Havoptic AI Release Intelligence
Server Details
Release intelligence for AI coding tools: releases, typed changes, breaking changes, cadence.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 15 tools
The active tools (cadence_stats, compare_tools, get_release, get_upgrade_notes, whats_changed_since, etc.) are mostly distinct, but five deprecated tools duplicate their successors (feature_timeline/feature_adoption, latest_releases/get_latest_releases, list_tracked_tools/list_tools, release_history/get_latest_releases, search_release_notes/search_changes). The 'Deprecated: use X' notes mitigate this, but an agent must read descriptions carefully to avoid picking the stale twin. Overlap between get_breaking_changes, whats_changed_since, and get_latest_releases also requires attention.
All names are snake_case, which helps, but verb conventions are mixed: bare-noun (cadence_stats, feature_adoption), get_ prefixed (get_release, get_latest_releases), list_, search_, and compare_. Readable but not a predictable verb_noun pattern throughout.
15 tools is at the upper edge of a reasonable set, and 5 of them are deprecated aliases, so the effective surface is ~10. The deprecated entries inflate the count without adding capability, making the set feel heavier than its scope requires.
Coverage is strong for release intelligence: catalog listing, per-release detail, cadence stats, breaking changes, upgrade paths, feature adoption, cross-tool comparison, search, and digests. Minor gap: no dedicated get_tool detail endpoint (must rely on list_tools with a fuzzy query) and no explicit tool-metadata retrieval beyond listing.
Available Tools
15 toolscadence_statsRelease cadence statsARead-onlyIdempotentInspect
How fast tools ship: release counts over 7/30/90 days, average days between releases, and last release — for selected tools or all of them. Legacy input tool (single id) still works.
Inputs: tool, tools. Returns: object, omitted, cadences, truncated, +4 more
compare_toolsCompare toolsARead-onlyIdempotentInspect
Compare 2–4 AI coding tools: release cadence, feature-matrix differences, recent changes, and Havoptic's editorial verdict per pair. aspects defaults to cadence, features, verdict. Legacy inputs tool_a/tool_b still work.
Inputs: since, tools, tool_a, tool_b, +1 more. Returns: tools, object, aspects, cadence, +6 more
feature_adoptionFeature adoption timelineARead-onlyIdempotentInspect
Who shipped a cross-tool feature first (MCP support, subagents, planning mode, hooks, checkpoints, …), which tools followed and their lag in days. Successor to feature_timeline.
Inputs: feature (required). Returns: object, omitted, features, available, +5 more
feature_timelineFeature introduction timelineARead-onlyIdempotentInspect
Deprecated: use feature_adoption. Which tool shipped each notable cross-tool feature first (MCP support, subagents, planning mode, hooks, checkpoints, ...), follower lag in days, and copying-trend insights. Optionally filter to one feature.
Inputs: feature.
get_breaking_changesBreaking changes feedARead-onlyIdempotentInspect
Breaking changes (and, by default, deprecations) across tools in a window (default last 30 days), newest first. Legacy releases without typed changes are counted, not guessed.
Inputs: since, tools, include_deprecations. Returns: items, since, object, omitted, +5 more
get_latest_releasesLatest releasesARead-onlyIdempotentInspect
Newest releases (newest first) across all or selected tools. Successor to latest_releases and release_history (pass since/until for a date window). Default channel=stable, detail=brief.
Inputs: limit, since, tools, until, +4 more. Returns: total, object, omitted, releases, +5 more
get_releaseGet one releaseARead-onlyIdempotentInspect
One release by id (e.g. 'claude-code-2.1.183', canonical 'claude-code@2.1.183') or by tool + version ('latest' allowed). detail=full (the default for a bare id lookup, as before) includes complete release notes; brief/standard omit them unless include_raw_notes is true.
Inputs: id, tool, detail, version, +1 more. Returns: object, omitted, release, truncated, +4 more
get_upgrade_notesUpgrade notes between versionsARead-onlyIdempotentInspect
Everything between two versions of one tool: breaking changes, deprecations, security fixes, features and fixes, plus an explicit coverage gap for legacy releases without typed changes. to_version defaults to latest.
