# io.github.mdfifty50-boop/agent-security (npm · agent-security-mcp)

Security scanning and threat detection for AI agents

- Trust score: 63/100 (medium)
- Change this week: +19
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `agent-security-mcp`: 63/100 (this document), [markdown](https://verifymcp.io/servers/mdfifty50-boop-agent-security/agent-security-mcp.md), [page](https://verifymcp.io/servers/mdfifty50-boop-agent-security/agent-security-mcp)

## Channel facts

- Registry: `npm`
- Package: `agent-security-mcp`
- Version: `0.1.3`
- 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**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (97 of 101), 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 (97 of 101), 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 101 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 45/100
  - 0% 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 622 tokens (~62/item across 10 items; 8 tools + 2 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add mdfifty50-boop-agent-security -- npx -y agent-security-mcp
```

### Codex

```bash
codex mcp add mdfifty50-boop-agent-security -- npx -y agent-security-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mdfifty50-boop-agent-security": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "agent-security-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add mdfifty50-boop-agent-security --command npx --arg -y --arg agent-security-mcp
```

### Hermes

```yaml
mcp_servers:
  mdfifty50-boop-agent-security:
    command: "npx"
    args: ["-y", "agent-security-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "mdfifty50-boop-agent-security": {
      "command": "npx",
      "args": [
        "-y",
        "agent-security-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 63, +4)

- [functional improvement] Stability: unverified → 0.23

### 2026-08-02 (score 59, +44)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Security disclosure: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] License: unverified → pass
- [functional improvement] Schema quality: unverified → 0
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional] Licence: MIT

### 2026-08-01 (score 15, −4)

- [functional regression] Schema quality: 0 → unverified

### 2026-07-31 (score 19, −7)

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

### 2026-07-30 (score 26, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 44)

First indexed and scored.

## MCP tools (8)

### `health_check` (~20 tokens)

Returns server health, uptime, version, and usage stats

### `scan_mcp_config` (~76 tokens)

Scan an MCP server configuration for security issues including dangerous commands, exposed secrets, network exposure, and container misconfigurations. Returns a risk score (0-100), issues found, and actionable recommendations.

Input parameters:

- `config` (object, required): MCP server configuration object
- `server_name` (string, required): Name of the MCP server being scanned

### `detect_prompt_injection` (~85 tokens)

Analyze text for prompt injection attempts. Detects instruction overrides, identity manipulation, system prompt extraction, data exfiltration, delimiter attacks, encoded injections, and privilege escalation. Context-aware risk scoring.

Input parameters:

- `context` (string, required): Where this text originates — affects risk scoring (user_input is highest risk)
- `text` (string, required): The text to analyze for prompt injection patterns

### `validate_scope_contract` (~81 tokens)

Check if an agent action complies with its scope contract. Validates tool usage against allowlists, file access against permitted paths, and boundary constraints (no_network, read_only, no_exec, no_secrets).

Input parameters:

- `action` (object, required): The action to validate against the scope contract
- `scope_contract` (object, required): The agent scope contract defining permitted actions

### `scan_secrets` (~96 tokens)

Detect leaked secrets and credentials in text or code. Identifies API keys (OpenAI, AWS, GitHub, GCP, Stripe, Slack, Telegram), JWT tokens, database connection strings, private keys, and .env patterns. All values are masked in output.

Input parameters:

- `content` (string, required): The text or code content to scan for secrets
- `content_type` (string, required): Type of content being scanned — affects detection sensitivity

### `audit_agent_permissions` (~89 tokens)

Audit an agent configuration for over-privileged access. Compares granted permissions against role-based expectations (researcher, analyst, developer, reviewer, orchestrator, monitor). Flags principle of least privilege violations.

Input parameters:

- `agent_config` (object, required): Agent configuration to audit
- `role` (string, required): The declared role of the agent (researcher, analyst, developer, reviewer, orchestrator, monitor)

### `generate_security_report` (~99 tokens)

Generate a comprehensive security assessment report for an agent deployment. Aggregates results from config scans and permission audits into a prioritized remediation plan with OWASP LLM Top 10 compliance notes.

Input parameters:

- `agent_name` (string, required): Name of the agent or deployment being assessed
- `audit_results` (array): Array of audit_agent_permissions results to include in the report
- `configs` (array): Array of scan_mcp_config results to include in the report

### `detect_tool_poisoning` (~57 tokens)

Analyze an MCP tool definition for poisoning indicators — hidden instructions in descriptions that could manipulate agent behavior. Covers OWASP Agentic Top 10 tool poisoning attack vectors.

Input parameters:

- `tool_definition` (object, required): The MCP tool definition to analyze

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/mdfifty50-boop-agent-security/agent-security-mcp#diagnostics

## Score history

- 2026-08-03: 63
- 2026-08-02: 59
- 2026-08-01: 15
- 2026-07-31: 19
- 2026-07-30: 26
- 2026-07-28: 44
- 2026-07-27: 44

## Links

- npm package: https://www.npmjs.com/package/agent-security-mcp
- Socket report: https://socket.dev/npm/package/agent-security-mcp
- Repository: https://github.com/mdfifty50-boop/agent-security-mcp
- Changelog RSS feed: https://verifymcp.io/servers/mdfifty50-boop-agent-security/agent-security-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/mdfifty50-boop-agent-security/agent-security-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/mdfifty50-boop-agent-security/agent-security-mcp