Agent Security MCP Server

Prompt injection detection, secret scanning, permission auditing

Local serverstdio

What is the Agent Security MCP Server?

Prompt injection detection, secret scanning, permission auditing

What the server does

Security scanning, prompt injection detection, secret leak detection, and agent permission auditing for AI agent workflows. Built on the Model Context Protocol (MCP).

Credentials and setup notes

  • Node.js >= 18.0.0 - @modelcontextprotocol/sdk >= 1.12.0

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

ToolWhat it does
scan_mcp_configScan MCP server configurations for security issues (dangerous commands, exposed secrets, network exposure, container misconfigs)
detect_prompt_injectionAnalyze text for prompt injection attempts across 7 attack categories with context-aware risk scoring
validate_scope_contractCheck if agent actions comply with scope contracts (tool allowlists, file access, boundary constraints)
scan_secretsDetect leaked API keys, tokens, private keys, database URIs, and credentials in text or code
audit_agent_permissionsAudit agent configurations against role-based expectations and flag principle of least privilege violations
generate_security_reportGenerate comprehensive security assessment reports with prioritized remediation plans
detect_tool_poisoningAnalyze MCP tool definitions for hidden instructions that could manipulate agent behavior (OWASP Agentic Top 10)

How to install the Agent Security MCP Server

{
  "mcpServers": {
    "agent-security": {
      "command": "node",
      "args": ["/path/to/agent-security-mcp/src/index.js"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Node.js >= 18.0.0 - @modelcontextprotocol/sdk >= 1.12.0

Example prompts to try

  • “Use Agent Security MCP to scan mcp config.”
  • “Use Agent Security MCP to detect prompt injection.”
  • “Use Agent Security MCP to validate scope contract.”

Frequently asked questions

Prompt injection detection, secret scanning, permission auditing Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.