com.havoptic/releases

Est-ce que com.havoptic/releases est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.havoptic/releases » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 15 outils

• cadence_stats≈ 426 tokens

  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.

  Paramètres, retour & exemple (2)

  Paramètres

  • tool · string · optionnel
    Legacy: one tool id (use tools instead)
  • tools · array · optionnel
    Tool ids (fuzzy: 'claude', 'codex', 'copilot' resolve). Omit for all tools; see list_tools.

  Exemple d'appel

  {"name": "cadence_stats", "arguments": {"tool": "texte", "tools": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"object": "texte", "omitted": {}, "cadences": [], "truncated": true, "next_cursor": "texte", "freshness_note": "texte", "estimated_tokens": 1, "dataset_updated_at": "texte"}}

• compare_tools≈ 542 tokens

  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.

  Paramètres, retour & exemple (5)

  Paramètres

  • since · string · optionnel
    Window for recent_changes (ISO date or 7d/30d; default 30d)
  • tools · array · optionnel
    2–4 tool ids (fuzzy)
  • tool_a · string · optionnel
    Legacy: first tool (use tools instead)
  • tool_b · string · optionnel
    Legacy: second tool (use tools instead)
  • aspects · array · optionnel
    Default ['cadence','features','verdict']

  Exemple d'appel

  {"name": "compare_tools", "arguments": {"since": "texte", "tools": [], "tool_a": "texte", "tool_b": "texte", "aspects": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"tools": [], "object": "texte", "aspects": [], "cadence": [], "omitted": {}, "truncated": true, "next_cursor": "texte", "freshness_note": "texte", "estimated_tokens": 1, "dataset_updated_at": "texte"}}

• feature_adoption≈ 353 tokens

  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.

  Paramètres, retour & exemple (1)

  Paramètres

  • feature · string · requis
    Feature id or substring, e.g. mcp-oauth, subagents, planning

  Exemple d'appel

  {"name": "feature_adoption", "arguments": {"feature": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"object": "texte", "omitted": {}, "features": [], "available": true, "truncated": true, "next_cursor": "texte", "freshness_note": "texte", "estimated_tokens": 1, "dataset_updated_at": "texte"}}

• feature_timeline≈ 184 tokens

  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.

  Paramètres, retour & exemple (1)

  Paramètres

  • feature · string · optionnel
    Feature id or name substring, e.g. 'subagents', 'mcp', 'planning'

  Exemple d'appel

  {"name": "feature_timeline", "arguments": {"feature": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_breaking_changes≈ 465 tokens

  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.

  Paramètres, retour & exemple (3)

  Paramètres

  • since · string · optionnel
    ISO date or relative window, default 30d
  • tools · array · optionnel
    Tool ids (fuzzy: 'claude', 'codex', 'copilot' resolve). Omit for all tools; see list_tools.
  • include_deprecations · boolean · optionnel
    Default true

  Exemple d'appel

  {"name": "get_breaking_changes", "arguments": {"since": "texte", "tools": [], "include_deprecations": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"items": [], "since": "texte", "object": "texte", "omitted": {}, "truncated": true, "next_cursor": "texte", "freshness_note": "texte", "estimated_tokens": 1, "dataset_updated_at": "texte"}}

• get_latest_releases≈ 609 tokens

  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.

  Paramètres, retour & exemple (8)

  Paramètres

  • limit · integer · optionnel
    Max releases (default 10)
  • since · string · optionnel
    Only releases on/after this ISO date
  • tools · array · optionnel
    Tool ids (fuzzy: 'claude', 'codex', 'copilot' resolve). Omit for all tools; see list_tools.
  • until · string · optionnel
    Only releases on/before this ISO date
  • cursor · string · optionnel
    next_cursor from a previous truncated response.
  • detail · string · optionnel · brief | standard | full
    brief (default) omits infographics and raw notes; standard adds evidence and links; full adds complete release notes.
  • channel · string · optionnel · stable | prerelease | all
    Default stable
  • max_tokens · integer · optionnel
    Soft cap on the text response, estimated as ceil(chars/3.5). Default 1500.

  Exemple d'appel

  {"name": "get_latest_releases", "arguments": {"limit": 1, "since": "texte", "tools": [], "until": "texte", "cursor": "texte", "detail": "brief"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"total": 1, "object": "texte", "omitted": {}, "releases": [], "truncated": true, "next_cursor": "texte", "freshness_note": "texte", "estimated_tokens": 1, "dataset_updated_at": "texte"}}

• get_release≈ 498 tokens

  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.

