# Systemores AI Agent & MCP Security Auditor

> Systemores AI Agent & MCP Security Auditor is a freemium MCP server for security. Audit AI agent prompts, MCP tool schemas and agent graphs from your IDE. It can run locally on your machine or as a hosted remote server.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** CLI, API, vscode
- **Website:** https://audit.systemores.com
- **Repository:** https://github.com/bobcar0/systemores-plugin
- **MCP Registry name:** io.github.bobcar0/systemores-plugin
- **Categories:** security, AI models and LLM tooling
- **Listing updated:** 2026-11-14

## About

Systemores treats an agent's system prompt like code that can be linted. It maps instructions onto Murray's Needs-Press model, scoring 21 behavioral dimensions, and probes how the agent holds up under simulated adversarial pressure, sycophancy and drift. A second set of checks looks at the plumbing: MCP tool schemas for annotation or injection flags, and multi-agent delegation graphs for cycles and privilege escalation.

The plugin installs into Google Antigravity, Claude Code, Gemini CLI or Cursor, or runs with `npx -y @systemores/systemores-plugin`. Three static auditors need no key: `systemores_audit_tool_integrity`, `systemores_audit_agent_graph` and `systemores_measure_drag`. Paid keys add live tools such as `systemores_stress_test_agent`, `systemores_audit_turn_live`, `systemores_evaluate_drift` and `systemores_assess_bias`, and the Team tier adds `systemores_export_dossier` for EU AI Act, NIST AI RMF, EEOC/ECOA and SOC 2 formats.

The suite is 12 tools in total. Its scores come from the vendor's own scoring engine, so treat them as a diagnostic aid rather than an external certification.

## Features

- **MCP schema audit:** Checks tool schemas for annotation and injection problems.
- **Agent graph audit:** Looks for cycles and privilege escalation in multi-agent delegation graphs.
- **21-dimension stress test:** Scores an agent persona under simulated adversarial pressure (Pro).
- **Live turn circuit breaker:** Inline check on each turn, advertised at under 250 ms (Pro).
- **Bias and drift checks:** Sweeps for EEOC, ECOA and COPPA issues and multi-turn drift (Pro).
- **Compliance dossiers:** Exports EU AI Act, NIST AI RMF and SOC 2 formatted reports (Team).

## Good for

- Review an MCP server's tool schemas before connecting it
- Check a multi-agent setup for delegation loops
- Stress test a customer-support agent's system prompt before launch
- Produce compliance paperwork for an AI agent review

