# Havoptic AI Release Intelligence (remote · mcp.havoptic.com)

Release intelligence for AI coding tools: releases, typed changes, breaking changes, cadence.

- Trust score: 71/100 (medium)
- Change this week: +41
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `mcp.havoptic.com`: 71/100 (this document), [markdown](https://verifymcp.io/servers/com-havoptic-releases/mcp.md), [page](https://verifymcp.io/servers/com-havoptic-releases/mcp)

## Channel facts

- Endpoint: `https://mcp.havoptic.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 66/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 406, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 83/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 4166 tokens (~49/item across 85 items; 15 tools + 70 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 95% of tool parameters carry a description.
  - Structured output schemas are declared (67% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Havoptic AI Release Intelligence MCP server?

Havoptic AI Release Intelligence is a hosted endpoint at https://mcp.havoptic.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-havoptic-releases 'https://mcp.havoptic.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-havoptic-releases": {
      "url": "https://mcp.havoptic.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-havoptic-releases": {
      "type": "http",
      "url": "https://mcp.havoptic.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-havoptic-releases]
url = "https://mcp.havoptic.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-havoptic-releases": {
      "type": "remote",
      "url": "https://mcp.havoptic.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-havoptic-releases --url 'https://mcp.havoptic.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-havoptic-releases:
    url: "https://mcp.havoptic.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-havoptic-releases": {
      "Transport": "http",
      "Url": "https://mcp.havoptic.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-havoptic-releases -t streamable-http -u 'https://mcp.havoptic.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-havoptic-releases": {
      "type": "http",
      "url": "https://mcp.havoptic.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 70, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-02 (score 69, +39)

- [security improvement] Authorization: unverified → partial
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Tool coverage: 67
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: pass
- [functional] First check of Tool coverage: 95
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: good

### 2026-10-20 (score 30)

First indexed and scored.

## MCP tools (15)

### `list_tracked_tools` (~71 tokens)

List tracked AI coding tools

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.

### `latest_releases` (~334 tokens)

Latest releases

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.

Input parameters:

- `detail` (string): brief omits infographics and fullNotes; full includes complete notes on single-release reads.
- `limit` (integer): Max releases to return (default 10)
- `tool` (string): 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', 'lova…

### `release_history` (~375 tokens)

Release history

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.

Input parameters:

- `detail` (string): brief omits infographics and fullNotes; full includes complete notes on single-release reads.
- `limit` (integer): Max releases to return (default 50)
- `since` (string): Only releases on/after this ISO date (e.g. '2026-01-01')
- `tool` (string, required): 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', 'lova…
- `until` (string): Only releases on/before this ISO date

### `search_release_notes` (~323 tokens)

Search release notes

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.

Input parameters:

- `limit` (integer): Max results (default 10)
- `query` (string, required): Search terms, e.g. '--dangerously-skip-permissions' or 'MCP OAuth'
- `tool` (string): 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', 'lova…

### `feature_timeline` (~86 tokens)

Feature introduction timeline

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.

Input parameters:

- `feature` (string): Feature id or name substring, e.g. 'subagents', 'mcp', 'planning'

### `list_tools` (~107 tokens)

List tracked products

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').

Input parameters:

- `category` (string)
- `query` (string): Fuzzy match on name/alias
- `vendor` (string): Vendor id slug, e.g. 'anthropic', 'google'

Output parameters:

- `dataset_updated_at` (string|null)
- `estimated_tokens` (integer)
- `freshness_note` (string|null)
- `next_cursor` (string|null)
- `object` (string)
- `omitted` (object)
- `suggestions` (array)
- `tools` (array)
- `truncated` (boolean)

### `get_latest_releases` (~212 tokens)

Latest releases

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.

Input parameters:

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

Output parameters:

- `dataset_updated_at` (string|null)
- `estimated_tokens` (integer)
- `freshness_note` (string|null)
- `next_cursor` (string|null)
- `object` (string)
- `omitted` (object)
- `releases` (array)
- `total` (integer)
- `truncated` (boolean)

### `whats_changed_since` (~211 tokens)

What changed since

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.

Input parameters:

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

Output parameters:

- `dataset_updated_at` (string|null)
- `estimated_tokens` (integer)
- `freshness_note` (string|null)
- `items` (array)
- `next_cursor` (string|null)
- `object` (string)
- `omitted` (object)
- `since` (string)
- `truncated` (boolean)

### `search_changes` (~163 tokens)

Search changes

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.

