# HeyClaude — Claude & AI workflow directory (remote · heyclau.de)

Search the HeyClaude directory of Claude Code agents, MCP servers, skills, and tools.

- Trust score: 78/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `heyclau.de`: 78/100 (this document), [markdown](https://verifymcp.io/servers/jsonbored-heyclaude/api-mcp.md), [page](https://verifymcp.io/servers/jsonbored-heyclaude/api-mcp)
- npm · `@heyclaude/mcp`: 44/100, [markdown](https://verifymcp.io/servers/jsonbored-heyclaude/heyclaude-mcp.md), [page](https://verifymcp.io/servers/jsonbored-heyclaude/heyclaude-mcp)

## Channel facts

- Endpoint: `https://heyclau.de/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.4.0`

## 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 2026-08-03.

- **Endpoint Security**: 80/100
  - 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 is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 85/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 3237 tokens (~77/item across 42 items; 28 tools + 14 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 99% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http jsonbored-heyclaude https://heyclau.de/api/mcp
```

### Codex

```toml
[mcp_servers.jsonbored-heyclaude]
url = "https://heyclau.de/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jsonbored-heyclaude": {
      "type": "remote",
      "url": "https://heyclau.de/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add jsonbored-heyclaude --url https://heyclau.de/api/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  jsonbored-heyclaude:
    url: "https://heyclau.de/api/mcp"
```

### Other

```json
{
  "mcpServers": {
    "jsonbored-heyclaude": {
      "type": "http",
      "url": "https://heyclau.de/api/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.

### 2026-08-03 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 77, +4)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 73, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 73, 0)

- [functional] Server version: 0.14.2 → 0.14.7

### 2026-07-28 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 72, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 71)

First indexed and scored.

## MCP tools (28)

### `registry.search` (~266 tokens)

Search read-only HeyClaude registry entries by query, category, exact tag, and skill platform compatibility.

Input parameters:

- `category` (string): Restrict results to this category (e.g. 'mcp', 'skills', 'hooks').
- `claimStatus` (string): Filter by claim or verification status ('unclaimed', 'pending', 'verified', or 'all').
- `downloadTrust` (string): Filter by package download trust level ('first-party', 'external', 'none', or 'all').
- `hasPrivacyNotes` (string): Filter by whether entries include privacy notes ('true', 'false', or 'all').
- `hasSafetyNotes` (string): Filter by whether entries include safety notes ('true', 'false', or 'all').
- `limit` (integer): Maximum number of results to return (1–25, default 10).
- `platform` (string): Restrict to entries compatible with this platform (e.g. 'claude-desktop', 'cursor').
- `query` (string): Keywords to search for in entry titles, descriptions, and tags.
- `sourceStatus` (string): Filter by whether the entry's source URL is reachable ('available', 'missing', or 'all').
- `tag` (string): Return only entries carrying this exact tag.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `registry.plan` (~155 tokens)

Plan a read-only Claude or Codex workflow toolbox from ranked HeyClaude registry entries. Each entry includes an inline install block (install command, config snippet, download URL) and the recommended stack is summarized as a copy-pasteable installPlan, alongside trust and follow-up guidance.

Input parameters:

- `category` (string): Constrain recommendations to a single category (e.g. 'mcp', 'skills').
- `goal` (string, required): Plain-language description of the workflow or goal to build a toolbox for.
- `limit` (integer): Maximum number of recommendations to include (1–10, default 6).
- `platform` (string): Target platform or client for the toolbox (e.g. 'claude-desktop', 'cursor').

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `registry.recommend` (~190 tokens)

Answer 'what should I use to do X' in one call. Given a plain-language task (and optional platform/category), returns the best-match HeyClaude entries ranked by fit — each with why it fits, trust summary, disclosed safety/privacy notes, and an inline install block — plus a topPick and a consolidated installPlan. Unlike workflow.plan it does not force category diversity; it returns the genuinely best matches. Collapses the search → compare → detail → asset loop into a single answer-shaped response.

Input parameters:

- `category` (string): Restrict recommendations to a single category.
- `limit` (integer): Maximum recommendations to return (default 3).
- `platform` (string): Restrict to entries compatible with this platform.
- `task` (string, required): Plain-language description of what you want to accomplish, e.g. 'review pull requests in Claude Code' or 'connect to a Postgres database'.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `registry.info` (~26 tokens)

Fetch read-only HeyClaude MCP package, registry, tool, and public rate-limit metadata.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `registry.list` (~264 tokens)

List read-only HeyClaude entries with bounded pagination and optional category, platform, tag, and query filters.

Input parameters:

- `category` (string): Category to list entries from (e.g. 'mcp', 'skills', 'agents').
- `claimStatus` (string): Filter by claim or verification status ('unclaimed', 'pending', 'verified', or 'all').
- `downloadTrust` (string): Filter by package download trust level ('first-party', 'external', 'none', or 'all').
- `hasPrivacyNotes` (string): Filter by whether entries include privacy notes ('true', 'false', or 'all').
- `hasSafetyNotes` (string): Filter by whether entries include safety notes ('true', 'false', or 'all').
- `limit` (integer): Number of entries per page (1–25, default 20).
- `offset` (integer): Pagination offset for large result sets (0–5000).
- `platform` (string): Filter to entries compatible with this platform.
- `query` (string): Keyword search to narrow the listing.
- `sourceStatus` (string): Filter by whether the entry's source URL is reachable ('available', 'missing', or 'all').
- `tag` (string): Filter to entries carrying this exact tag.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `registry.updates` (~263 tokens)

List recently added or upstream-updated HeyClaude entries from generated registry metadata.

