Agentos MCP server

Read from the package source without running it. The installed server may list more.

• attach_policy

  Attach safety policies to an agent. Policies enforce rules and constraints on agent behavior. Available policy templates: - pii-protection: Protects personally identifiable information (GDPR compliant) - rate-limiting: Prevents resource abuse through rate limits - cost-control: Prevents runaway costs from automated operations - data-deletion: Prevents accidental data loss - secrets-protection: Pre

• audit_log

  Query the audit trail for an agent. The audit log records: - Every action attempted by the agent - Policy evaluations and decisions - Approval requests and outcomes - Success/failure status - Timestamps and metadata Use for: - Debugging agent behavior - Compliance reporting - Security investigations - Performance analysis

• check_compliance

  Check an agent's compliance with regulatory frameworks. Supported frameworks: - SOC2: Service Organization Control 2 Type II - GDPR: EU General Data Protection Regulation - HIPAA: Health Insurance Portability and Accountability Act - PCI_DSS: Payment Card Industry Data Security Standard - CCPA: California Consumer Privacy Act - NIST: NIST Cybersecurity Framework - ISO27001: ISO/IEC 27001 Informati

• create_agentwrite action

  Create a new AI agent from a natural language description. The agent will be configured with appropriate policies and safety guardrails. Example usage: - "Create an agent that processes customer feedback from support emails daily" - "Build a data pipeline that backs up my Documents folder to Google Drive" - "Set up an agent to monitor our API health and alert on issues" Returns the agent specifica

• create_policywrite action

  Create a custom policy from a natural language description. Policies define rules that agents must follow. Example policies: - "Block access to customer credit card data" - "Require approval for any external API calls" - "Rate limit database queries to 100 per minute" - "Log all file deletions" Policies can be based on existing templates: - pii-protection, rate-limiting, cost-control - gdpr-compli

• deploy_agentwrite action

  Deploy an agent to start execution. Deployment environments: - local: Runs on your machine (default) - cloud: Runs on AgentOS cloud infrastructure (requires API key) Before deployment, the agent must: - Pass all policy checks - Have valid configuration - Have necessary integrations configured For scheduled agents, deployment starts the scheduler. For triggered agents, deployment enables the trigge

• get_agent_status

  Get the current status, metrics, and health of an agent. Returns: - Current status (draft, testing, deployed, paused, stopped, error) - Execution metrics (runs, success rate, errors) - Recent activity - Policy compliance stats - Resource usage

• list_templates

  Browse the library of pre-built agent and policy templates. Agent templates include: - Data processors, email assistants, database analysts - File organizers, backup agents, web scrapers - Slack bots, API monitors, report generators Policy templates include: - Security: PII protection, secrets protection, data deletion safety - Compliance: GDPR, SOC 2, HIPAA, PCI DSS - Operational: Rate limiting,

• request_approval

  Request human approval for a sensitive agent action. Use this when: - Policy requires human review before execution - Agent attempts a high-risk action - You want to add an extra safety check Approval requests are sent to designated approvers via: - Email notification - Slack notification (if configured) - Dashboard alert Requests expire after the specified time (default: 24 hours).

• test_agent

  Test an agent with a simulated scenario before deployment. This performs a dry-run that: - Validates the agent configuration - Checks all policies against the test scenario - Simulates workflow execution - Reports any policy violations or issues - Estimates resource usage and costs No actual changes are made during testing.

• Code scan43 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancerepository archived0/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Safety score

69/100

higher than 33% of 48,255 servers

Tools

10

the typical server has 7

Tools that change things

30%

typical: 0%. Fewer write tools means less an agent can break

GitHub stars

74

more than 95% of 28,688 servers

Downloads a week

52

more than 43% of 12,191 servers with a package

Agentos: common questions

Is Agentos MCP server safe?

With care: it is graded C, so read the findings first (69/100). Read the Agentos safety report

How do I install Agentos?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Agentos need an API key?

No secret keys are declared. It reads 2 settings from the environment.

Is Agentos maintained?

The last commit was 246 days ago (2026-03-03). The latest release is v1.0.1.

How does Agentos compare with other MCP servers?

safety score 69/100 (higher than 33% of 48,255 servers); tools 10 (the typical server has 7); tools that change things 30% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.