  Paramètres, retour & exemple (5)

  Paramètres

  • id · string · optionnel
    Canonical (tool@version) or legacy (tool-version) release id
  • tool · string · optionnel
    Tool id (fuzzy), used with version
  • detail · string · optionnel · brief | standard | full
    brief (default) omits infographics and raw notes; standard adds evidence and links; full adds complete release notes.
  • version · string · optionnel
    Semver or 'latest'
  • include_raw_notes · boolean · optionnel
    Include the full upstream notes in any detail mode

  Exemple d'appel

  {"name": "get_release", "arguments": {"id": "texte", "tool": "texte", "detail": "brief", "version": "texte", "include_raw_notes": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"object": "texte", "omitted": {}, "release": {}, "truncated": true, "next_cursor": "texte", "freshness_note": "texte", "estimated_tokens": 1, "dataset_updated_at": "texte"}}

• get_upgrade_notes≈ 443 tokens

  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.

  Paramètres, retour & exemple (4)

  Paramètres

  • tool · string · requis
    Tool id (fuzzy)
  • detail · string · optionnel · brief | standard | full
    brief (default) omits infographics and raw notes; standard adds evidence and links; full adds complete release notes.
  • to_version · string · optionnel
    Target version (inclusive), default 'latest'
  • from_version · string · requis
    Version you are on (exclusive)

  Exemple d'appel

  {"name": "get_upgrade_notes", "arguments": {"tool": "texte", "from_version": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"to": "texte", "from": "texte", "object": "texte", "omitted": {}, "truncated": true, "product_id": "texte", "next_cursor": "texte", "release_count": 1, "freshness_note": "texte", "estimated_tokens": 1, "dataset_updated_at": "texte"}}

• latest_releases≈ 406 tokens

  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.

  Paramètres, retour & exemple (3)

  Paramètres

  • tool · string · optionnel
    Tool id, e.g. 'claude-code', 'openai-codex', 'cursor', 'gemini-cli', 'kiro', 'github-copilot', 'windsurf', 'antigravity-cli', 'grok-build', 'cline', 'opencode', 'zed', 'factory-droid', 'devin', 'lovable', 'amp', 'copilot-vscode', 'replit-agent', 'bolt', 'v0', 'openai-platform', 'anthropic-api', 'gemini-api', 'xai-api', 'mistral-api', 'deepseek-api', 'amazon-bedrock', 'gemini-agent-platform', 'mcp-spec', 'openai-agents-python', 'openai-agents-js', 'claude-agent-sdk-python', 'claude-agent-sdk-typescript', 'vercel-ai-sdk', 'langgraph-python', 'langgraph-js', 'llamaindex', 'crewai', 'mastra', 'cloudflare-agents-sdk', 'ollama', 'vllm', 'lm-studio', 'huggingface-transformers'. Use list_tools for the live list.
  • limit · integer · optionnel
    Max releases to return (default 10)
  • detail · string · optionnel · brief | standard | full
    brief omits infographics and fullNotes; full includes complete notes on single-release reads.

  Exemple d'appel

  {"name": "latest_releases", "arguments": {"tool": "texte", "limit": 1, "detail": "brief"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_tools≈ 474 tokens

  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').

  Paramètres, retour & exemple (3)

  Paramètres

  • query · string · optionnel
    Fuzzy match on name/alias
  • vendor · string · optionnel
    Vendor id slug, e.g. 'anthropic', 'google'
  • category · string · optionnel · coding-agent-cli | ide | ide-extension | model-api | agent-sdk | framework | infra | hosted-agent

  Exemple d'appel

  {"name": "list_tools", "arguments": {"query": "texte", "vendor": "texte", "category": "coding-agent-cli"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"tools": [], "object": "texte", "omitted": {}, "truncated": true, "next_cursor": "texte", "suggestions": [], "freshness_note": "texte", "estimated_tokens": 1, "dataset_updated_at": "texte"}}

• list_tracked_tools≈ 149 tokens

  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.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_tracked_tools", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• release_history≈ 458 tokens

  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.