Input parameters:

- `category` (string): Restrict to a single category (e.g. 'mcp', 'hooks').
- `claimStatus` (string): Filter by claim or verification status ('unclaimed', 'pending', 'verified', or 'all').
- `downloadTrust` (string): Filter by package download trust level ('first-party', 'external', 'none', or 'all').
- `hasPrivacyNotes` (string): Filter by whether entries include privacy notes ('true', 'false', or 'all').
- `hasSafetyNotes` (string): Filter by whether entries include safety notes ('true', 'false', or 'all').
- `limit` (integer): Maximum entries to return (1–25, default 10).
- `platform` (string): Filter to entries compatible with this platform.
- `query` (string): Keyword search to narrow the listing.
- `since` (string): Return only entries updated after this date, e.g. '2026-05-01'.
- `sourceStatus` (string): Filter by whether the entry's source URL is reachable ('available', 'missing', or 'all').
- `tag` (string): Filter to entries carrying this exact tag.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `entry.related` (~89 tokens)

Fetch read-only related HeyClaude entries based on category, tags, platforms, keywords, and source metadata.

Input parameters:

- `category` (string, required): Category of the reference entry (e.g. 'mcp', 'skills').
- `limit` (integer): Maximum related entries to return (1–25, default 8).
- `slug` (string, required): Slug of the reference entry to find related entries for.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `entry.detail` (~243 tokens)

Fetch a read-only HeyClaude registry entry detail payload by category and slug. By default (bodyMode='excerpt') the body markdown is trimmed to a short lead and large copyable fields are omitted to conserve context, with bodyChars/bodyTruncated/omittedFields describing what was dropped; pass bodyMode='full' for the complete content or 'none' to drop the body entirely. Use entry.asset to retrieve omitted install/script content.

Input parameters:

- `bodyMode` (string): How much entry content to return. 'excerpt' (default) trims the body markdown to a short lead and omits large copyable fields (scriptBody, fullCopyableContent, copySnippet), reporting what was droppe…
- `category` (string, required): Category of the entry (e.g. 'mcp', 'skills', 'agents').
- `slug` (string, required): Slug of the entry to fetch.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `entry.asset` (~168 tokens)

Fetch the category-aware copy/install asset for a HeyClaude entry without writing local files. Pass assetType (e.g. 'install_command', 'config_snippet') to return only that asset and avoid the full_content/script payloads when you do not need them.

Input parameters:

- `assetType` (string): Return only this asset type instead of every asset. Use it to avoid paying for the full_content or script payload (up to tens of KB) when you only need, e.g., the install_command or config_snippet.
- `category` (string, required): Category of the entry (e.g. 'mcp', 'skills').
- `platform` (string): Target platform to tailor the install command or config snippet.
- `slug` (string, required): Slug of the entry to fetch the asset for.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `entry.compare` (~71 tokens)

Compare 2-5 read-only HeyClaude entries by fit, category, platforms, source metadata, and install complexity.

Input parameters:

- `entries` (array, required): 2–5 entries to compare, each identified by category and slug.
- `platform` (string): Target platform for the comparison (affects install steps shown).

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `registry.stats` (~27 tokens)

Fetch aggregate read-only registry stats, freshness, category counts, and real source-signal coverage.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `install.setup` (~78 tokens)

Fetch read-only MCP client setup snippets for Codex, Claude Desktop, Cursor, Windsurf, or remote HTTP clients.

Input parameters:

- `client` (string): MCP client to generate a setup snippet for (e.g. 'claude-desktop', 'cursor').
- `endpointUrl` (string): Override the default remote MCP endpoint URL in the generated snippet.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `install.compatibility` (~51 tokens)

Fetch platform compatibility metadata for a HeyClaude skill entry.

Input parameters:

- `category` (string): Entry category (defaults to 'skills').
- `slug` (string, required): Slug of the skill entry to check compatibility for.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `install.guidance` (~91 tokens)

Fetch read-only install, config, usage, and package guidance for a HeyClaude entry.

Input parameters:

- `category` (string, required): Category of the entry (e.g. 'mcp', 'skills').
- `platform` (string): Target platform to tailor the install steps (e.g. 'claude-desktop', 'cursor').
- `slug` (string, required): Slug of the entry to get install guidance for.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `install.adapter` (~59 tokens)

Fetch generated read-only platform adapter content, currently Cursor rule adapters for skill packages.

Input parameters:

- `platform` (string): Target platform for the adapter (defaults to 'cursor').
- `slug` (string, required): Slug of the skill to generate a platform adapter for.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `registry.feeds` (~27 tokens)

List read-only HeyClaude registry feeds, category feeds, platform feeds, and artifact locations.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `submission.schema` (~42 tokens)

Fetch read-only HeyClaude submission schemas for PR-first intake by category.

