Tools (12)We asked this server directly for its tool list on Aug 2.
search_releases
Search indexed release notes. Defaults to hybrid retrieval (FTS5 + semantic vectors fused via RRF). Results carry a `kind` discriminator so agents can branch on `release` vs `changelog_chunk` hits. When Vectorize or the embedding provider is unavailable, the tool silently degrades to lexical FTS and flags the result.
search_registry
Semantic search across the registry — returns orgs, products, or sources that match the query by meaning, not just keyword. Useful when you know what kind of thing you're looking for ('observability vendor with open-source agent') but not its exact name. Falls back to LIKE-based lexical search when Vectorize is unavailable.
get_latest_releases
Get the most recent releases, optionally filtered by product or organization
list_sources
List all indexed changelog sources
list_organizations
List all indexed organizations, optionally filtered
get_organization
Get detailed information about a single organization including accounts, tags, sources, products, aliases, and a short preview of its AI-generated overview when one exists. Use `get_organization_overview` to read the full overview text.
Show all 12 tools ↓
get_organization_overview
Read the full AI-generated overview for an organization — a short briefing that distills recent changelog activity into themed sections. Returned with a generated-at timestamp and a stale warning if the overview is older than 30 days. Use this when the user wants the narrative summary for an org, not the raw release list.
get_source
Detail for a single indexed source: organization, optional product linkage, release count (excluding suppressed), last-fetched timestamp, and whether a tracked CHANGELOG file is available for get_source_changelog. Use this after list_sources or search_releases when the user wants to understand one source in depth (e.g. 'tell me about the apollo-client source').
get_source_changelog
Read a tracked CHANGELOG file for a GitHub source. Monorepos expose per-package files (e.g. `packages/next/CHANGELOG.md`) alongside the root CHANGELOG — pass `path` to read a specific one, omit it to get the root. Supports heading-aligned slicing by chars (`limit`) or by tokens (`tokens`, cl100k_base) for LLM context budgeting. Every response includes `totalTokens` for the whole file and, in token mode, `sliceTokens` for the returned chunk. `totalTokens` is an exact cl100k_base count for files under 256KB and an approximation (`ceil(totalChars / 4)`) for larger files; `sliceTokens` is always exact. Files over 1MB are truncated at fetch time; the response flags this so you know the tail is missing.
get_release
Fetch the full content of a single release by id. Release ids are returned by search_releases / get_latest_releases — 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.
list_products
List products — the optional grouping layer between organizations and sources. Multi-product orgs (e.g. Vercel → Next.js, Turborepo) expose their lineup here. Pass an organization filter to scope to one org; omit it to see every indexed product.
get_product
Detail for a single product including its organization, category, tags, and the sources grouped under it. Use when the user asks about a specific product (e.g. 'what sources does Next.js have?' on Vercel) rather than the whole organization.
Is this your server?
Create a free RNWY account to connect your on-chain identity to this server. MCP server claiming is coming; register now and you'll be first in line.