Inputs: tool (required), from_version (required), detail, to_version. Returns: to, from, object, omitted, +7 more
latest_releasesLatest releasesARead-onlyIdempotentInspect
Deprecated: use get_latest_releases. Most recent AI coding tool releases (newest first), optionally filtered to one tool. Returns summaries; use get_release for full notes. Default detail=brief omits infographic URLs.
Inputs: tool, limit, detail.
list_toolsList tracked productsARead-onlyIdempotentInspect
Catalog of the products Havoptic tracks (AI coding tools plus model/API platforms, agent SDKs and inference runtimes): id, name, vendor, category, release count and latest release. Use first to find valid tool ids (fuzzy query: 'copilot', 'devin').
Inputs: query, vendor, category. Returns: tools, object, omitted, truncated, +5 more
list_tracked_toolsList tracked AI coding toolsARead-onlyIdempotentInspect
Deprecated: use list_tools. All AI coding tools Havoptic tracks (Claude Code, OpenAI Codex CLI, Cursor, Gemini CLI, Kiro CLI, GitHub Copilot CLI, Devin Desktop/Windsurf, Antigravity CLI, Grok Build), with release counts and their latest release.
Inputs: no named parameters.
release_historyRelease historyARead-onlyIdempotentInspect
Deprecated: use get_latest_releases with since. Release history for one tool within an optional date window (newest first). Summaries only; use get_release for full notes. Default detail=brief omits infographic URLs.
Inputs: tool (required), limit, since, until, +1 more.
search_changesSearch changesARead-onlyIdempotentInspect
Search typed change items (title + evidence) and, unless kinds is set, legacy release notes — flags, error strings, feature names, config keys. Successor to search_release_notes. Brief mode returns snippets only.
Inputs: query (required), kinds, limit, since, +2 more. Returns: items, query, object, omitted, +6 more
search_release_notesSearch release notesARead-onlyIdempotentInspect
Deprecated: use search_changes. Full-text search across all tracked release notes — flags, error strings, feature names, config keys. Returns ranked matches with snippet context.
Inputs: query (required), tool, limit.
whats_changed_sinceWhat changed sinceARead-onlyIdempotentInspect
Digest of typed changes (breaking, security, features, fixes, …) since a date or relative window ('7d', '30d'), grouped by tool with breaking changes first. States how many releases in range are legacy records without typed changes.
Inputs: since (required), kinds, tools, cursor, +2 more. Returns: items, since, object, omitted, +5 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Related MCP Connectors
Changelogs for coding agents: versions, breaking changes, migrations. Free changelog-to-JSON.
Release notes and changelogs from across the web, indexed for agents. Also via CLI and REST API.
Generate changelogs, release emails, help-center articles, banners, and social posts from commits.
Change intelligence for coding agents: sourced breaking changes for npm, PyPI, and Rust packages.
Related MCP Servers
- AlicenseAqualityBmaintenanceVerified, dated facts for AI coding agents: what breaks between npm package versions (diffed from TypeScript types), per-version vulnerabilities, the newest version compatible with a given Node/Python/Rust/PHP, end-of-life dates of ~480 runtimes and frameworks, and AI model prices. Covers npm, PyPI, crates.io and Packagist.121AGPL 3.0
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to draft customer-ready or internal release notes from work closed in GitHub, Jira, or Linear, using deterministic fetching and rule-based categorization that flags uncertain items in a review list instead of guessing. Everything stays read-only, so a human approves and publishes the final notes.1MIT
- AlicenseNot gradedqualityDmaintenanceLive codebase intelligence for AI agents. Import graph PageRank for file importance, git forensics for co-change coupling and fragile code, convention detection across 16 domains, and blast radius analysis.21 npm3Business Source 1.1
- AlicenseAqualityDmaintenanceProvides accurate, source-grounded breaking-change briefings for npm packages by reading real GitHub release notes and CHANGELOGs, helping coding agents avoid hallucinated dependency migrations.38 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.