Input parameters:

- `category` (string): Submission category to fetch the schema for. Returns all schemas if omitted.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `submission.validate` (~47 tokens)

Validate a HeyClaude content submission draft locally without creating GitHub issues, pull requests, or publishing content.

Input parameters:

- `fields` (object, required): Submission field values to validate against the HeyClaude content schema.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `submission.duplicates` (~229 tokens)

Search generated registry artifacts for likely duplicate entries before a user opens a submission PR.

Input parameters:

- `brandDomain` (string): Brand's canonical domain (e.g. 'example.com') to check for duplicates.
- `category` (string): Category to scope the duplicate search.
- `docsUrl` (string): Documentation URL to check for duplicates.
- `downloadUrl` (string): Download or release URL to check for duplicates.
- `githubUrl` (string): GitHub repository URL to check for duplicates.
- `limit` (integer): Maximum number of duplicate candidates to return (1–10).
- `name` (string): Tool or resource name to search for near-duplicates.
- `slug` (string): Slug to check for an exact existing entry.
- `sourceUrl` (string): Primary source URL to check against existing entries.
- `sourceUrls` (array): Multiple source URLs to check (e.g. GitHub repo + docs site).
- `title` (string): Display title to search for near-duplicates.
- `websiteUrl` (string): Homepage or product URL to check for duplicates.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `submission.urls` (~67 tokens)

Build prefilled HeyClaude submit and review URLs for a validated PR-first submission draft without making write calls.

Input parameters:

- `fields` (object, required): Validated submission field values to encode into submit and review URLs.
- `includePrBody` (boolean): Include a pre-filled PR body in the returned URL.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `submission.guidance` (~43 tokens)

Fetch category-specific HeyClaude contribution guidance, required fields, and review expectations.

Input parameters:

- `category` (string): Category to fetch contribution guidelines for. Returns general guidance if omitted.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `submission.prepare` (~46 tokens)

Build a read-only maintainer-reviewed HeyClaude submission draft with canonical PR text and URLs.

Input parameters:

- `fields` (object, required): Submission field values to compile into a canonical maintainer-reviewed PR draft.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `submission.examples` (~44 tokens)

Fetch read-only category examples and templates for faster, more accurate HeyClaude submissions.

Input parameters:

- `category` (string): Category to fetch submission examples for. Returns cross-category examples if omitted.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `submission.review` (~71 tokens)

Review a HeyClaude submission draft locally for schema errors, duplicate risk, and maintainer checklist items without writing to GitHub.

Input parameters:

- `duplicateLimit` (integer): Maximum number of duplicate candidates to include in the review.
- `fields` (object, required): Submission field values to review for schema errors and maintainer checklist items.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `submission.policy` (~30 tokens)

Fetch HeyClaude's read-only submission, artifact, import, and maintainer-review policy for contributors and agents.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `entry.trust` (~93 tokens)

Explain deterministic trust, source, package, safety, privacy, and review metadata signals for one HeyClaude entry. This is a metadata review only and does not provide malware scanning, automatic safety guarantees, or installation approval.

Input parameters:

- `category` (string, required): Category of the entry (e.g. 'mcp', 'skills', 'agents').
- `slug` (string, required): Slug of the entry to explain trust signals for.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `entry.safety` (~96 tokens)

Review 1-5 HeyClaude entries for source, package, safety, and privacy metadata fit before install or recommendation. This is a metadata review only and does not provide malware scanning, automatic safety guarantees, or installation approval.

Input parameters:

- `entries` (array, required): 1–5 entries to review for safety and privacy metadata, each identified by category and slug.
- `platform` (string): Target platform to contextualize safety and compatibility notes.

Output parameters:

- `ok` (boolean)
- `policy` (object)

### `entry.coverage` (~109 tokens)

Compare 2-5 HeyClaude entries side by side by how much trust metadata they disclose (source, package, safety, privacy, and review provenance) and rank them by deterministic signal coverage. This measures disclosed-metadata completeness only; it is not a malware scan, a safety verdict, or installation approval, and a higher score does not mean an entry is safe.

Input parameters:

- `entries` (array, required): 2-5 entries to compare by disclosed trust metadata coverage.
- `platform` (string)

Output parameters:

- `ok` (boolean)
- `policy` (object)

## Diagnostics

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

## Score history

- 2026-08-03: 78
- 2026-08-02: 77
- 2026-08-01: 77
- 2026-07-31: 77
- 2026-07-30: 73
- 2026-07-29: 73
- 2026-07-28: 73
- 2026-07-27: 72
- 2026-07-26: 71

## Links

- Remote endpoint: https://heyclau.de/api/mcp
- Repository: https://github.com/JSONbored/awesome-claude
- Website: https://heyclau.de/
- Changelog RSS feed: https://verifymcp.io/servers/jsonbored-heyclaude/api-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/jsonbored-heyclaude/api-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/jsonbored-heyclaude/api-mcp