# agent-config (npm · @event4u/agent-config)

Governed skills, rules and commands for AI coding agents, served by a read-only MCP server.

- Trust score: 84/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `@event4u/agent-config`: 84/100 (this document), [markdown](https://verifymcp.io/servers/event4u-app-agent-config/event4u-agent-config.md), [page](https://verifymcp.io/servers/event4u-app-agent-config/event4u-agent-config)

## Channel facts

- Registry: `npm`
- Package: `@event4u/agent-config`
- Version: `20.1.0`
- 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 2026-11-05.

- **Supply Chain Security**: 99/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 55 of 197 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to event4u-app/agent-config).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 72/100
  - 84% 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 5308 tokens (~21/item across 244 items; 2 tools + 242 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 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).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% 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 2 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 40/100
  - Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28.

## Install

### How do I install the agent-config MCP server?

agent-config runs locally as an npm package, launched with npx -y @event4u/agent-config. 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 event4u-app-agent-config -- npx -y @event4u/agent-config
```

### Cursor

```json
{
  "mcpServers": {
    "event4u-app-agent-config": {
      "command": "npx",
      "args": [
        "-y",
        "@event4u/agent-config"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "event4u-app-agent-config": {
      "command": "npx",
      "args": [
        "-y",
        "@event4u/agent-config"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add event4u-app-agent-config -- npx -y @event4u/agent-config
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "event4u-app-agent-config": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@event4u/agent-config"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add event4u-app-agent-config --command npx --arg -y --arg @event4u/agent-config
```

### Hermes

```yaml
mcp_servers:
  event4u-app-agent-config:
    command: "npx"
    args: ["-y", "@event4u/agent-config"]
```

### Netclaw

```json
{
  "McpServers": {
    "event4u-app-agent-config": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@event4u/agent-config"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add event4u-app-agent-config -t stdio -c npx -a -y @event4u/agent-config
```

### Other

```json
{
  "mcpServers": {
    "event4u-app-agent-config": {
      "command": "npx",
      "args": [
        "-y",
        "@event4u/agent-config"
      ]
    }
  }
}
```

## 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 84, +11)

- [security improvement] CVE-2026-118773 no longer affects this package
- [security improvement] CVE-2026-118764 no longer affects this package
- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → 0.88

### 2026-11-04 (score 73, −8)

- [security regression] Tool safety: pass → unverified
- [security regression] Known CVEs: fail → unverified
- [security regression] Stability: 0.33 → unverified
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Dependency health: 0.88 → unverified
- [functional regression] Schema quality: 84 → unverified
- [functional] First check of Tool coverage: 100
- [functional] Package version: 19.2.0 → 20.1.0
- [functional] Package version: 19.2.0 → 20.0.0

### 2026-11-02 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 80, 0)

- [security regression] Stability: 0.23 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 84 → unverified
- [functional] Package version: 19.1.0 → 19.2.0

### 2026-10-31 (score 80, +14)

- [security regression] CVE-2026-118764 affects this package: medium
- [security regression] CVE-2026-118773 affects this package: medium
- [security regression] Known CVEs: pass → fail
- [security improvement] Malware scan: unverified → pass

### 2026-10-30 (score 66, −14)

- [security regression] Malware scan: pass → unverified
- [functional] Package version: 19.0.0 → 19.1.0

### 2026-10-28 (score 80, +1)

- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.10 → unverified
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 84 → unverified
- [functional] Package version: 18.2.0 → 19.0.0

### 2026-10-26 (score 79, +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.

## MCP tools (2)

### `suggest_skill_for_task` (~127 tokens)

Rank skills against a free-form task description. Use when the skill you need is not in the catalogue the host delivered, so asking by name is impossible and asking by task is not. Each row carries the skill's own description — its routing criteria, including any clause saying when to use something else. CHOOSE BY READING THE ROWS, then open at most two bodies with read_skill. Returns names, scores, personas and descriptions — never bodies.

Input parameters:

- `limit` (integer): Max results. Default 8.
- `task` (string, required): The task to match skills against.

Output parameters:

- `clamped_from` (number)
- `error` (string)
- `skills_indexed` (number)
- `status` (string)
- `suggestions` (array)
- `tier_filter` (string)
- `tiers` (string)

### `read_skill` (~32 tokens)

Return one skill body by name, as listed by suggest_skill_for_task.

Input parameters:

- `name` (string, required): Skill name.

Output parameters:

- `body` (string)
- `description` (string)
- `error` (string)
- `name` (string)
- `source` (string)
- `status` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/event4u-app-agent-config/event4u-agent-config#diagnostics

## Score history

- 2026-11-05: 84
- 2026-11-04: 73
- 2026-11-03: 81
- 2026-11-02: 81
- 2026-11-01: 80
- 2026-10-31: 80
- 2026-10-30: 66
- 2026-10-29: 80
- 2026-10-28: 80
- 2026-10-27: 79
- 2026-10-26: 79
- 2026-10-25: 78
- 2026-10-24: 52

## Common questions

### What is the agent-config MCP server?

agent-config is an MCP server listed in the public MCP registry as io.github.event4u-app/agent-config. Governed skills, rules and commands for AI coding agents, served by a read-only MCP server. This page covers its npm package (@event4u/agent-config).

### Is the agent-config MCP server safe to use?

agent-config scores 84 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 agent-config MCP server expose?

agent-config exposes 2 tools: suggest_skill_for_task, read_skill. Their descriptions and schemas cost roughly 159 tokens of context every time the server is loaded.

### Is the agent-config MCP server still maintained?

agent-config 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.

### What licence is the agent-config MCP server under?

agent-config declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@event4u/agent-config
- Socket report: https://socket.dev/npm/package/@event4u/agent-config
- Repository: https://github.com/event4u-app/agent-config
- Website: https://event4u-app.github.io/agent-config
- Changelog RSS feed: https://verifymcp.io/servers/event4u-app-agent-config/event4u-agent-config.xml
- Changelog JSON feed: https://verifymcp.io/servers/event4u-app-agent-config/event4u-agent-config.json
- HTML version of this page: https://verifymcp.io/servers/event4u-app-agent-config/event4u-agent-config