Input parameters:

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

Output parameters:

- `dataset_updated_at` (string|null)
- `estimated_tokens` (integer)
- `freshness_note` (string|null)
- `items` (array)
- `next_cursor` (string|null)
- `object` (string)
- `omitted` (object)
- `query` (string)
- `releases` (array)
- `truncated` (boolean)

### `get_release` (~179 tokens)

Get one release

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.

Input parameters:

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

Output parameters:

- `dataset_updated_at` (string|null)
- `estimated_tokens` (integer)
- `freshness_note` (string|null)
- `next_cursor` (string|null)
- `object` (string)
- `omitted` (object)
- `release` (object)
- `truncated` (boolean)

### `get_upgrade_notes` (~121 tokens)

Upgrade notes between versions

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.

Input parameters:

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

Output parameters:

- `dataset_updated_at` (string|null)
- `estimated_tokens` (integer)
- `freshness_note` (string|null)
- `from` (string)
- `next_cursor` (string|null)
- `object` (string)
- `omitted` (object)
- `product_id` (string)
- `release_count` (integer)
- `to` (string)
- `truncated` (boolean)

### `get_breaking_changes` (~113 tokens)

Breaking changes feed

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.

Input parameters:

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

Output parameters:

- `dataset_updated_at` (string|null)
- `estimated_tokens` (integer)
- `freshness_note` (string|null)
- `items` (array)
- `next_cursor` (string|null)
- `object` (string)
- `omitted` (object)
- `since` (string)
- `truncated` (boolean)

### `compare_tools` (~145 tokens)

Compare tools

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.

Input parameters:

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

Output parameters:

- `aspects` (array)
- `cadence` (array)
- `dataset_updated_at` (string|null)
- `estimated_tokens` (integer)
- `freshness_note` (string|null)
- `next_cursor` (string|null)
- `object` (string)
- `omitted` (object)
- `tools` (array)
- `truncated` (boolean)

### `feature_adoption` (~73 tokens)

Feature adoption timeline

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.

Input parameters:

- `feature` (string, required): Feature id or substring, e.g. mcp-oauth, subagents, planning

Output parameters:

- `available` (boolean)
- `dataset_updated_at` (string|null)
- `estimated_tokens` (integer)
- `features` (array)
- `freshness_note` (string|null)
- `next_cursor` (string|null)
- `object` (string)
- `omitted` (object)
- `truncated` (boolean)

### `cadence_stats` (~103 tokens)

Release cadence stats

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.

Input parameters:

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

Output parameters:

- `cadences` (array)
- `dataset_updated_at` (string|null)
- `estimated_tokens` (integer)
- `freshness_note` (string|null)
- `next_cursor` (string|null)
- `object` (string)
- `omitted` (object)
- `truncated` (boolean)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-havoptic-releases/mcp#diagnostics

## Score history

- 2026-11-05: 71
- 2026-11-04: 70
- 2026-11-03: 70
- 2026-11-02: 69
- 2026-11-01: 30
- 2026-10-31: 30
- 2026-10-30: 30
- 2026-10-29: 30
- 2026-10-28: 30
- 2026-10-27: 30
- 2026-10-26: 30
- 2026-10-25: 30
- 2026-10-24: 30
- 2026-10-23: 30
- 2026-10-22: 30
- 2026-10-21: 30
- 2026-10-20: 30

## Common questions

### What is the Havoptic AI Release Intelligence MCP server?

Havoptic AI Release Intelligence is an MCP server listed in the public MCP registry as com.havoptic/releases. Release intelligence for AI coding tools: releases, typed changes, breaking changes, cadence. This page covers its hosted endpoint (https://mcp.havoptic.com/mcp).

### Is the Havoptic AI Release Intelligence MCP server safe to use?

Havoptic AI Release Intelligence scores 71 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Havoptic AI Release Intelligence MCP server expose?

Havoptic AI Release Intelligence exposes 15 tools: list_tracked_tools, latest_releases, release_history, search_release_notes, feature_timeline, and 10 more. Their descriptions and schemas cost roughly 2,616 tokens of context every time the server is loaded.

### Does the Havoptic AI Release Intelligence MCP server require authentication?

No. We connected to Havoptic AI Release Intelligence without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Havoptic AI Release Intelligence MCP server still maintained?

Havoptic AI Release Intelligence is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.havoptic.com/mcp
- Repository: https://github.com/scotthavird/havoptic.com
- Website: https://www.havoptic.com/api-docs
- Changelog RSS feed: https://verifymcp.io/servers/com-havoptic-releases/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-havoptic-releases/mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-havoptic-releases/mcp