# OpenClaw Agent Instruction Registry (npm · agentbase-mcp)

Search and retrieve agent instruction files: system prompts, skills, workflows, and safety filters.

- Trust score: 65/100 (medium)
- Change this week: +19
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `agentbase-mcp`: 65/100 (this document), [markdown](https://verifymcp.io/servers/izworskic-openclaw-registry/agentbase-mcp.md), [page](https://verifymcp.io/servers/izworskic-openclaw-registry/agentbase-mcp)

## Channel facts

- Registry: `npm`
- Package: `agentbase-mcp`
- Version: `1.0.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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.

- **Supply Chain Security**: 86/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 154 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 350 tokens (~87/item across 4 items; 4 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add izworskic-openclaw-registry -- npx -y agentbase-mcp
```

### Codex

```bash
codex mcp add izworskic-openclaw-registry -- npx -y agentbase-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "izworskic-openclaw-registry": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "agentbase-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add izworskic-openclaw-registry --command npx --arg -y --arg agentbase-mcp
```

### Hermes

```yaml
mcp_servers:
  izworskic-openclaw-registry:
    command: "npx"
    args: ["-y", "agentbase-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "izworskic-openclaw-registry": {
      "command": "npx",
      "args": [
        "-y",
        "agentbase-mcp"
      ]
    }
  }
}
```

## 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 65, +44)

- [security regression] Provenance: unverified → fail
- [security improvement] Malware scan: unverified → pass
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Security disclosure: unverified → fail
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → excellent
- [functional] Licence: MIT

### 2026-08-02 (score 21, −15)

- [security regression] Malware scan: pass → unverified
- [functional regression] Security disclosure: fail → unverified

### 2026-08-01 (score 36, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-07-31 (score 21, −25)

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

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (4)

### `search_registry` (~144 tokens)

Search the OpenClaw agent instruction registry. Returns matching instruction files with metadata. Use this to find system prompts, skills, workflows, domain packs, safety filters, and orchestration patterns.

Input parameters:

- `category` (string): Filter by category. One of: system-prompts, skills, workflows, tool-definitions, domain-packs, safety-filters, orchestration
- `featured_only` (boolean): If true, return only featured (quality >= 90) files.
- `min_quality` (number): Minimum quality score (0-100). Recommended: 80 for production use.
- `q` (string): Keyword search across title, tags, and slug. Optional.

### `get_instruction` (~131 tokens)

Fetch a complete instruction file from the OpenClaw registry by slug. Returns the full Markdown file including YAML frontmatter, purpose, usage notes, and the deployable instruction text. The instruction is in the "## The Instruction" section.

Input parameters:

- `instruction_only` (boolean): If true, return only the deployable instruction text (extracted from the fenced code block). If false, return the full Markdown file. Default: false.
- `slug` (string, required): The slug of the instruction file (e.g. "tier1-customer-support", "structured-web-research"). Get slugs from search_registry.

### `list_categories` (~35 tokens)

List all categories in the OpenClaw registry with file counts and descriptions. Use this to understand what types of instruction files are available.

### `get_featured` (~40 tokens)

Return all featured instruction files (quality score 90+). These are verified, complete, and production-tested. Good starting point for finding high-quality instructions.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/izworskic-openclaw-registry/agentbase-mcp#diagnostics

## Score history

- 2026-08-03: 65
- 2026-08-02: 21
- 2026-08-01: 36
- 2026-07-31: 21
- 2026-07-30: 46
- 2026-07-28: 46
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/agentbase-mcp
- Socket report: https://socket.dev/npm/package/agentbase-mcp
- Repository: https://github.com/AgentBase1/mcp-server
- Website: https://openclaw-sandy-eight.vercel.app/
- Changelog RSS feed: https://verifymcp.io/servers/izworskic-openclaw-registry/agentbase-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/izworskic-openclaw-registry/agentbase-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/izworskic-openclaw-registry/agentbase-mcp