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http systemores-plugin https://audit.systemores.com/api/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://audit.systemores.com/api/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "systemores-plugin": {
      "url": "https://audit.systemores.com/api/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "systemores-plugin": {
      "type": "http",
      "url": "https://audit.systemores.com/api/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "systemores-plugin": {
      "serverUrl": "https://audit.systemores.com/api/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "systemores-plugin": {
      "type": "http",
      "url": "https://audit.systemores.com/api/mcp"
    }
  }
}
```

## Tools

- `systemores_stress_test_agent`: Exposes the target agent persona to a battery of adversarial prompts (Presses) and evaluates behavioral stability using Murray's Needs-Press diagnostic model.
- `systemores_evaluate_drift`: Simulates multiple conversational turns to evaluate agent output consistency and behavioral drift over extended interactions.
- `systemores_assess_bias`: Verifies the agent's compliance with fair-lending, fair-housing, employment non-discrimination (EEOC/SIOP/ECOA), child-directed safety (COPPA), or EU AI Act (EU 2024/1689) standards.
- `systemores_measure_drag`: Measures operational latency, response length, and execution drag parameters to analyze cognitive throughput stability within the Behavioral OS ecosystem.
- `systemores_tool_integrity`: Evaluates whether the agent's system prompt establishes the behavioral conditions for safe, reliable tool use — auditing tool selection discipline, argument construction fidelity, and failure resilience when tool returns are ambiguous or erroneous.
- `systemores_audit_tool_integrity`: Audits the structural integrity, naming conventions, schema completeness, safety annotations, and injection surface of an AI agent's exposed tool definitions. Identifies malformed schemas, privilege overreach, deceptive safety hints, duplicate names, and description quality gaps. Operates entirely offline — no external API calls required.
- `systemores_audit_agent_graph`: Statically scans multi-agent execution topologies (DAGs/meshes) using DFS algorithms to detect cyclic delegation loops and privilege escalation paths from public untrusted sub-agents to backend write/admin tools.
- `systemores_generate_cohort`: Generates statistical cohorts of synthetic user personas across enterprise operational domains with IPIP-NEO-120 30-facet psychometric profiles, demographic diversity, and prompt injection payloads.
- `systemores_inject_environment_fault`: Configures dynamic chaos injection policies for tools, mock APIs, and databases during simulations (HTTP 429 rate limits, 500 errors, timeouts, 401 unauthorized, malformed JSON).
- `systemores_analyze_trace_telemetry`: Ingests standard OpenTelemetry (OTel) trace JSON payloads to detect financial token cost burn traps (> $2.50 threshold), runtime loop deadlocks between sub-agents, and cognitive latency drag hotspots (> 3000ms).
- `systemores_export_dossier`: Aggregates findings from graph audits, synthetic cohort simulations, chaos tests, and trace analytics into signed zero-retention compliance dossiers with verifiable certificate links and live SVG trust badges for EU AI Act (EU 2024/1689), NIST AI RMF 1.0, EEOC/ECOA, and SOC 2 AI Addendums.
- `systemores_audit_turn_live`: Performs real-time (~250ms) operational and behavioral turn auditing using Systemores System One. Computes policy compliance score, sycophancy probability, unauthorized tool scope, and returns an inline circuit-breaker action (DISPATCH, INTERCEPT, QUARANTINE, STRIP_TOOL).

## FAQ

### What is free?

Three static auditors run without a key: tool integrity, agent graph and cognitive drag.

### Which editors does it support?

Google Antigravity, Claude Code, Gemini CLI and Cursor, or any client through npx.

### What do paid tiers add?

Pro adds the live stress test, turn circuit breaker, drift and bias checks. Team adds dossiers, trace analysis and CI licensing.

### Do I need a key for the remote server?

The hosted endpoint is at audit.systemores.com/api/mcp; the registry lists the key as optional for the free auditors.

### Is Systemores AI Agent & MCP Security Auditor free?

Systemores AI Agent & MCP Security Auditor has a free plan, with paid plans for more usage or features.

### How do I add Systemores AI Agent & MCP Security Auditor to Claude Code?

Run this command in your terminal: claude mcp add --transport http systemores-plugin https://audit.systemores.com/api/mcp

### What are the best alternatives to Systemores AI Agent & MCP Security Auditor?

The closest alternatives to Systemores AI Agent & MCP Security Auditor are REA, Claude Code Ultimate Guide, Agent Roast, Midplane and Leash.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Agent Roast](https://ai-powered.com/mcp/agent-roast): Agent Roast is an open-source MCP server for developer tools.
- [Midplane](https://ai-powered.com/mcp/midplane): Midplane is an open-source MCP server for databases.
- [Leash](https://ai-powered.com/mcp/leash): Leash is a free MCP server for security.
- [SecureCloud](https://ai-powered.com/mcp/securecloud): SecureCloud is a free MCP server for security.
- [Tinplate Edge AI Safety, Security & EU Compliance](https://ai-powered.com/mcp/tinplate-edge-ai-safety-security-and-eu-compliance): Tinplate Edge AI Safety, Security & EU Compliance is a freemium MCP server for security.
- [Eikino](https://ai-powered.com/mcp/eikino): Eikino is a freemium MCP server for security.

---
Source: https://ai-powered.com/mcp/systemores-ai-agent-and-mcp-security-auditor
