Agentos

AgentOS MCP Server

Build safe AI agents with natural language and 0% policy violations

Part of [Agent OS](https://github.com/imran-siddique/agent-os) - Kernel-level governance for AI agents

🚀 Quick Install

npx agentos-mcp-server

npm: agentos-mcp-server MCP Registry: io.github.imran-siddique/agentos

Overview

AgentOS MCP Server brings the complete Agent OS safety framework to any MCP-compatible AI assistant including Claude Desktop, GitHub Copilot, Cursor, and more. Create, deploy, and manage policy-compliant autonomous agents through natural conversation.

┌─────────────────────────────────────────────────────────────┐

│ Claude Desktop / Copilot / Cursor │ │ ┌────────────────────────────────────────────────────────┐ │ │ │ "Create an agent that..." │ │ │ └──────────────────────┬─────────────────────────────────┘ │ └─────────────────────────┼───────────────────────────────────┘ │ MCP Protocol ┌─────────────▼─────────────┐ │ 🛡️ AgentOS MCP Server │ │ │ │ • 10 Tools │ │ • Policy Engine │ │ • Approval Workflows │ │ • Audit Logging │ │ • Template Library │ └─────────────┬─────────────┘ │ ┌───────────────────┼───────────────────┐ │ │ │ ┌─────▼─────┐ ┌──────▼──────┐ ┌─────▼─────┐ │ Agents │ │ Policies │ │ Audit │ │ (Local) │ │ (Enforced) │ │ (Logged) │ └───────────┘ └─────────────┘ └───────────┘

✨ Features

🤖 Natural Language Agent Creation

User: Create an agent that processes customer feedback from support emails daily

Claude: ✅ Agent Created Successfully!

Agent: customer-feedback-processor ✅ Data Source: Email inbox via IMAP ✅ Processing: Sentiment analysis + categorization ✅ Output: Daily summary to Slack ✅ Schedule: Every day at 9 AM

Safety Policies Applied: 🛡️ PII Protection: Customer emails/names anonymized 🛡️ Rate Limiting: Max 1000 emails per run 🛡️ Human Review: Negative sentiment cases flagged

🛡️ Policy Enforcement with 0% Violations

• 6 built-in policies (PII, rate-limiting, cost-control, data-deletion, secrets, human-review)
• Real-time policy evaluation
• Automatic blocking of violations
• Clear explanations and alternatives

✅ Human-in-the-Loop Approval Workflows

• Risk-based approval requirements
• Multi-party approval for critical actions
• Email/Slack notifications
• Expiration handling

📊 Complete Audit Trail

• Every action logged immutably
• Policy evaluations recorded
• Compliance report generation
• Export for auditors

📋 Template Library

• 10+ agent templates (data processor, email assistant, backup, scraper, etc.)
• 6+ policy templates (GDPR, SOC 2, HIPAA, PCI DSS, etc.)
• Industry-specific compliance frameworks

🏛️ Compliance Ready

• SOC 2 - Security & availability controls
• GDPR - EU data protection
• HIPAA - Healthcare data privacy
• PCI DSS - Payment card security
• CCPA - California privacy
• NIST - Cybersecurity framework
• ISO 27001 - Information security
• FedRAMP - Federal authorization

🚀 Quick Start

Step 1: Configure Claude Desktop

Add to your claude_desktop_config.json:

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:

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

Claude will:

1. Create the agent with appropriate configuration
2. Suggest safety policies based on the task
3. Let you test before deployment
4. Deploy with monitoring enabled

💬 Example Conversations

Creating a Data Processing Agent

User: I need an agent that processes customer feedback from support emails daily

Claude: ✅ Agent Created Successfully!

Agent: customer-feedback-processor ID: a1b2c3d4-e5f6-7890-abcd-ef1234567890 Status: draft Language: python

Task: Process customer feedback from support emails daily

Workflow Steps:

1. connect_email: email.connect
2. process_data: execute
3. output_results: output

Safety Policies Applied: 🛡️ PII Protection: Customer emails/names anonymized 🛡️ Rate Limiting: Max 1000 emails per run 🛡️ Human Review: Negative sentiment cases flagged

Next Steps:

1. Use test_agent to run a dry-run test
2. Use attach_policy to add more safety policies
3. Use deploy_agent when ready to run

Testing Before Deployment

User: Test this agent with a scenario of processing 100 emails

Claude: ✅ Test PASSED

Agent: customer-feedback-processor Scenario: Process 100 customer emails Mode: Dry Run (no changes)

Configuration Check: ✅ Valid Workflow Check: ✅ Valid (3 steps)

Policy Evaluation: ✅ No violations detected

Warnings: ⚠️ PII access logged

Resource Estimates:

• Duration: ~30 seconds
• Cost: $0.05

Next Step: Use deploy_agent to deploy this agent.

Checking Compliance

User: Check if this agent is SOC 2 compliant

Claude: # Compliance Report: SOC2

Agent: customer-feedback-processor Framework: SOC2 Date: 2026-01-30

Summary

✅ COMPLIANT Score: 100% (4/4 controls passed)

Control Assessment

✅ CC6.1: Logical Access Controls Restrict logical access to information assets Evidence: Policy enforcement enabled, Access logging active

✅ CC6.6: Security Event Monitoring Detect and respond to security events Evidence: Audit logging enabled, Event timestamps recorded

✅ CC7.2: Incident Response Respond to security incidents Evidence: Human review enabled, Escalation procedures in place

✅ CC8.1: Change Management Manage changes to system components Evidence: Deployment approval required, Version control enabled

Creating Custom Policies

User: Create a policy that blocks access to customer credit card data

Claude: ✅ Custom Policy Created

Policy: Block Access To Customer ID: custom-a1b2c3d4 Category: security

Description: Block access to customer credit card data

Rules Generated (1):

🟠 custom_block_rule [high] Block actions based on: block access to customer credit card data Action: deny

Usage:

1. Attach to agent: attach_policy with policyId "custom-a1b2c3d4"
2. Test enforcement: test_agent with policy scenarios
3. View active policies: get_agent_status

🔧 Available Tools

Tool Details

create_agent

Create a new AI agent from a natural language description with automatic policy recommendations.

Parameters:

attach_policy

Attach safety policies to an agent with conflict detection.

Parameters:

test_agent

Run a dry-run test with simulated scenarios.

Parameters:

deploy_agent

Deploy an agent to local or cloud environment.

Parameters:

check_compliance

Check an agent against regulatory frameworks.

Parameters:

📋 Policy Templates

Built-in Security Policies

Compliance Templates

🤖 Agent Templates

Data Processing

Communication

| email-assistant | Monitors and processes emails | pii-protec