MCP Server for Claude Desktop

Build safe AI agents through natural conversation with Claude.
10 tools, 8 compliance frameworks, 0% policy violations.

The AgentOS MCP Server brings kernel-level agent governance directly into Claude Desktop. Instead of writing code or configuration files, simply describe what you want in natural language — Claude will create safe, policy-compliant agents with built-in safety guarantees.

🤖

Natural Language Creation

Describe your agent in plain English. Claude handles the rest — configuration, policies, and deployment.

🛡️

0% Policy Violations

Every action validated against policies in real-time. Dangerous operations blocked automatically.

✅

Human-in-the-Loop

Approval workflows for sensitive actions. Risk-based routing with multi-party approval support.

📊

Complete Audit Trail

Every action logged immutably. Generate compliance reports for SOC 2, GDPR, HIPAA, and more.

📋

Template Library

10+ agent templates and 6+ policy templates. From data processing to compliance frameworks.

🏛️

8 Compliance Frameworks

SOC 2, GDPR, HIPAA, PCI DSS, CCPA, NIST, ISO 27001, FedRAMP — all built-in.

✓ SOC 2 ✓ GDPR ✓ HIPAA ✓ PCI DSS ✓ CCPA ✓ NIST ✓ ISO 27001 ✓ FedRAMP

Step 1: Configure Claude Desktop

Add to your claude_desktop_config.json:

📍 Config File Locations

Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "agentos": {
      "command": "npx",
      "args": ["-y", "@agentos/mcp-server"],
      "env": {
        "AGENTOS_POLICY_MODE": "strict"
      }
    }
  }
}

Step 2: Restart Claude Desktop

Close and reopen Claude Desktop to load the MCP server.

Step 3: Start Building Agents!

Just ask Claude naturally:

👤 You

Create an agent that backs up my Documents folder to Google Drive every night

🤖 Claude (using AgentOS)

✅ Agent Created Successfully!

Agent: documents-backup-agent
Schedule: Every day at 2 AM

Safety Policies Applied:

🛡️ Cost Control: Max $10/day cloud storage
🛡️ Data Protection: Encryption in transit
🛡️ Audit Logging: All operations tracked

Would you like me to run a test backup first?

Tool	Description
`create_agent`	Create agent from natural language description with auto-suggested policies
`attach_policy`	Attach safety policies to agents with conflict detection
`test_agent`	Dry-run test before deployment with scenario simulation
`deploy_agent`	Deploy agent locally or to cloud with approval workflows
`get_agent_status`	Get agent status, metrics, and recent activity
`list_templates`	Browse 10+ agent and 6+ policy templates
`request_approval`	Create approval request for sensitive actions
`audit_log`	Query immutable audit trail with filtering
`create_policy`	Create custom policy from natural language
`check_compliance`	Check against 8 compliance frameworks with reports