  Paramètres, retour & exemple (5)

  Paramètres

  • tool · string · requis
    Tool id, e.g. 'claude-code', 'openai-codex', 'cursor', 'gemini-cli', 'kiro', 'github-copilot', 'windsurf', 'antigravity-cli', 'grok-build', 'cline', 'opencode', 'zed', 'factory-droid', 'devin', 'lovable', 'amp', 'copilot-vscode', 'replit-agent', 'bolt', 'v0', 'openai-platform', 'anthropic-api', 'gemini-api', 'xai-api', 'mistral-api', 'deepseek-api', 'amazon-bedrock', 'gemini-agent-platform', 'mcp-spec', 'openai-agents-python', 'openai-agents-js', 'claude-agent-sdk-python', 'claude-agent-sdk-typescript', 'vercel-ai-sdk', 'langgraph-python', 'langgraph-js', 'llamaindex', 'crewai', 'mastra', 'cloudflare-agents-sdk', 'ollama', 'vllm', 'lm-studio', 'huggingface-transformers'. Use list_tools for the live list.
  • limit · integer · optionnel
    Max releases to return (default 50)
  • since · string · optionnel
    Only releases on/after this ISO date (e.g. '2026-01-01')
  • until · string · optionnel
    Only releases on/before this ISO date
  • detail · string · optionnel · brief | standard | full
    brief omits infographics and fullNotes; full includes complete notes on single-release reads.

  Exemple d'appel

  {"name": "release_history", "arguments": {"tool": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_changes≈ 618 tokens

  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.

  Paramètres, retour & exemple (6)

  Paramètres

  • kinds · array · optionnel
    Change kinds to include, e.g. ['breaking','security'].
  • limit · integer · optionnel
    Max results per section (default 10)
  • query · string · requis
    Search terms, e.g. 'MCP OAuth' or '--dangerously-skip-permissions'
  • since · string · optionnel
  • tools · array · optionnel
    Tool ids (fuzzy: 'claude', 'codex', 'copilot' resolve). Omit for all tools; see list_tools.
  • until · string · optionnel

  Exemple d'appel

  {"name": "search_changes", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"items": [], "query": "texte", "object": "texte", "omitted": {}, "releases": [], "truncated": true, "next_cursor": "texte", "freshness_note": "texte", "estimated_tokens": 1, "dataset_updated_at": "texte"}}

• search_release_notes≈ 390 tokens

  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.

  Paramètres, retour & exemple (3)

  Paramètres

  • tool · string · optionnel
    Tool id, e.g. 'claude-code', 'openai-codex', 'cursor', 'gemini-cli', 'kiro', 'github-copilot', 'windsurf', 'antigravity-cli', 'grok-build', 'cline', 'opencode', 'zed', 'factory-droid', 'devin', 'lovable', 'amp', 'copilot-vscode', 'replit-agent', 'bolt', 'v0', 'openai-platform', 'anthropic-api', 'gemini-api', 'xai-api', 'mistral-api', 'deepseek-api', 'amazon-bedrock', 'gemini-agent-platform', 'mcp-spec', 'openai-agents-python', 'openai-agents-js', 'claude-agent-sdk-python', 'claude-agent-sdk-typescript', 'vercel-ai-sdk', 'langgraph-python', 'langgraph-js', 'llamaindex', 'crewai', 'mastra', 'cloudflare-agents-sdk', 'ollama', 'vllm', 'lm-studio', 'huggingface-transformers'. Use list_tools for the live list.
  • limit · integer · optionnel
    Max results (default 10)
  • query · string · requis
    Search terms, e.g. '--dangerously-skip-permissions' or 'MCP OAuth'

  Exemple d'appel

  {"name": "search_release_notes", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• whats_changed_since≈ 648 tokens

  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.

  Paramètres, retour & exemple (6)

  Paramètres

  • kinds · array · optionnel
    Change kinds to include, e.g. ['breaking','security'].
  • since · string · requis
    ISO-8601 date/datetime or relative: 7d, 30d
  • tools · array · optionnel
    Tool ids (fuzzy: 'claude', 'codex', 'copilot' resolve). Omit for all tools; see list_tools.
  • cursor · string · optionnel
    next_cursor from a previous truncated response.
  • detail · string · optionnel · brief | standard | full
    brief (default) omits infographics and raw notes; standard adds evidence and links; full adds complete release notes.
  • max_tokens · integer · optionnel
    Soft cap on the text response, estimated as ceil(chars/3.5). Default 1500.

  Exemple d'appel

  {"name": "whats_changed_since", "arguments": {"since": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"items": [], "since": "texte", "object": "texte", "omitted": {}, "truncated": true, "next_cursor": "texte", "freshness_note": "texte", "estimated_tokens": 1, "dataset_updated_at": "texte"}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://mcp.havoptic.com/mcp