+ "labels": {
+ "description": "Provenance to keep with any quote, e.g. “Pre-release”.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "prerelease": {
+ "const": true,
+ "type": "boolean"
+ },
+ "product": {
+ "additionalProperties": false,
+ "properties": {
+ "name": {
+ "type": "string"
+ },
+ "slug": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "slug",
+ "name"
+ ],
+ "type": "object"
+ },
+ "sourceUrl": {
+ "description": "The vendor's own release notes.",
+ "type": "string"
+ },
+ "summary": {
+ "type": "string"
+ },
+ "title": {
+ "type": "string"
+ },
+ "url": {
+ "description": "This release's page on What's New.",
+ "type": "string"
+ },
+ "version": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "title",
+ "date",
+ "url",
+ "sourceUrl",
+ "product"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "query",
+ "products",
+ "releases"
+ ],
+ "type": "object"
+}whats_new1 field changedOutput schema / (root)Previous value: -nullNew value: +{
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
+ "additionalProperties": false,
+ "properties": {
+ "changeCounts": {
+ "additionalProperties": {
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+ },
+ "description": "Change items across the whole span, even when truncated.",
+ "propertyNames": {
+ "enum": [
+ "added",
+ "changed",
+ "fixed",
+ "removed",
+ "deprecated",
+ "security"
+ ],
+ "type": "string"
+ },
+ "type": "object"
+ },
+ "newerCount": {
+ "description": "Releases above the pinned version, before the limit.",
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+ },
+ "notes": {
+ "description": "How the product or the version was resolved.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "product": {
+ "additionalProperties": false,
+ "properties": {
+ "category": {
+ "enum": [
+ "Developer Tools",
+ "Frameworks & Libraries",
+ "Languages & Runtimes",
+ "Games",
+ "Operating Systems",
+ "Browsers",
+ "Communication",
+ "Media",
+ "AI",
+ "Design Tools",
+ "Productivity",
+ "Firmware",
+ "Drivers"
+ ],
+ "type": "string"
+ },
+ "description": {
+ "type": "string"
+ },
+ "homepage": {
+ "description": "The vendor's own site.",
+ "type": "string"
+ },
+ "labels": {
+ "description": "Provenance to keep with any quote, e.g. “Sample data”.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "name": {
+ "type": "string"
+ },
+ "platforms": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "slug": {
+ "type": "string"
+ },
+ "url": {
+ "description": "This product's page on What's New.",
+ "type": "string"
+ },
+ "vendor": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "slug",
+ "name",
+ "vendor",
+ "category",
+ "description",
+ "url",
+ "homepage"
+ ],
+ "type": "object"
+ },
+ "releases": {
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "body": {
+ "type": "string"
+ },
+ "bodyTruncated": {
+ "const": true,
+ "description": "The body was cut at the cap; the permalink has it all.",
+ "type": "boolean"
+ },
+ "changes": {
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "category": {
+ "enum": [
+ "added",
+ "changed",
+ "fixed",
+ "removed",
+ "deprecated",
+ "security"
+ ],
+ "type": "string"
+ },
+ "text": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "category",
+ "text"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "channel": {
+ "description": "The source's own classification, e.g. “longterm”.",
+ "type": "string"
+ },
+ "date": {
+ "description": "ISO 8601 timestamp.",
+ "type": "string"
+ },
+ "labels": {
+ "description": "Provenance to keep with any quote, e.g. “Pre-release”.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "prerelease": {
+ "const": true,
+ "type": "boolean"
+ },
+ "sourceUrl": {
+ "description": "The vendor's own release notes.",
+ "type": "string"
+ },
+ "summary": {
+ "type": "string"
+ },
+ "title": {
+ "type": "string"
+ },
+ "url": {
+ "description": "This release's page on What's New.",
+ "type": "string"
+ },
+ "version": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "title",
+ "date",
+ "url",
+ "sourceUrl"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "returned": {
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+ },
+ "sinceVersion": {
+ "description": "The version you passed.",
+ "type": "string"
+ },
+ "sinceVersionFound": {
+ "description": "Whether that version was found in the history. False means the releases below are the latest, not the ones after yours.",
+ "type": "boolean"
+ },
+ "truncated": {
+ "const": true,
+ "type": "boolean"
+ }
+ },
+ "required": [
+ "product",
+ "returned",
+ "releases"
+ ],
+ "type": "object"
+}list_productssearch_releaseswhats_newRelease notes and changelogs from across the web, indexed for agents. Also via CLI and REST API.
Live, sourced changes feed: Apple, Google Play, Android, GitHub, Vercel, Cloudflare, Firebase, more.
Generate changelogs, release emails, help-center articles, banners, and social posts from commits.
Latest versions, LTS windows, and EOL dates for 300+ products. Fresh ground truth for stale models.
Add one secure layer between your agents and this server.
