# Agent Verify (npm · agentverify)

Security checks for AI agents and MCP configs: 124 tested checks, from your AI coding assistant.

- Trust score: 70/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `agentverify`: 70/100 (this document), [markdown](https://verifymcp.io/servers/ai-blockchain-ventures-agentverify/agentverify.md), [page](https://verifymcp.io/servers/ai-blockchain-ventures-agentverify/agentverify)

## Channel facts

- Registry: `npm`
- Package: `agentverify`
- Version: `2.0.0`
- 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**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 48/100
  - 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 1 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 76/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 390 tokens (~130/item across 3 items; 3 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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 3 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**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; 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

### How do I install the Agent Verify MCP server?

Agent Verify runs locally as an npm package, launched with npx -y agentverify. 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 ai-blockchain-ventures-agentverify -- npx -y agentverify
```

### Cursor

```json
{
  "mcpServers": {
    "ai-blockchain-ventures-agentverify": {
      "command": "npx",
      "args": [
        "-y",
        "agentverify"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-blockchain-ventures-agentverify": {
      "command": "npx",
      "args": [
        "-y",
        "agentverify"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add ai-blockchain-ventures-agentverify -- npx -y agentverify
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-blockchain-ventures-agentverify": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "agentverify"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-blockchain-ventures-agentverify --command npx --arg -y --arg agentverify
```

### Hermes

```yaml
mcp_servers:
  ai-blockchain-ventures-agentverify:
    command: "npx"
    args: ["-y", "agentverify"]
```

### Netclaw

```json
{
  "McpServers": {
    "ai-blockchain-ventures-agentverify": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "agentverify"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-blockchain-ventures-agentverify -t stdio -c npx -a -y agentverify
```

### Other

```json
{
  "mcpServers": {
    "ai-blockchain-ventures-agentverify": {
      "command": "npx",
      "args": [
        "-y",
        "agentverify"
      ]
    }
  }
}
```

## 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.

### 2026-11-04 (score 70, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-03 (score 55)

First indexed and scored.

## MCP tools (3)

### `scan_path` (~146 tokens)

Scan agent files

Scan an AI agent for security risks before it is deployed: dangerous tool permissions, prompt injection paths, exposed secrets, risky MCP servers, missing approval gates, SQL/SSRF/code-execution risks, and framework-specific issues (LangChain, CrewAI, AutoGen, OpenAI Agents SDK, Claude Agent SDK). Give a file or a folder; a folder is scanned as one report using the most important agent files (up to 60 files / 5MB). Returns a verdict, a 0-100 security score (higher is safer) and findings with file and line.

Input parameters:

- `path` (string, required): File or folder to scan. Relative paths are resolved from the current project.

### `scan_code` (~97 tokens)

Scan agent code

Scan a snippet of agent code, a tool definition, a system prompt or an MCP config for security risks. Use this for code that is not saved to a file yet. Returns a verdict, a security score and findings.

Input parameters:

- `content` (string, required): The code or config to scan.
- `fileName` (string): A file name with the right extension (e.g. agent.py, mcp.json) so the language is detected.

### `scan_mcp_config` (~104 tokens)

Check my MCP servers

Check the MCP servers configured on this computer (Claude Code, Claude Desktop, Cursor, VS Code, Windsurf) for risks such as broad filesystem access, unpinned packages, remote servers without auth, auto-approved tools and API keys stored in plain text. Only the server definitions are read, and secret values are masked on this computer before anything is sent.

Input parameters:

- `path` (string): Optional: a specific MCP config file. Leave empty to check all known locations.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/ai-blockchain-ventures-agentverify/agentverify#diagnostics

## Score history

- 2026-11-05: 70
- 2026-11-04: 70
- 2026-11-03: 55

## Common questions

### What is the Agent Verify MCP server?

Agent Verify is an MCP server listed in the public MCP registry as io.github.AI-Blockchain-Ventures/agentverify. Security checks for AI agents and MCP configs: 124 tested checks, from your AI coding assistant. This page covers its npm package (agentverify).

### Is the Agent Verify MCP server safe to use?

Agent Verify scores 70 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. 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 Verify MCP server expose?

Agent Verify exposes 3 tools: scan_path, scan_code, scan_mcp_config. Their descriptions and schemas cost roughly 347 tokens of context every time the server is loaded.

### Is the Agent Verify MCP server still maintained?

Agent Verify 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 Verify MCP server under?

Agent Verify 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/agentverify
- Socket report: https://socket.dev/npm/package/agentverify
- Repository: https://github.com/AI-Blockchain-Ventures/agentverify
- Website: https://aimodularity.com/agentverify/
- Changelog RSS feed: https://verifymcp.io/servers/ai-blockchain-ventures-agentverify/agentverify.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-blockchain-ventures-agentverify/agentverify.json
- HTML version of this page: https://verifymcp.io/servers/ai-blockchain-ventures-agentverify/agentverify